This article introduces a new hybrid intake procedure developed for posttraumatic stress disorder (PTSD) screening, which combines an automated textual assessment of respondents’ self-narratives and item-based measures that are administered consequently. Text mining technique and item response modeling were used to analyze long constructed response (i.e., self-narratives) and responses to standardized questionnaires (i.e., multiple choices), respectively. The whole procedure is combined in a Bayesian framework where the textual assessment functions as prior information for the estimation of the PTSD (...) latent trait. The purpose of this study is twofold: first, to investigate whether the combination model of textual analysis and item-based scaling could enhance the classification accuracy of PTSD, and second, to examine whether the standard error of estimates could be reduced through the use of the narrative as a sort of routing test. With the sample at hand, the combination model resulted in a reduction in the misclassification rate, as well as a decrease of standard error of latent trait estimation. These findings highlight the benefits of combining textual assessment and item-based measures in a psychiatric screening process. We conclude that the hybrid test design is a promising approach to increase test efficiency and is expected to be applicable in a broader scope of educational and psychological measurement in the future. (shrink)

Techniques of text data analysis have been known for many years and commonly used in many areas of life. Text mining enables, among others, the acquisition of information from the text, its filtering, and studying of similarities and relationships. The aim of this paper is to design a method that would make it possible to assess the health quality of dietary supplements, on the basis of text mining techniques. A fictional plant-based product was (...) used in the study, which was compared with other products containing at least one of the tested ingredients registered in the years 2007–2019 in the register of dietary supplements kept by the Chief Sanitary Inspectorate (GIS), which were given either the “consistent” or “to be clarified” status. The obtained results concern the frequency of occurrence of the individual ingredients (St John’s wort/Hypericum, melissa, rose root/Rhodiola) in other products, considering their status in the register. The data thus obtained was subjected to classical statistical analysis in order to find correlations between the presence of a given ingredient and the product status. In view of the obtained results, the text mining analysis may be considered as a helpful tool in the process of internal risk assessment performed by manufacturers of dietary supplements. (shrink)

Cause-related marketing has risen to become a popular strategy to increase business value through profit-motivated giving. Despite the growing number of articles published in the last decade, no comprehensive analysis of the most discussed constructs of cause-related marketing is available. This paper uses an advanced Text Mining methodology to conduct a comprehensive analysis of 246 articles published in 40 different journals between 1988 and 2013 on the subject of cause-related marketing. Text Mining also allows (...) quantitative analyses to be performed on the literature. For instance, it is shown that the most prominent long-term topics discussed since 1988 on the subject are “brand-cause fit”, “law and Ethics”, and “corporate and social identification”, while the most actively discussed topic presently is “sectors raising social taboos and moral debates”. The paper has two goals: first, it introduces the technique of CTM to the Marketing area, illustrating how Text Mining may guide, simplify, and enhance review processes while providing objective building blocks to be used in a review; second, it applies CTM to the C-RM field, uncovering and summarizing the most discussed topics. Mining text, however, is not aimed at replacing all subjective decisions that must be taken as part of literature review methodologies. (shrink)

Public’s concern about poor animal welfare provided by intensive farming systems has increased over the last decades. This study reviewed the interest of the scientific research on the pain issue in pig production to assess if the societal instances may be a driving force for the research activity. A literature search protocol was set up to identify the peer-reviewed papers published between 1970 and 2017 that covered the topic of ‘pain in pigs’ using Scopus®, database of Elsevier©. One hundred and (...) thirty papers were selected and they were mainly focused on the practice of castration followed by tail docking. The scientific community first focused on these painful practices as a way to improve production efficiency and quality issues while more recently, due to the increased pressure by the public opinion, turned its interest towards the search of alternative solutions. A text mining analysis on the abstract of the selected papers clearly indicated the effort of the research to explore solutions to alleviate pain. Evocative words of this target were the selected terms ‘pharmacological analgesic’ and ‘anaesthetic treatments’. The text mining highlighted vocalizations as the main pain indicators in pigs as this term was frequently associated to ‘acute stress’. Ethical issues were a minor research topic in the scientific literature on pig breeding but in the short run, they are supposed to become a major subject to justify the acceptance of the modern production systems at the eyes of the consumers. (shrink)

A recent systematic review of Machine Learning (ML) approaches to health data, containing over 100 studies, found that the most investigated problem was mental health (Yin et al., 2019). Relatedly, recent estimates suggest that between 165,000 and 325,000 health and wellness apps are now commercially available, with over 10,000 of those designed specifically for mental health (Carlo et al., 2019). In light of these trends, the present chapter has three aims: (1) provide an informative overview of some of the recent (...) work taking place at the intersection of text mining and mental health so that we can (2) highlight and analyze several pressing ethical issues that are arising in this rapidly growing field and (3) suggest productive directions for how these issues might be better addressed within future interdisciplinary work to ensure the responsible development of text mining approaches in psychology generally, and in mental health fields, specifically. In Section 1, we review some of the recent literature on text-mining and mental health in the contexts of traditional experimental settings, social media, and research involving electronic health records. Then, in Section 2, we introduce and discuss ethical concerns that arise before, during, and after research is conducted. Finally, in Section 3, we offer several suggestions about how ethical oversight of text-mining research might be improved to be more responsive to the concerns mapped out in Section 2. (shrink)

With the emergence of online communities, more and more people are participating in online technology communities to meet personalized learning needs. This study aims to investigate whether and how male and female users behave differently in online technology communities. Using text data from Python Technology Community, through LDA (Latent Dirichlet Allocation) model, sentiment analysis and regression analysis, this paper reveals the different topics of male and female users in the online technology community, their sentimental tendencies and activity (...) under different topics, and their correlation and their mutual influence. The results show that: (1) Male users tend to provide information help, while female users prefer to participate in the topic of making friends and advertising. (2) When communicating in the technology community, male and female users mostly express positive emotions, but female users express positive emotions more frequently. (3) Different emotional tendencies of male and female users under different topics have different effects on their activity in the community. The activity of female users is more susceptible to emotional orientation. (shrink)

Interaction mining is about discovering and extracting insightful information from digital conversations, namely those human?human information exchanges mediated by digital network technology. We present in this article a computational model of natural arguments and its implementation for the automatic argumentative analysis of digital conversations, which allows us to produce relevant information to build interaction business analytics applications overcoming the limitations of standard text mining and information retrieval technology. Applications include advanced visualisations and abstractive summaries.

At the heart of Mizrahi’s project lies a sociological narrative concerning the recent history of philosophers’ negative attitudes towards scientism. Critics (e.g. de Ridder (2019), Wilson (2019) and Bryant (2020)), have detected various empirical inadequacies in Mizrahi’s methodology for discussing these attitudes. Bryant (2020) points out one of the main pertinent methodological deficiencies here, namely that the mere appearance of the word ‘scientism’ in a text does not suffice in determining whether the author feels threatened by it. Not all (...) philosophers use the term in ‘inherently negative’ (29) or pejorative ways. In this paper, I not only corroborate Bryant’s critical claim, but argue that Mizrahi’s response to this part of Bryant’s objection is inadequate. (shrink)

The ERC-funded ModERN project is investigating 18th-century authorship practices using data-rich computational techniques to examine the digital archive of the Enlightenment period. This paper explores the use of new large-scale text reuse detection and network analysis to identify intertextual 'influencers' in a large heterogeneous collection of 18th-century French texts.

In this paper we look at the manual analysis of arguments and how this compares to the current state of automatic argument analysis. These considerations are used to develop a new approach combining a machine learning algorithm to extract propositions from text, with a topic model to determine argument structure. The results of this method are compared to a manual analysis.

Financial risks are among the most important risks in the construction industry projects, which significantly impact project objectives, including project cost. Besides, financial risks have many interactions with each other and project parameters, which must be taken into account to analyze risks correctly. In addition, a source of financial risks in a project is the contract, which is the most important project document. Identifying terms related to financial risks in a contract and considering their effects on the risk management process (...) is an essential issue that has been neglected. Hence, an integrated model for evaluating financial risks and their related contractual clauses were presented. To this end, the effect of financial risks on the project cost was simulated using a system dynamics model. Moreover, terms related to financial risks in a contract text were identified and extracted using text mining, and their effect was included in the system dynamics model. The model was implemented in a hospital construction project in Tehran as a case study, and its results were analyzed. The innovation of the research is integrating text mining and the system dynamics model to investigate the effect of financial risks and related contractual clauses on the project cost. (shrink)

Argumentation mining is an application of natural language processing (NLP) that emerged a few years ago and has recently enjoyed considerable popularity, as demonstrated by a series of international workshops and by a rising number of publications at the major conferences and journals of the field. Its goals are to identify argumentation in text or dialogue; to construct representations of the constellation of claims, supporting and attacking moves (in different levels of detail); and to characterize the patterns of (...) reasoning that appear to license the argumentation. Furthermore, recent work also addresses the difficult tasks of evaluating the persuasiveness and quality of arguments. Some of the linguistic genres that are being studied include legal text, student essays, political discourse and debate, newspaper editorials, scientific writing, and others. The book starts with a discussion of the linguistic perspective, characteristics of argumentative language, and their relationship to certain other notions such as subjectivity. Besides the connection to linguistics, argumentation has for a long time been a topic in Artificial Intelligence, where the focus is on devising adequate representations and reasoning formalisms that capture the properties of argumentative exchange. It is generally very difficult to connect the two realms of reasoning and text analysis, but we are convinced that it should be attempted in the long term, and therefore we also touch upon some fundamentals of reasoning approaches. Then the book turns to its focus, the computational side of mining argumentation in text. We first introduce a number of annotated corpora that have been used in the research. From the NLP perspective, argumentation mining shares subtasks with research fields such as subjectivity and sentiment analysis, semantic relation extraction, and discourse parsing. Therefore, many technical approaches are being borrowed from those (and other) fields. We break argumentation mining into a series of subtasks, starting with the preparatory steps of classifying text as argumentative (or not) and segmenting it into elementary units. Then, central steps are the automatic identification of claims, and finding statements that support or oppose the claim. For certain applications, it is also of interest to compute a full structure of an argumentative constellation of statements. Next, we discuss a few steps that try to 'dig deeper': to infer the underlying reasoning pattern for a textual argument, to reconstruct unstated premises (so-called 'enthymemes'), and to evaluate the quality of the argumentation. We also take a brief look at 'the other side' of mining, i.e., the generation or synthesis of argumentative text. The book finishes with a summary of the argumentation mining tasks, a sketch of potential applications, and a—necessarily subjective—outlook for the field. Table of Contents: Preface / Acknowledgments / Introduction / Argumentative Language / Modeling Arguments / Corpus Annotation / Finding Claims / Finding Supporting and Objecting Statements / Deriving the Structure of Argumentation / Assessing Argumentation / Generating Argumentative Text / Summary and Perspectives / Bibliography / Authors' Biographies / Index. (shrink)

In coal mining technology systems, it is very important to acquire, store, and represent basic geological data comprehensively and accurately. Based on the current working mode and information level in mining geology at coal mines, this paper proposes a process of building basic geological database for modeling of coal mines by using existing results’ data of mining geology and develops the efficient program for getting the basic geological data from the important 2D plane drawings’ achievement at mines, (...) such as the contour maps of mine coal seam floors, geological cross-sections, underground drilling results, and geological survey results, based on AutoLISP, which is a programming language for the secondary development of AutoCAD. The obtained data in general text format is stored and managed by the MongoDB database, which realizes the storage, query, analysis, and correction of massive data of geological objects in the space of the underground coalmine. The application results show that compared with the previous data acquisition methods such as manual input and graphic transformation attribute, the extraction of spatial and attribute data from the existing mine 2D plane drawings by programming can effectively avoid the prominent problems such as artificial gross error, distortion of graph conversion, and different database structure, make the obtained spatial geological data more comprehensive, accurate, and effective, and, meanwhile, increase the rate by more than 60%, which plays an important role in data support for the construction of the geological modeling systems for transparent mines. (shrink)

One of the new topics that has attracted the attention of researchers in recent years is neuro-marketing. The purpose of the present study is to achieve an insight into the progress of studies on neuro-marketing through review of scientific articles in this field with methodology text-mining. A total of 394 articles were selected between 2005 and 2017 using the search for “neuro-marketing” in valid databases. By reviewing the title, abstract, and keywords at various stages of screening, the researchers (...) selected 311 articles related to the neuro-marketing topic in order to carry out the text mining process. Then, pre-processing of data was performed and using cluster analysis, 6 optimal clusters were obtained according to Davis Bouldin index. Using the multi-attribute decision-making technique, the most important roots were ranked in each cluster. The results showed that interest in research on neuro-marketing has increased in recent years and clusters created around topics such as marketing strategies, advertising and video ads, ethical issues, advertising message components, neuroscience in marketing, economics and consumer behavior, and decision making and brand selection. The study shows that the researchers’ attention is moving from the concepts and principles of the use of neuroscience in marketing, economics and consumer behavior to design and develop marketing strategies using neuroscience. (shrink)

The concept of apublic energy fieldis central to public administration discourse theory. Its main idea is the facilitation of dialog between government and the public, on the basis of equality, to construct a public policy consensus. In contemporary society, social media provides new and distinctive channels for such interactions. Social media can, therefore, be conceived as a novel type ofpublic energy field. Since the outbreak of the COVID-19 pandemic, interactions between the Chinese government and the Chinese public (whether located in (...) China or abroad) have been acutely reflected through WeChat official accounts. This article focuses on the COVID-19 pandemic and, through social media text mining and processing, analyzes the text topics and emotions covered. Basic principles of discourse validity, regarding this public energy field and two guarantee conditions, are applied to analyze the information exchange and dialog between the government and the public on COVID-19 through WeChat official accounts. It was found that the government’s WeChat official accounts have not yet formed a harmonious dialog space to balance the public energy field, and that the interaction between the government and the public has to be improved. The government’s social discourse had a significant influence on the public’s social discourse. Using text analysis, the study found that the government has published information on 11 topics related to the prevention and control of the pandemic. It can be argued that the public energyfieldpresented by both the government and the public effectively portrayed and reflected the actual situation of the pandemic in China. (shrink)

Because obituaries are succinct and explicitly intended to summarize their subjects’ lives, they may be expected to include only the features that the author finds most salient but also to signal to others in the community the socially-recognized aspects of the deceased’s character. We begin by reviewing studies 1 and 2, in which obituaries were carefully read and labeled. We then report study 3, which further develops these results with a semi-automated, large-scale semantic analysis of several thousand obituaries. Geography, (...) gender, and elite status all turn out to be associated with the virtues and values associated with the deceased. (shrink)

In lieu of an abstract, here is a brief excerpt of the content:Reviewed by:All Mine!: Happiness, Ownership, and Naming in Eleventh-Cenury China by Stephen OwenNguyen T. Thanh-Huyen (bio)All Mine!: Happiness, Ownership, and Naming in Eleventh-Cenury China. By Stephen Owen. New York: Columbia University Press, 2021. Pp. 208. Paperback $30.00, isbn 978-0-231-20311-1. Reading Stephen Owen's new book, All Mine!: Happiness, Ownership, and Naming in Eleventh-Century China (hereafter All Mine!), many readers will find that the perspectives of eleventh-century Song scholar-officials on finding (...) happiness in material things are still highly relevant to the increasingly materialistic culture in China and the world in the present day. Under the Song dynasty, the pursuit of happiness through material objects is "what contemporaries themselves recognized as uncomfortable topics" (p. 14). In writing this book, Owen attempts to survey a literary phenomenon in which material-contingent happiness permeated Song literature despite the moral surveillance of classical ideology on happiness and ownership that stretched back to the Lunyu (Analects of Confucius). At the same time, the author elucidates how material-contingent happiness in literature drove and was driven by the sociocultural changes and the growth of commercialization in the Song. All Mine! is a fine balance between literary study and intellectual history. Owen's approach tends to be all-inclusive, as he covers a diverse range of genres (including prose, poetry, miscellany, and biography) and texts with which readers generally have different levels of familiarity. For every text, Owen provides thorough explanation on its background, allusions, and references, while also offering in-depth cultural, aesthetic, and structural analysis. He calls our attention to the subtle differences between similar texts, such as the biographies of Ouyang Xiu 歐陽脩 and Tao Yuanming 陶淵明, to show how they deliver entirely different ideas about happiness and ownership and signal a radical transition from the old to a new world of values. Regarding intellectual history, the book studies the conflicts between different discourses on happiness. Owen reveals different forces of censorship against happiness of acquisition and ownership, presenting them especially clearly with Ouyang Xiu's stories in Chapter 1 ("The Biography of the Retired Layman Six") and Chapter 2 ("The Magistrate of Peach Blossom Spring"). The author also pays close attention to the act of naming as a form of ownership. As he points out, the process of Song literati trying to "get the right name" for objects and sites often converged with the process of elaborating different [End Page 1] person-thing relationships based on the social status of the owner and the characteristics of the object of ownership, thereby grounding the principles for judging the morality of material-contingent happiness. Readers can also see the happiness-ownership paradox in literature as closely related to the commercialization of elite-praised goods that was flourishing in Song society. This validates Owen's choice "to think of cultural and historical phenomena as ecosystems or solar systems in constant change, each particular changed by and changing the whole" (p. 13). Perhaps the most impressive chapters in the book are 3 and 5, which deal with the Song's perspective on ownership as transient and unstable, and its relationship with happiness. Chapter 3 explores the pervasive awareness that "things are held by power, not by right" (p. 67). The source of "power" could be financial, social, political, and military advantage, or something humans can't control, like death. Owen relates many sad Song stories of elites whose things were taken by someone with greater power. The most interesting one is perhaps that of Su Dongpo 苏東坡 and his "Nine Blossoms Mountain in a Jug," in which Su was not willing to give up the little world that he attached to this rock mountain, despite being very conscious about the dangers of possession. "It is alright if the superior man lets his interests be temporarily invested in things, but it is not alright if he lets his interest remain in those things," the author writes (p. 72). Chapter 3 contains many examples of "names as a form of ownership." Ownership of physical things can be transient and infringeable, but the writings on names of objects and sites by famous Song literati like Ouyang Xiu and Su Dongpo... (shrink)

In light of Taiwan's extensive exposure to the Chinese Communist Party's "cognitive domain infiltration warfare," this paper proposes new response mechanisms and strategies for cybersecurity and national defense. The focus is primarily on assessing the CCP's cognitive infiltration tactics to develop policy recommendations in cybersecurity linguistics. These recommendations are intended to serve as a reference for future national defense and information security policies. Within the constraints of limited resources, this study attempts to provide an integrated analysis method combining qualitative (...) and quantitative tools. This method involves text mining in cybersecurity linguistics, focusing on "textual content" and incorporating discourse deconstruction. The aim is to enhance the success rate in identifying and defining contentious information in cognitive warfare, thereby offering policy suggestions. -/- Keywords: Cognitive Infiltration, Big Data Corpus, Cybersecurity Linguistics, Text Mining Analysis, Narrative Language Deconstruction. (shrink)

Along with urban development globally, the NIMBY crisis has been a complex social problem, which requires urgent remedial action. The inevitable management of Municipal Solid Waste has been one of the toughest risk management tasks in the worldwide modernization process. At present, certain fuzzy and unstructured results and methods have been formed for MSW-NIMBY crisis response, mainly focusing on the sociology and politics which scatter in complex and sensitive reports and news. Aiming at enhancing the effectiveness of data mining (...) from specific sparse text of MSW-NIMBY crisis, an improved knowledge extraction method is developed. Through rule-based text mining and complex network analysis, the Entity Relationship network of MSW-NIMBY crisis is reconstructed. Meanwhile, a novel transitivity for relationship between entities in semantic analysis is proposed to improve the feasibility and accuracy of information extraction. Characteristics and regularity of MSW-NIMBY crisis evolution and experience of crisis governance could be identified effectively. Results show that knowledge integration and ER transitivity can enhance knowledge recognition and major other factors, which could help formulate the governance strategies of NIMBY crisis from academic texts. (shrink)

Argumentation mining aims to automatically detect, classify and structure argumentation in text. Therefore, argumentation mining is an important part of a complete argumentation analyisis, i.e. understanding the content of serial arguments, their linguistic structure, the relationship between the preceding and following arguments, recognizing the underlying conceptual beliefs, and understanding within the comprehensive coherence of the specific topic. We present different methods to aid argumentation mining, starting with plain argumentation detection and moving forward to a more structural (...) analysis of the detected argumentation. Different state-of-the-art techniques on machine learning and context free grammars are applied to solve the challenges of argumentation mining. We also highlight fundamental questions found during our research and analyse different issues for future research on argumentation mining. (shrink)

Education public opinion information management is an important research focus in the field of Education Data Mining. In this paper, we classify the education data information based on the traditional Flat-OCC model. From the cognitive psychology perspective, we identify up to 12 kinds of emotions, including sadness and happiness. In addition, the EMO-CBOW model is also proposed in this paper to further identify emotion by using various emoticons in educational data sets. The empirical result shows that the proposed Flat-OCC (...) model can classify and identify the emotion of education public opinion data well; and for the recognition of educational emotion classification, the categorization accuracy of the Flat-OCC+EMO-CBOW model is significantly higher than that of a single Flat-OCC model, which reveals that the emotional-pack-based model we propose can enhance our benchmark model. (shrink)

Purpose This study aims to analyze how English-language versions of e-newspapers in the first two countries affected, China and Japan, which are non-English-speaking countries and have different socio-economic and political settings, have highlighted Coronavirus disease 2019 pandemic news and informed the global community. Design/methodology/approach A text-mining approach was used to explore experts’ thoughts as published by the two leading English-language newspapers in China and Japan from January to March 2020. This study analyzes the Opinion section, which mainly comprises (...) editorial and the op-ed section. The current study groups all editorial discussions and highlights into ten major aspects, which cover health, economy, politics, culture and others. Findings Within the first three months, the media in both China and Japan shifted their focus from health and preparedness to the economy, politics and social welfare. Governance and social welfare were key concerns in China’s news media, while, in contrast, global politics received the highest level of attention from experts in Japan’s news media. Environment and technologies aspects did not receive much attention by the expert’s columns. Originality/value At the initial stage of a world crisis, how leading nations and initially affected nations deal with the problem, how media play their role and guide mass population with experts’ thoughts are highlighted here. The understanding developed in this study can provide guidance to news media in other countries in playing effective roles in the management of this health crisis and catastrophes. (shrink)

This paper presents the results of an empirical study following up on Mizrahi (2021). Using the same methods of text mining and corpus analysis used by Mizrahi (2021), we test empirically a philosophical account of scientific progress that Mizrahi (2021) left out of his empirical study, namely, the so-called functional-internalist account of scientific progress according to which the aim or goal or scientific research is to solve problems. In general, our results do not lend much empirical evidence (...) in support of the problem-solving model of scientific progress over the other philosophical accounts of scientific progress (namely, the epistemic, noetic, and semantic accounts of scientific progress) tested in Mizrahi (2021) and in this follow-up study. Of all the subjects in the JSTOR database we have tested in this study, however, Mathematics is an interesting exception as far as the problem-solving model of scientific progress is concerned. For, in Mathematics alone, we have found that there is significantly more talk of the aims and/or goals of research in terms of solutions than in terms of truth, knowledge, or understanding. (shrink)

Modeling law search and retrieval as prediction problems has recently emerged as a predominant approach in law intelligence. Focusing on the law article retrieval task, we present a deep learning framework named LamBERTa, which is designed for civil-law codes, and specifically trained on the Italian civil code. To our knowledge, this is the first study proposing an advanced approach to law article prediction for the Italian legal system based on a BERT (Bidirectional Encoder Representations from Transformers) learning framework, which has (...) recently attracted increased attention among deep learning approaches, showing outstanding effectiveness in several natural language processing and learning tasks. We define LamBERTa models by fine-tuning an Italian pre-trained BERT on the Italian civil code or its portions, for law article retrieval as a classification task. One key aspect of our LamBERTa framework is that we conceived it to address an extreme classification scenario, which is characterized by a high number of classes, the few-shot learning problem, and the lack of test query benchmarks for Italian legal prediction tasks. To solve such issues, we define different methods for the unsupervised labeling of the law articles, which can in principle be applied to any law article code system. We provide insights into the explainability and interpretability of our LamBERTa models, and we present an extensive experimental analysis over query sets of different type, for single-label as well as multi-label evaluation tasks. Empirical evidence has shown the effectiveness of LamBERTa, and also its superiority against widely used deep-learning text classifiers and a few-shot learner conceived for an attribute-aware prediction task. (shrink)

This article reports a corpus-aided ecological discourse analysis of texts from an international mining company and an environmental advocacy group regarding a proposal to build a massive open-pit copper mine in the Santa Rita Mountains of Arizona, USA. The analysis details the grammatical and semantic clusters within the controversial environmental debate and how these clusters reflect the values and beliefs of each group as well as their conceptualization of the mountains and the environment. The integration of the (...) ecolinguistic framework with corpus linguistic methods of keyword analysis as well as part of speech and semantic tag analysis facilitated the identification of clusters of linguistic features perpetuating a dominant and ultimately destructive cultural discourse that places humans in a role of dominion and authority over the environment in the company texts. In contrast, clusters within the oppositional discourse forwarded by the environmental group promote the aesthetic value of the land and a need for responsible environmental stewardship. (shrink)

This release includes the code and supplementary information mentioned in: Malaterre, Christophe & Martin Léonard. 2023. "Charting the Territories of Epistemic Concepts in the Practice of Science: A Text-Mining Approach", British Journal for the Philosophy of Science.

Available corpora for Argument Mining differ along several axes, and one of the key differences is the presence (or absence) of discourse markers to signal argumentative content. Exploring effective ways to use discourse markers has received wide attention in various discourse parsing tasks, from which it is well-known that discourse markers are strong indicators of discourse relations. To improve the robustness of Argument Mining systems across different genres, we propose to automatically augment a given text with discourse (...) markers such that all relations are explicitly signaled. Our analysis unveils that popular language models taken out-of-the-box fail on this task; however, when fine-tuned on a new heterogeneous dataset that we construct (including synthetic and real examples), they perform considerably better. We demonstrate the impact of our approach on an Argument Mining downstream task, evaluated on different corpora, showing that language models can be trained to automatically fill in discourse markers across different corpora, improving the performance of a downstream model in some, but not all, cases. Our proposed approach can further be employed as an assistant tool for better discourse understanding. (shrink)

With the continuous progress and penetration of automated data collection technology, enterprises and organizations are facing the problem of information overload. The demand for expertise in data mining and analysis is increasing. Self-efficacy is a pivotal construct that is significantly related to willingness and ability to perform a particular task. Thus, the objective of this study is to develop an instrument for assessing self-efficacy in data mining and analysis. An initial measurement list was developed based on (...) the skills and abilities about executing data mining and analysis, and expert recommendations. A useful sample of 103 university students completed the online survey questionnaire. A 19-item four-factor model was extracted by exploratory factor analysis. Using the partial least squares-structural equation modeling technique, the model was cross-examined. The instrument showed satisfactory reliability and validity. The proposed instrument will be of value to researchers and practitioners in evaluating an individual’s abilities and readiness in executing data mining and analysis. (shrink)

According to the PubMed resource from the U.S. National Library of Medicine, over 750,000 scientific articles have been published in the ~5000 biomedical journals worldwide in the year 2007 alone. The vast majority of these publications include results from hypothesis-driven experimentation in overlapping biomedical research domains. Unfortunately, the sheer volume of information being generated by the biomedical research enterprise has made it virtually impossible for investigators to stay aware of the latest findings in their domain of interest, let alone to (...) be able to assimilate and mine data from related investigations for purposes of meta-analysis. While computers have the potential for assisting investigators in the extraction, management and analysis of these data, information contained in the traditional journal publication is still largely unstructured, free-text descriptions of study design, experimental application and results interpretation, making it difficult for computers to gain access to the content of what is being conveyed without significant manual intervention. In order to circumvent these roadblocks and make the most of the output from the biomedical research enterprise, a variety of related standards in knowledge representation are being developed, proposed and adopted in the biomedical community. In this chapter, we will explore the current status of efforts to develop minimum information standards for the representation of a biomedical experiment, ontologies composed of shared vocabularies assembled into subsumption hierarchical structures, and extensible relational data models that link the information components together in a machine-readable and human-useable framework for data mining purposes. (shrink)

Topic modeling—a text‐mining technique often used to uncover thematic structures in large collections of texts—has been increasingly frequently used in the context of the analysis of scholarly output. In this study, we construct a corpus of 19,488 texts published since 1971 in seven leading journals in the field of bioethics and philosophy of medicine, and we use a machine learning algorithm to identify almost 100 topics representing distinct themes of interest in the field. On the basis of (...) intertopic correlations, we group the content‐based topics into eight clusters, thus providing a novel, fine‐grained intellectual map of bioethics and philosophy of medicine. Moreover, we conduct a number of diachronic analyses, examining how the “prominence” of different topics has changed across time. In this way, we are able to observe the distinct patterns in which bioethics and philosophy of medicine have evolved and changed their focus over the past half a century. (shrink)

While the empirical evidence pointing to a gender gap in professional, academic philosophy in the English-speaking world is widely accepted, explanations of this gap are less so. In this paper, we aim to make a modest contribution to the literature on the gender gap in academic philosophy by taking a quantitative, corpus-based empirical approach. Since some philosophers have suggested that it may be the argumentative, “logic-chopping,” and “paradox-mongering” nature of academic philosophy that explains the underrepresentation of women in the discipline, (...) our research questions are the following: Do men and women philosophers make different types of arguments in their published works? If so, which ones and with what frequency? Using data mining and text analysis methods, we study a large corpus of philosophical texts mined from the JSTOR database in order to answer these questions empirically. Using indicator words to classify arguments by type, we search through our corpus to find patterns of argumentation. Overall, the results of our empirical study suggest that women philosophers make deductive, inductive, and abductive arguments in their published works just as much as male philosophers do, with no statistically significant differences in the proportions of those arguments relative to each philosopher’s body of work. (shrink)

Despite the popularity of the employment interview in the employee selection literature and organizational talent selection process, few have examined the comments interviewers give after each interview. This study investigated the predictability of the match between interviewer post-interview notes and radar charts from job analysis on the candidate’s later career performance using text mining techniques and data from one of the largest internet-based technology companies in China. A large sample of 7,650 interview candidates who passed the interviews (...) and joined the company was obtained to show that the number of job-related capabilities interviewers mentioned in their notes was positively related to candidate’s job performance, the number of promotions, and negatively related to turnover. Moreover, the dimensions of the radar chart from job analysis covered in the interview moderated the predictability of interview post-interview notes. Our results indicated that a smaller number of radar chart dimensions by which interviewers assessed the candidates in the interview positively moderated candidates’ promotion for product development jobs, and negatively moderated turnover for technical jobs. The implications of these results for structured interview research in both theory and practice are discussed. (shrink)

More and more tourists are sharing their travel feelings and posting their real experiences on the Internet, generating tourism big data. Online travel reviews can fully reflect tourists’ emotions, and mining and analyzing them can provide insight into the value of them. In order to analyze the potential value of online travel reviews by using big data technology and machine learning technology, this paper proposes an improved support vector machine algorithm based on travel consumer sentiment analysis and builds (...) an Hadoop Distributed File System system based on Map-Reduce model. Firstly, Internet travel reviews are pre-processed for sentiment analysis of the review text. Secondly, an improved SVM algorithm is proposed based on the main features of linear classification and kernel functions, so as to improve the accuracy of sentiment word classification. Then, HDFS data nodes are deployed on the basis of Hadoop platform with the actual tourism application context. And based on the Map-Reduce programming model, the map function and reduce function are designed and implemented, which greatly improves the possibility of parallel processing and reduces the time consumption at the same time. Finally, an improved SVM algorithm is implemented under the built Hadoop platform. The test results show that online travel reviews can be an important data source for travel big data recommendation, and the proposed method can quickly and accurately achieve travel sentiment classification. (shrink)

Member States of the United Nations proposed Seventeen Sustainable Development Goals (SDGs) in 2015, emphasizing the well-being of people, planet, prosperity, peace, and partnership. Countries are expected to work diligently to achieve these goals by the year 2030. The paths chosen to achieve the SDGs depend on each country’s specific needs, challenges, and opportunities. This contribution conducts a bibliometric study of selected SDG research related to hunger and climate change among countries of the North Asia Pacific region. A review of (...) literature related to the seventeen SDGs is provided to update the current research in SDGs as a background for the regional bibliometric search. The academic published literature related to this work were collected and text mined to create a research database for trend analysis. In this research, the natural language model KeyBERT and a text mining algorithm for normalized term frequency were used to extract key terminologies for bibliometric analysis. The study provides an overview of the seventeen SDGs in the literature review and then focuses on SDG 2 (zero hunger) and SDG 13 (climate action) publication trends. These two SDGs are in close alignment with sustainable food systems and agricultural development. The conclusion indicates that greater cooperation (SDG 17) is critical to improving the quality of life within the region and in building an ethical framework that restricts external exploitation of resources that benefit newly developed economies over developing economies. (shrink)

With the accelerated evolution of the internet in the form of web-sites, social networks, microblogs, and online portals, a large number of reviews, opinions, recommendations, ratings, and feedback are generated by writers or users. This user-generated sentiment content can be about books, people, hotels, products, research, events, etc. These sentiments become very beneficial for businesses, governments, and individuals. While this content is meant to be useful, a bulk of this writer-generated content requires using text mining techniques and sentiment (...) analysis. However, there are several challenges facing the sentiment analysis and evaluation process. These challenges become obstacles in analyzing the accurate meaning of sentiments and detecting suitable sentiment polarity specifically in the Bangla language. Sentiment analysis is the practice of applying natural language processing and text analysis techniques to identify and extract subjective information from text. This paper presents how the attention mechanism could be incorporated effectively and efficiently in analyzing the Bangla sentiment or opinion. (shrink)

Sentiment analysis aims to predict sentiment polarities (positive, negative or neutral) of a given piece of text. It lies at the intersection of many fields such as Natural Language Processing (NLP), Computational Linguistics, and Data Mining. Sentiments can be expressed explicitly or implicitly. Arabic Sentiment Analysis presents a challenge undertaking due to its complexity, ambiguity, various dialects, the scarcity of resources, the morphological richness of the language, the absence of contextual information, and the absence of explicit (...) sentiment words in an implicit piece of text. Recently, deep learning has obviously shown a great success in the field of sentiment analysis and is considered as the state-of-the-art model in Arabic Sentiment Analysis. However, the state-of-the-art accuracy for Arabic sentiment analysis still needs improvements regarding contextual information and implicit sentiment expressed in different real cases. In this paper, an efficient Bidirectional LSTM Network (BiLSTM) is investigated to enhance Arabic Sentiment Analysis, by applying Forward-Backward encapsulate contextual information from Arabic feature sequences. The experimental results on six benchmark sentiment analysis datasets demonstrate that our model achieves significant improvements over the state-of-art deep learning models and the baseline traditional machine learning methods. (shrink)

What the present work aimed to achieve is an assessment of the origin an d unity of Husserl s Logical Investigations. My approach was to take the history of its development as fundamental for the determination of its basic structure. Therefore, I proceeded to analyse Husserl s development between the Philosophy of Arithmetic and Logical Investigations with re spect to the fundamental issues in the justification of knowledge in mathematics and logic. In Husserl s own words, one of the concerns (...) that set him on the road to phenomenology was the clarification and analysis of the relation b etween the subjectivity of knowing and the objectivity of knowledge. Fro m my investigations it has, I hope, become apparent how this problem ori ginated in his earliest works and, through various influences and exchanges, led to his theory of intentionality in the first editio n of the Logical Investigations. The Logical Investigations is located between his Brentanist phase and t he ultimate development of transcendental phenomenology. It is the sedim ent of Husserl s logical investigations during the 1890s, which is the m ain period I analysed in the present work. Husserl himself often remarke s on the early origin of some of the issues he tried to deal with in the Logical Investigations. Still in his sketches for a new preface to the second edition of 1913, he took pains to point out the developmental his tory of the work from the Philosophy of Arithmetic onward. Regarding the Philosophy of Arithmetic, more often than not, Husserl remarks that it was just and elaboration of his Habilitationsschrift. Hence, following h is lead, we tried to embrace the whole period of his psychological and l ogical analyses from 1886/7 to 1900/01. Of course, I was certainly not the first, nor will I be the last, to be intrigued by Husserl s development in these years. Numerous books and articles have been written long before mine on precisely these issue s, often dealing with specific topics, such as the uneasy relation of psychology and psychologism in Husserl s work or fundamental inʂ 58;uences such as Bolzano s, which I therefore chose to leave aside. Not simply to duplicate or summarise such pre-existing scholarship, I tried to concentrate on the issues to which I felt I could contribute an orig inal insight, advancing the field. I would like to indicate ᤙ 7;ve points here, where I think I attained this goal: 1. The enduring relevance of Husserl s mathematical ba ckground. 2. Support for an early development of a theory of hig her order objects 3. A better evaluation of Frege s influence 4. A contextualisation of Schuhmann s thesis regarding the relevance of Twardowski for Husserl s notion of intentionality 5. The dependence of the unity of the Logical Investig ations on its historical development. Without understanding its developmental history we would misunderstand i ts internal coherence. In the first part we saw Husserl s early struggle to integrate the mathematical and psychological points of view on the philosophy of math ematics, a struggle that lasted from the Habilitationsschrift at least u p to and including his Doppelvortrag. The basic problem is the justi@ 257;cation of knowledge, in the case of mathematics, the justifica tion of knowledge in formal sciences, obtained with symbolic methods. Su ch problems regarding the subjectivity of knowing and the objectivity of knowledge guided the development of his position from Philosophy of Ari thmetic to Logical Investigations. In articulating his solution Husserl analysed the various relations betw een founding and founded layers of knowledge and whether and how one cou ld pass from on to the other. Already at the time of the Philosophy of A rithmetic he tried to account for higher order acts, relations and objec ts, the mature account of which would have to wait until the Logical Inv estigations and later. Among various influences on his progression towards phenomenology, Frege has been often considered to have provided the conversion to an ti-psychologism with his review of the Philosophy of Arithmetic. I think I have demonstrated that the review is almost entirely irrelevant in th is sense and that we should rather look at a much earlier influenc e on the Philosophy of Arithmetic. By showing that Brentano s conception of intentionality was already more sophisticated than until recently assumed, thanks to some recent public ations of unpublished material from Brentano s and Husserl s Nachlass, I think Schuhmann s thesis is right, but should be reinterpreted as being less radical than it would appear. Both Husserl and Twardowski were in& #64258;uenced by Brentano as his students. Following his and Meinong s l ead, they both elaborated a theory on intentionality, in connection with the other theories of intentionality in his school and the Brentano-Bol zano paradox. Furthermore, by providing a more continuous reading of Hus serl s development through the transcendental turn, I hope to have made clear that his later theory of the noema is not a return to a neo-Twardo wskian triadic position, but a reaffirmation, now in transcendental key, of his 1894 take on the matter. The Logical Investigations are uniquely determined by their historical c ontext in the middle of Husserl s development, falling almost exactly be tween the Habilitationsschrift and the Ideas. Due to their troubled hist ory, including changes in Husserl s earliest position around 1890, the f ailure of the second volume of the Philosophy of Arithmetic, various in& #64258;uences around 1894, and the subsequent reorientation and broadeni ng of his theories to a non-psychologistic logic and mathesis universali s, the Logical Investigations might at first seem to fall apart in two fundamentally disconnected books, the second one of which containin g six heterogeneous studies. It is my contention that it is exactly its troubled history that ties the Logical Investigations together, as Husse rl developed his logical investigations in the 1890s on the basis of a h andful thorny problems, including intentionality as centerpiece. From th e Habilitationsschrift to the Ideas it is the relation between subject a nd object, in all respects, ontological as well as epistemological, that guides his research. The Logical Investigations is a intermediate sedim ent of his struggles, containing an elaboration and improvement of his p osition in his early works and also pointing ahead towards the later pos ition of transcendental phenomenology as an implication and continuation of the solutions he proposes. Furthermore, I tried to address the problem that, while Husserl regarded his Logical Investigations as the breakthrough to phenomenology, many f undamental notions of the later transcendental phenomenology seem to be missing in the first edition of the Logical Investigations. The me thod of the reduction, the notion of a pure ego and a full account of th e noema are at most sketched or implied. Hence, I also looked ahead to t he further development of phenomenology after the Logical Investigations. As Husserl s influence has extended beyond the movement he found ed, I felt I could not bypass his significance for the currently d ominant analytical philosophy. Especially with respect to some of the co re topics of the Logical Investigations, but also earlier themes such as Husserl s semiotics, there is an interest in phenomenology from the ana lytic side. Nevertheless, precisely with regard to the unifying theme of intentionality, analytical philosophy often seems to miss the mark, and spectacularly so. I discussed Searle s influential, but in my opi nion, misguided and flawed approach, and I hope it is clear that I have chosen my method and approach in complete antithesis to his. The central contributions I was able to give, were only possible thanks to solid historical groundwork as necessary prerequisite for systematic analyses. Wherever possible, a reference to the original primary sources was provided, allowing the texts to speak for themselves and providing the reader with the critical instruments to evaluate my interpretations. As Husserl stood in a fruitful exchange with many other scholars, as st udent, colleague, friend and teacher, the intellectual context of his th oughts is essential to a correct understanding of his theories and aims. I hope to have found the right balance in the historical and the system atical aspects of my work to suit the interests of the reader and the re quirements of scholarship. (shrink)

Literary criticism is neither more nor less important today than it has been since the becoming an accepted activity in the Renaissance. The humanists of the sixteenth and seventeenth centuries created the institution of criticism as we know it: the recovery and analysis of works of art. They printed, edited, and interpreted texts that dated from antiquity and which had been lost or disheveled. Evangelical in their fervor, avid in their search for lost or buried riches, they also put (...) into circulation certain influential ideas. Perhaps the most important of these was that the authoritative version of a book is the original version, freed from interpolation and accretion. A correlative idea was that, similarly, one could rely on an original or natural light in the interpreter, an intuitive good sense that helped him to a true understanding of a text if it was a genuine text. . . . There are signs that we are now nearing the end of this Renaissance humanism. Not because of a determinist or providential march of history, but ideas eventually exhaust what influence they may have. Today, after all, there is no dearth of ancient texts, or of new ones. Editing, moreover, has become only too conscious of the difficulty of recovering an "original" version or edition: in Wordsworth scholarship, for example, the authority of the 1850 Prelude, the text approved by the poet shortly before his death, was challenged by the 1805-6 Prelude printed by de Sélincourt in the 1920s; and the authority of this is in turn being eroded by antecedent manuscripts, the so-called "Five-Books Prelude" and "Two-Part Prelude." It is equally precarious to establish the text of Emily Dickinson's poems—which of the variants are to be chosen as definitive? Or, from another angle, Melville's Billy Budd has become a mine for genetic speculation. Even when no editorial problem exists, a philosophical issue arises as to the concept of originality itself.1 · 1. For the time being, it is enough to quote Hegel's provocative attack on all "Ur-Metaphysics": "What comes later is more concrete and richer; the first is abstract, and least differentiated." Geoffrey Hartman, professor of English and comparative literature at Yale University, is the author of The Unmediated Vision, Andre Malraux, Wordsworth's Poetry, Beyond Formalism, and most recently The Fate of Reading. He is currently working on a book to be published in late 1977, Criticism in the Wilderness. (shrink)

\noindent\textbf{Introduction} Online interventions hold great potential for Therapeutic Change Process Research (TCPR), a field that aims to relate in-therapeutic change processes to the outcomes of interventions. Online a client is treated essentially through the language their counsellor uses, therefore the verbal interaction contains many important ingredients that bring about change. TCPR faces two challenges: how to derive meaningful change processes from texts, and secondly, how to assess these complex, varied and multi-layered processes? We advocate the use text mining (...) and multi-level models (MLMs): the former offers tools and methods to discovers patterns in texts; the latter can analyse these change processes as outcomes that vary at multiple levels. \noindent\textbf{Method} We (re-)used the data from \cite{Lamers2015} because it includes outcomes and the complete online intervention for clients with mild depressive symptoms. We used text mining to obtain basic text-variables from e-mails, that we analysed through MLMs. \noindent\textbf{Results} We found that we could relate outcomes of interventions to variables containing text-information. We conclude that we can indeed bridge text mining and MLMs for TCPR as it was possible to relate text-information (obtained through text mining) to multi-levelled TCPR outcomes (using a MLM). \noindent\textbf{Discussion} Text mining can be helpful to obtain change processes, which is also the main challenge for TCPR. We showed how MLMs and text mining can be combined, but our proposition leaves open how to obtain the most relevant textual operationalization of TCPR concepts. That requires interdisciplinary collaboration and discussion. The future does look bright: based on our proof-of-concept study we conclude that MLMs and text mining can indeed advance TCPR. (shrink)

Each narration or text, as it informs about an event, situation or person in history, has a history that sheds light on both its formation and how it arrived to us. The illumination of this history is at least as important as the content analysis of the information. For this reason, it is necessary both to examine whether the source in which the information is given has survived to the present day as it was created by the author (...) without being exposed to any external intervention, and to analyze the narration in terms of reliability and indication within the integrity of the isnād-text. In that case, when the word “text criticism” is mentioned, an understanding of a specific criticism should come to mind, which includes both critical edition (scholarly editing) of the first source and the critique of the narration by making sound research in terms of isnād and literary criticism (naqd al-isnād wa-l-matn). Due to reasons such as the inability to follow a standard method, the limited number of the copies and/or the distance of the copies from the author in terms of history and commercial concerns, many classical works published with relative verification contain such errors require a re-examination. One of these works is Ibn Hibbān’s (d. 354/965) book al-Majrūhīn. In his work al-Majrūhīn, Ibn Hibbān divided the narrators into two groups according to their reliability and collected the ones that he determined as weak according to his opinion. In this work, he placed Abū Ḥanīfa (d. 150/767) at the top of the list. First, he denounced Abū Ḥanīfa with the following expressions: Sahib al-ra’y, child of slaves, bicker, hypocrite, had little knowledge of hadith, a Murji’ī propagandist, a narrator who was blamed by imams. Then he tried to justify these claims by about thirty narrations from various salaf scholars. These narratives are completely different from the largely intellecutal discussions and criticisms of scholars such as al-Awza'i (d. 157/774), Ibn Abī Laylā (d. 148/765) and Ibn Abī Shayba (d. 235/849) on Abu Ḥanīfa and his school. The narrations compiled by Ibn Hibbān are display insulting and polemical narrations against Abu Ḥanīfa’s personality and reliability. In terms of being a source for later periods, it is important to examine and criticize these narratives in terms of the narration techniques. The al-jarḥ wa-l-taʿdīl is important part of the hadith science. al-Mejrūhīn, one of the leading works of this science is remarkable in many respects. According to this narration Abū Ḥanīfa Nuʿmān b. S̱ābit b. Zūtā b. Māh’ın (öl. 150/767) said, "If a man worships this mule to get closer to Allah, I see no harm in it." According to our analysis, there are the following determinations about the narrators in the chain of this narrative. Ibn Abī Mushir is unknown (majhūl), the narrator who is written as “Mahfūz b. Abī Savba” but his correct name is “Tawba” is matrūk. Ahmad b. al-Walīd al-Mahramī al-Karkhī is weak, and Yahyā b. Hamza, source person, is qadari who narrates from people with munkar al-hadith; but is also considered as a thiḳa narrator. As for Sa‘īd b. Abd al-Azīz, he has nothing to do with the reception and transmission of the narrative. In addition, there is also a break in the chain. First of all, what is expected from a basic work such as al-Majrūhīn, whose subject and purpose is purely a narrator analysis, is that the report in it should be acceptable, at least in terms of isnād. When the narrative in question, which is also included in earlier sources such as al-Fesewī (d. 277/890), is evaluated in terms of both the isnād and the text, one realizes the transformation of an expression circulating in the form of gossip against Abu Ḥanīfa in Damascus around the subject of ʾirjāʾ. ʾIrjāʾ was at the forefront of the heated debates in the second half of the second century into semā form in terms of isnād and text, besides, the word النعل/clog is transformed into البغل/mule. Apart from the weak points of the chain, Sa‘īd b. Abd al-Azīz, who has nothing to do with the reception and transmission of the narrative, has also been turned into the narrator/source of the report with the samā expression. Regardless of the purpose and the criteria of the narration technically, during the conversation with Sa‘īd, Yahyā b. Hamza’s sincere friend and teacher, a special speech in which a common report attributed to Abu Ḥanīfa was expressed, was transformed into Yahyâ’s samā‘ in the form of jazm. As a result, the word “shoe” or “clog” has evolved into mule. It would be a reductionist and over optimistic approach to assume that all this may have resulted from tashīf and tahrīf of the copyists. The narration we discussed is a typical example in terms of showing the effect of the conflict of ideas between Ahl al-Hadīth and Ahl ar-Ra’y on the narrations. Of course, this shoud be not regarded as the only example. (shrink)

Using Galileo Galilei's Saggiatore and Ludovico Ariosto's Orlando furioso as a focal point, this article evaluates a mixed methods approach for identifying matches of words and phrases that are rich material for close reading and contextualization. The method focuses on ngram matches and networks of phrases that are used together. The similarity of Galileo's treatise to Ariosto's poem is compared to 45 other early modern Italian texts to evaluate the relative exceptionalism or normality of the findings. Ngram matches reveal a (...) series of previously unknown connections between the Saggiatore and Furioso, which indicate an analytical understanding of the poem, rather than borrowing of narrative or figurative expression. Network analysis offers a preliminary outline for two communities of texts that frequently use the same ngrams found in the Furioso. (shrink)

In this paper, we set out to investigate the following question: if science relies heavily on induction, does philosophy of science rely heavily on induction as well? Using data mining and text analysis methods, we study a large corpus of philosophical texts mined from the JSTOR database (n = 14,199) in order to answer this question empirically. If philosophy of science relies heavily on induction, just as science supposedly does, then we would expect to find significantly more (...) inductive arguments than deductive arguments and abductive arguments in the published works of philosophers of science. Using indicator words to classify arguments by type (namely, deductive, inductive, and abductive arguments), we search through our corpus to find patterns of argumentation. Overall, the results of our study suggest that philosophers of science do rely on inductive inference. But induction may not be as foundational to philosophy of science as it is thought to be for science, given that philosophers of science make significantly more deductive arguments than inductive arguments. Interestingly, our results also suggest that philosophers of science do not rely on abductive arguments all that much, even though philosophers of science consider abduction to be a cornerstone of scientific methodology. (shrink)

The philosophical literature on scientific explanation contains a striking diversity of accounts. I use novel empirical methods to address this fragmentation and assess the importance and generality of explanation in science. My evidence base is a set of 781 articles from one year of the journal Science, and I begin by applying text mining techniques to discover patterns in the usage of “explain” and other words of philosophical interest. I then use random sampling from the data set to (...) develop and test a classification scheme for scientific explanation. My results show that explanation and inference to the best explanation are ubiquitous in science, that they occur across a wide range of scientific disciplines, and that they are a goal of scientific practise. These explanations and inferences to the best explanation come in a diversity forms, which at least partially justifies the fragmentation of philosophical accounts. I draw two methodological lessons: first that text mining can enhance traditional conceptual analysis by establishing facts about word usage; and second that random sampling of cases can increase our confidence that a philosophical account applies in general. These empirical techniques supplement traditional philosophical methods. (shrink)

As more national governments adopt policies addressing the ethical implications of artificial intelligence, a comparative analysis of policy documents on these topics can provide valuable insights into emerging concerns and areas of shared importance. This study critically examines 57 policy documents pertaining to ethical AI originating from 24 distinct countries, employing a combination of computational text mining methods and qualitative content analysis. The primary objective is to methodically identify common themes throughout these policy documents and perform (...) a comparative analysis of the ways in which various governments give priority to crucial matters. A total of nineteen topics were initially retrieved. Through an iterative coding process, six overarching themes were identified: principles, the protection of personal data, governmental roles and responsibilities, procedural guidelines, governance and monitoring mechanisms, and epistemological considerations. Furthermore, the research revealed 31 ethical dilemmas pertaining to AI that had been overlooked previously but are now emerging. These dilemmas have been referred to in different extents throughout the policy documents. This research makes a scholarly contribution to the expanding field of technology policy formulations at the national level by analyzing similarities and differences among countries. Furthermore, this analysis has practical ramifications for policymakers who are attempting to comprehend prevailing trends and potentially neglected domains that demand focus in the ever-evolving field of artificial intelligence. (shrink)

Public discourse about the COVID-19 that appears on Twitter and other social media platforms provides useful insights into public concerns and responses to the pandemic. However, acknowledging that public discourse around COVID-19 is multi-faceted and evolves over time poses both analytical and ontological challenges. Studies that use text-mining approaches to analyse responses to major events commonly treat public discourse on social media as an undifferentiated whole, without systematically examining the extent to which that discourse consists of distinct sub-discourses (...) or which phases characterize its development. They also confound structured behavioural data with unstructured user-generated data in their sampling methods. The present study aims to demonstrate how one might go about addressing both of these sets of challenges by combining corpus linguistic methods with a data-driven text-mining approach to gain a better understanding of how the public discourse around COVID-19 developed over time and what topics combine to form this discourse in the Australian Twittersphere over a period of nearly four months. By combining text mining and corpus linguistics, this study exemplifies how both approaches can complement each other productively. (shrink)

This paper adopts Hadoop to build and test the storage and retrieval platform for painting resources. This paper adopts Hadoop as the platform and MapReduce as the computing framework and uses Hadoop Distributed Filesystem distributed file system to store massive log data, which solves the storage problem of massive data. According to the business requirements of the system, this paper designs the system according to the process of web text mining, mainly divided into log data preprocessing module, log (...) data storage module, log data analysis module, and log data visualization module. The core part of the system is the log data analysis module. The analysis of search keywords ranking, Uniform Resource Locator, and user click relationship, URL ranking, and other dimensions are realized through data statistical analysis, and Canopy coarse clustering is performed first according to search keywords, and then K-means clustering is used for the results after Canopy clustering, and the calculation of cosine similarity is adopted to realize the grouping of users and build user portrait. The Hadoop development environment is installed and deployed, and functional and performance tests are conducted on the contents implemented in this system. The constructed private cloud platform for remote sensing image data can realize online retrieval of remote sensing image metadata and fast download of remote sensing image data and solve the problems in storage, data sharing, and management of remote sensing image data to a certain extent. (shrink)

Due to existence of a huge amount of textual data either on the World Wide Web or in textual databases like PubMed, the development of novel automatic keyphrase extraction methods has emerged as one of the key research problems in recent past. Consequently, a number of machine learning techniques, mostly supervised, have been proposed to extract keyphrases from text documents. But, one of the main bottlenecks that hinders the success of such systems is the requirement of annotated corpora for (...) training purpose. In this paper, we propose the design of a deep text mining system to identify keyphrases in text documents that are either unstructured or semi-structured in nature. The novelty of our system lies in its applicability on a single document, instead of demanding a collection of annotated texts for training, to identify keyphrases embedded within it. The proposed system applies parsing techniques to identify candidate phrases. After mapping the original set of candidate phrases into a low-dimensional space using Singular Value Decomposition, the Markov Clustering technique is applied to cluster related sentences together. Finally, considering each cluster as a document, Latent Dirichlet Allocation is applied to identify feasible keyphrases that are presented to users in non-increasing order of their relevance score values. The efficacy of the proposed system is established through experimentation on datasets from two different domains. On comparative evaluation, we found that the proposed system outperforms KEA and KEA that apply the supervised machine learning approach for automatic keyphrase extraction from text documents. (shrink)

It is a common view among philosophers of science that theoretical virtues (also known as epistemic or cognitive values), such as simplicity and consistency, play an important role in scientific practice. In this article, I set out to study the role that theoretical virtues play in scientific practice empirically. I apply the methods of data science, such as text mining and corpus analysis, to study large corpora of scientific texts in order to uncover patterns of usage. These (...) patterns of usage, in turn, might shed some light on the role that theoretical virtues play in scientific practice. Overall, the results of this empirical study suggest that scientists invoke theoretical virtues explicitly, albeit rather infrequently, when they talk about models (less than 30%), theories (less than 20%), and hypotheses (less than 15%) in their published works. To the extent that they are mentioned in scientific publications, the results of this study suggest that accuracy, consistency, and simplicity are the theoretical virtues that scientists invoke more frequently than the other theoretical virtues tested in this study. Interestingly, however, depending on whether they talk about hypotheses, theories, or models, scientists may invoke one of those theoretical virtues more than the others. (shrink)