Text Mining

Gabe Ignatow is Professor of Sociology and Director of Graduate Studies at the University of North Texas. His research interests are mainly in the areas of sociological theory, digital research methods, cognitive social science, and the philosophy of social science. His most recent books are Text Mining and An Introduction to Text Mining, both coauthored with Rada Mihalcea (University of Michigan). He is also a coeditor, with Wayne Brekhus (University of Missouri), of the Oxford Handbook of Cognitive Sociology.Rada Mihalcea is a professor of computer science and engineering at the University of Michigan. Her research interests are in computational linguistics, with a focus on lexical semantics, multilingual natural language processing, and computational social sciences. She serves or has served on the editorial boards of the following journals: Computational Linguistics, Language Resources and Evaluation, Natural Language Engineering, Research on Language and Computation, IEEE Transactions on Affective Computing, and Transactions of the Association for Computational Linguistics. She was a general chair for the Conference of the North American Chapter of the Association for Computational Linguistics (NAACL, 2015) and a program cochair for the Conference of the Association for Computational Linguistics (2011) and the Conference on Empirical Methods in Natural Language Processing (2009). She is the recipient of a National Science Foundation CAREER award (2008) and a Presidential Early Career Award for Scientists and Engineers (2009). In 2013, she was made an honorary citizen of her hometown of Cluj-Napoca, Romania.

Text Mining and Analysis is a comprehensive book that deals with the latest developments of text mining research, methodology, and applications. An excellent choice for anyone who wants to learn how these emerging practices can benefit their own research in an era of Big Data.

• Part I: Digital Texts, Digital Social Science1. Social Science and the Digital Text RevolutionLearning ObjectivesIntroductionHistory of Text AnalysisRisk and Rewards of Text Mining for the Social SciencesSocial Data from Digital EnvironmentsTheory and MetatheoryEthics of Text MiningOrganization of This Volume2. Research Design StrategiesLearning ObjectivesIntroductionLevels of AnalysisStrategies for Document Selection and SamplingTypes of Inferential LogicApproaches to Research DesignPart II: Text Mining Fundamentals3. Web Crawling and ScrapingLearning ObjectivesIntroductionWeb StatisticsWeb CrawlingWeb ScrapingSoftware for Web Crawling and Scraping4. Lexical ResourcesLearning ObjectivesIntroductionWordNetRoget′s ThesaurusLinguistic Inquiry and Word CountGeneral InquirerWikipediaDownloadable Lexical Resources and APIs5. Basic Text ProcessingLearning ObjectivesIntroductionTokenizationStopword RemovalStemming and LemmatizationText StatisticsLanguage ModelsOther Text ProcessingSoftware for Text Processing6. Supervised LearningLearning ObjectivesFeature Representation and WeightingSupervised Learning AlgorithmsEvaluation of Supervised LearningSoftware for Supervised LearningPart III: Text Analysis Methods from the Humanities and Social Sciences7. Thematic Analysis, QDAS, and VisualizationLearning ObjectivesThematic AnalysisQualitative Data Analysis SoftwareVisualization Tools8. Narrative AnalysisLearning ObjectivesIntroductionConceptual FoundationsMixed Methods of Narrative AnalysisAutomated Approaches to Narrative AnalysisFuture DirectionsSpecialized Software for Narrative Analysis9. Metaphor AnalysisLearning ObjectivesIntroductionTheoretical FoundationsQualitative Metaphor AnalysisMixed Methods of Metaphor AnalysisAutomated Metaphor Identification MethodsSoftware for Metaphor AnalysisPart IV: Text Mining Methods from Computer Science10. Word and Text RelatednessLearning ObjectivesIntroductionTheoretical FoundationsCorpus-based and Knowledge-based Measures of RelatednessSoftware and Datasets for Word and Text RelatednessFurther Reading11. Text ClassificationLearning ObjectivesIntroductionApplications of Text ClassificationRepresenting Texts for Supervised Text ClassificationText Classification AlgorithmsBootstrapping in Text ClassifcationEvaluation of Text ClassificationSoftware and Datasets for Text Classification12. Information ExtractionLearning ObjectivesIntroductionEntity ExtractionRelation ExtractionWeb Information ExtractionTemplate FillingSoftware and Datasets for Information Extraction and Text Mining13. Information RetrievalLearning ObjectivesIntroductionTheoretical FoundationsComponents of an Information Retrieval SystemInformation Retrieval ModelsThe Vector-Space ModelEvaluation of Information Retrieval ModelsWeb-Based Information RetrievalSoftware and Datasets for Information Retrieval14. Sentiment AnalysisLearning ObjectivesIntroductionTheoretical FoundationsLexiconsCorporaToolsFuture DirectionsSoftware and Datasets for Word and Text Relatedness15. Topic ModelsLearning ObjectivesIntroductionDigital HumanitiesPolitical ScienceSociologySoftware for Topic ModelingV: Conclusions16. Text Mining, Text Analysis, and the Future of Social ScienceIntroductionSocial and Computer Science Collaboration