E-raamat: Text Mining: A Guidebook for the Social Sciences

For social scientists, this guide explains methods drawn from computer science, the humanities, and social sciences for collecting and analyzing textual data from groups, communities, and organizations in online platforms. It discusses historical, philosophical, and ethical contexts and research design strategies; fundamentals like web crawling and scraping, lexical resources, basic text processing, and supervised learning; text analysis methods like thematic analysis, qualitative data analysis software, visualization, narrative analysis, and metaphor analysis; and text mining methods like word and text relatedness, text classification, information extraction and retrieval, sentiment analysis, and topic models. Annotation ©2016 Ringgold, Inc., Portland, OR (protoview.com)

Social media sites generate massive volumes of natural language data that are available for social science research. But social scientists have struggled to take advantage of "big data", and of the new technologies available for analyzing it. Should researchers learn programming languages in order to mine textual data? Are there software packages that can be repurposed for social science research? Can traditional theories and methods be scaled up to take advantage of new sources of textual data, or are new methods and new ways of thinking about theory needed? Text Mining: A Guidebook for Social Sciences addresses these questions and provides a methods guidebook to text mining and analysis for social scientists. It is intended for both new and experienced researchers, and provides strategic as well as practical guidance in the areas of text mining and qualitative and quantitative text analytic research methods. Gabe Ignatow and Rada Mihalcea critically survey this fast-changing landscape, providing a roadmap for researchers that will shorten the time from concept to publication, and scholarly impact.