Practical Hands On: Text Analysis DH Activities DH Examples Further Steps in this Course Analog and Digital Documents PLIN064 Uvod do digital humanities Zuzana Nevěřilová xpopelkOf i.muni.cz Centrum zpracování přirozeného jazyka, B203 Fakulta informatiky, Masarykova univerzita 25. září 2019 Practical Hands On: Text Analysis DH Activities DH Examples Further Steps in this Course Analog and Digital Documents Practical Hands On: Text Analysis DH Activities DH Examples Further Steps in this Course Analog and Digital Documents Practical Hands On: Text Analysis DH Activities DH Examples Further Steps in this Course Analog and Digital Documents Activities Fundamental Activities (not only in DH): • curation - selection and organization in an interpretive framework • analysis - processing of text or data & visualization • editing - keeping track of authenticity, origin, transmission, production • modeling - assumption about knowledge specific to the subject (e.g. in case of analyzing correspondence, a timeline) Practical Hands On: Text Analysis DH Activities DH Examples Further Steps in this Course Analog and Digital Documents Activities Fundamental Activities (not only in DH): • curation - selection and organization in an interpretive framework • analysis - processing of text or data & visualization • editing - keeping track of authenticity, origin, transmission, production • modeling - assumption about knowledge specific to the subject (e.g. in case of analyzing correspondence, a timeline) Practical Hands On: Text Analysis DH Activities DH Examples Further Steps in this Course Analog and Digital Documents Activities Digital Activities: • digitization, • classification, • description, • metadata organization, • navigation [Burdick et al., 2012] Practical Hands On: Text Analysis DH Activities DH Examples Further Steps in this Course Analog and Digital Documents DH Examples I Text • linguistics: synchrony and diachrony • language variations: dialects, slang, pidgin .. . • language and social groups • literary texts: authors, eras, areas • cross-lingual discourse • discourse analysis: event extraction, communication studies • names: toponymy, ethnonymy, demonymy . .. • information science • history • cultural analytics: trends in cultural change • social studies Practical Hands On: Text Analysis DH Activities DH Examples Further Steps in this Course Analog and Digital Documents DH Examples II Visual art • new media • virtual reality • museology: curation, preservation, access • archaeology: 3D modeling • architecture Multi-modal • anthropology: sound + video of human activities • analysis of video-games and other born-digital objects Internet of Things • sensor data Practical Hands On: Text Analysis DH Activities DH Examples Further Steps in this Course Analog and Digital Documents DH in Czechia LINDAT/CLARIAH-CZ at FF Czech Association for Digital Humanities Czech Academy of Sciences LINDAT/CLARIN, DARIAH-CZ Practical Hands On: Text Analysis DH Activities DH Examples Further Steps in this Course Analog and Digital Documents Further Steps in this Course • Digital documents • Analogue documents and digitization • "Raw" data, enriched data, metadata • Data sources • Data science projects • Data processing in Python • Evaluation, presentation of results, visualization Practical Hands On: Text Analysis DH Activities DH Examples Further Steps in this Course Analog and Digital Documents Analog and Digital Documents: Preprocessing Making (historical) analog document digital ACE. jv^^Ä1^ 2^ mi were preach mar * Practical Hands On: Text Analysis DH Activities DH Examples Further Steps in this Course Analog and Digital Documents Analog and Digital Documents: Preprocessing Making (historical) analog document digital ref; ace. 'THE fcttowing Sernms w Hundred Han ago by the Andrew Gray Mnijier of the The Gifts, {jraas, Experiences itmJerful Tenth ttere fo wry that m maw trulu Ix> m were preached near 4 by the tmineutly pious Air* if the Gofpet in GUfgow. rimes and Labours of this very far above his 7earsf Qtjfjted at item* Far tbtf A4PvJ^rJr»j# Mil Practical Hands On: Text Analysis DH Activities DH Examples Further Steps in this Course Analog and Digital Documents Optical Character Recognition (OCR) 1. Recognition of the area with text 2. Recognition of character shapes 3. Probability of a character in a context or other characters 4. Issues: different fonts, language-specific characters, noise multi-layer PDFs Practical Hands On: Text Analysis DH Activities DH Examples Further Steps in this Course Analog and Digital Documents Software Preprocessing: BIQE, Book Restorer OCR: ABBY, InftyReader, Tesseract neural network based OCR (Cloud service) Practical Hands On: Text Analysis DH Activities DH Examples Further Steps in this Course Analog and Digital Documents Analog and Digital Documents: Overview • analog documents: historical artifacts • digital documents: digital copy of analog documents • retro-digital documents: originally analog document that were scanned and OCRed • born-digital documents: artifacts that were created originally as digital documents Czech experts: Digitalizační centrum Knihovny AV CR v.v.i. Practical Hands On: Text Analysis DH Activities DH Examples Further Steps in this Course Analog and Digital Documents 1 Burdick, A., Drucker, J., Lunenfeld, P., Presner, T., and Schnapp, J. (2012). Digit a LH u man ities. The MIT Press. ■I Terras, M., Nyhan, J., and Vanhoutte, E. (2013). Defining Digital Humanities: A Reader. Ashgate Publishing Company, Brookfield, VT, USA.