Thursday, Jan. 12, 4:30-5:30, POST 126
Multi-Dimensional Text Analytics: Concepts, Methods, Tools and Findings
Dr. Raghava Rao Mukkamala
Centre for Business Data Analytics
Copenhagen Business School, Denmark
In this talk, I first present a methodology for multi-dimensional text analysis using text mining, topic modeling, and domain-specific classification. Second, I present a research tool, MUTATO developed at the Centre for Business Data Analytics (http://bda.cbs.dk) for performing text mining, topic modeling and text classification using supervised and unsupervised machine learning approaches. MUTATO is developed as a web application by using Python and C# programming languages with open-source libraries such as Natural Language Toolkit (NLTK) and Gensim topic modeling libraries. As part of unsupervised approaches, MUTATO supports text mining by providing keyword analysis, collocation analysis and word-frequency analysis. MUTATO supports topic modeling to identify/discover topics and hidden information patterns from a given text corpus. As part of supervised machine-learning approaches, MUTATO supports 1) manual coding of text documents for preparing training sets using a systematic approach for manual content analysis 2) classification of text corpus according the given domain-specific models using the training sets. MUTATO also provides key performance measures for text classification in terms of precision, recall, accuracy and F-measure. Third and last, I will present applications of MUTATO in different research domains, highlight key empirical findings, discuss limitations and outline future work.
Raghava Rao Mukkamala is an Assistant Professor of Computational Social Science at the Department of IT Management, Copenhagen Business School; external lecturer of applied computing at the Westerdals Oslo School of Arts Communication and Technology; and co-director of the Computational Social Science Laboratory (cssl.cbs.dk). Raghava’s current research focus is on interdisciplinary approach to big data analytics. Combining formal/mathematical modeling approaches with data/text mining techniques and machine learning methodologies, his current research program seeks to develop new algorithms and techniques for big data analytics such as Social Set Analytics. Raghava holds a PhD degree in Computer Science and a M.Sc degree in Information Technology, both from IT University of Copenhagen, Denmark and a Bachelor of Technology degree from Jawaharlal Nehru Technological University, India. Before moving to research, Raghava has many of years of programming and IT development experience from Danish IT industry.