Entity extraction, topic modelling with WordStat by Derrick Cogburn

In this presentation, Professor Derrick Cogburn presents an overview of two key inductive/exploratory text mining techniques – entity extraction and topic modeling – using WordStat – content analysis and text mining tool. He situates these techniques within a broader discussion of data science and the voluminous amounts of textual data being enabled by the ongoing information revolution. Dr. Cogburn introduces tools, techniques, and approaches to text mining, along with the CRISP-DM project management approach. He then presents a brief snapshot of a project using entity extraction and topic modeling to understand twelve years of transcripts from the United Nations Internet Governance Forum (IGF). Finally, Dr. Cogburn turns to a hands on demonstration of entity extraction and topic modeling using WordStat.