This lecture introduces overview of text mining technology that enables to utilize huge amounts of textual data for identifying valuable knowledge and taking appropriate actions with some live demonstrations.
Tetsuya Nasukawa joined IBM in 1989, and he has been leading text mining projects since 1997. He is the primary inventor of the Text Analysis and Knowledge Mining (TAKMI) system that has been integrated into IBM products such as Watson Discovery Content Miner and Watson Explorer Content Analytics. He has over 30 years of experience in the natural language processing field. His areas of expertise include text mining, sentiment analysis, and personality estimation. Tetsuya has authored and co-authored more than 100 academic papers and received more than 10 academic awards. He has also written several books in Japanese as well as the Redbook of IBM Content Analytics and wrote the text mining sections of Encyclopedia of Natural Language Processing (Japanese) and Artificial Intelligence (Japanese).
He gave a tutorial on text mining at the Tenth Machine Translation Summit in 2005 and gave a keynote speech on text mining at the Eights International Symposium on Natural Language Processing in 2009.
He served as a Research Professor of Keio University from 2010 to 2011 and a Visiting Professor of Shizuoka University from 2012 to 2016.
He holds a PhD. degree in engineering from Waseda University, Japan.