CS730: Text Mining for Social Media (Fall 2010)

[ Lecture Notes and Schedule]


Lectures: Mondays: 11:30am-12:4pm Room: E510, Emerson Hall
Course Description: Proliferation of the Internet and ubiquitous access to the Web enable millions of Web users to collaborate online on a variety of activities. Many of these activities result in the construction of large repositories of knowledge, either as their primary aim (e.g., Wikipedia) or as a by-product (e.g., Yahoo Answers). This course will explore topics in text mining to extract, filter, and organize knowledge from social media and collaboratively generated content. The course topics will include: concept extraction and manipulation (e.g., knowledge base construction and Explicit Semantic Analysis), temporal analysis (e.g., for forecasting and topic evolution), sentiment analysis, incorporating meta-data (e.g., social network structure and user feedback), and applications to search and IR (e.g., searching social media or using it to improve web search).

Foundations of Statistical Natural Language Processing (FSNLP), Manning & Schütze.

Other readings will be from research and survey articles, to be posted online as needed.

  • In-class paper presentations (every 2-3 weeks): 50%

  • Final project/survey paper: 50%

Last updated: 31 August 2010