Bo Pang
Senior Research Scientist
Yahoo! Research
Sunnyvale, CA
bopang42@gmail.com
408-827-8168
Research interests: Natural Language Processing, Social Media, Web Advertising, Machine Learning
Education
Ph.D., Computer Science, Cornell University (2000-2006)
Thesis: Automatic analysis of document sentiment; Advisor: Lillian Lee
Visiting scholar, Computer Science, Carnegie Mellon University (2004-2005)
B.S., Computer Science, Tsinghua University (1995-2000)
Employment
Yahoo! Research (2006-present) Senior Research Scientist
Internships:
Google Inc. (Summer 2005; Google books search)
Information Science Institute / University of Southern California (Summer 2002; Extracting paraphrases from parallel translations)
IBM Almaden Research Center (Summer 2001; Analyzing document sentiment)
Selected publications [(almost) full list at Google Scholar]
Monograph: Bo Pang and Lillian Lee. Opinion mining and sentiment analysis.
Foundations and Trends in Information Retrieval 2(1-2), pp. 1-135, July 2008
Cristian Danescu-Niculescu-Mizil, Lillian Lee, Bo Pang, Jon Kleinberg.
Echoes of power: Language effects and power differences in social interaction. WWW'12
Nilesh Dalvi, Ravi Kumar, and Bo Pang.
Object matching in tweets with spatial models. WSDM'12
Deepak Agarwal, Bee-Chung Chen, and Bo Pang.
Personalized recommendation of user comments via factor models. EMNLP'11
Sharad Goel, Andrei Broder, Evgeniy Gabrilovich, Bo Pang.
Anatomy of the long tail: Ordinary people with extraordinary tastes. WSDM'10
Ravi Kumar, Jasmine Novak, Bo Pang, Andrew Tomkins.
On anonymizing query logs via token-based hashing. WWW'07
Bo Pang and Lillian Lee.
A sentimental education: Sentiment analysis using subjectivity summarization based on minimum cuts. ACL'04
Bo Pang, Kevin Knight, and Daniel Marcu.
Syntax-based alignment of multiple translations: Extracting paraphrases and generating new sentences. NAACL'03
Bo Pang and Lillian Lee, and Shivakumar Vaithyanathan.
Thumbs up? Sentiment classification using machine learning techniques. EMNLP'02
Selected projects
Local and entity matching: review identification and matching for local entities; matching tweets to local entities
Review/comment mining: generating review highlights for local entities; mining for actionable information in recipe reviews
Non-topic-based personalization: comment consumption based on perspectives; content selection (e.g., search results re-ranking) based on text comprehensibility/readability
Advertising: automatic bid phrase generation; landing page and ad selection
Press mentions
Mining the Web for Feelings, Not Facts. The New York Times. August 23, 2009.
Our Sentiments Exactly. Communications of the ACM. Volume 52, Issue 4 (April 2009).
Getting Sentimental About Customers. 1to1 Magazine. Winter 2009 Issue
Take a Sentimental Journey: What sentiment analysis means for PR professionals. Public Relations Society of America (PRSA). November, 2009
Honors/Awards
Best paper runner-up, WSDM 2012
Finalist, Google Anita Borg Memorial Scholarship, 2005
Cornell Graduate Fellowship in Cognitive Studies, 2004
Excellent Graduate, Tsinghua University, 2000
Excellent Student of Tsinghua University, 1997
First Prize Scholarships, Tsinghua University, 1996-1998
Recent invited talks
A Web of opinions for a Web of Concepts
-- University of Edinburgh, August, 2011; Rutgers, September, 2011
Web of opinions: sentiment analysis in the context of online communities
-- Peking University, April 20, 2011; Tsinghua University, April 20, 2011
Sentiment of Two Women: Sentiment Analysis & Social Media
-- SXSW Interactive, March 14, 2011
Anatomy of the long tail: the whys and hows of satisfying niche interests.
-- Keynote: WWW'11 workshop on Semantic Search, March 29, 2011; UT Austin, March 11, 2011.
Professional services
Area chair: EMNLP 2008, COLING 2010, EMNLP 2010, EMNLP 2011
Senior program committee: ICWSM 2010, ICWSM 2011, ICWSM 2012, CIKM 2012
Editorial Board: Journal of Artificial Intelligence Research (JAIR), since 2009
Panelist, NSF (IIS) Panel, 2007, 2008, 2010
Program committee: ACL, NAACL, EMNLP, COLING, AAAI, IJCAI, ICML, WWW, WSDM, CIKM