Ventures in Opinion Extraction and Summarization In this talk I will describe recent research on the extraction and summarization of sentiment and opinions. I'll start with a synopsis of work on extracting fine-grained opinion information from text. Here, the goal is to identify expressions of opinions, classify their sentiment, and determine the opinion holder and the topic/target of the opinion. Next, I'll briefly describe three very different attempts to produce usable summaries of opinions --- the first incorporates opinions into a timeline of events, the second operates in the context of opinion-oriented questions and user-generated content, and the third aims to identify the supporting evidence and reasons that a writer provides for his opinions. Bio Claire Cardie is a Professor in the Departments of Computer Science and Information Science at Cornell University and was the founding Chair of Cornell's Information Science Department. Cardie has a B.S. in Computer Science from Yale, and M.S. and Ph.D. degrees in Computer Science from the University of Massachusetts. She has served elected terms as an executive committee member of the Association for Computational Linguistics (ACL), an executive council member of AAAI, and twice as secretary of the North American chapter of the ACL (NAACL). Cardie was Program Chair of the joint ACL/COLING conference in 2006, of CoNLL 2000, and of EMNLP 1997. Cardie has broad interests in Natural Language Processing and was selected as a Fellow of the Association for Computational Linguistics in 2015 for foundational contributions to co-reference resolution, information and opinion extraction, and to machine learning methods in natural language processing. Cardie was also co-founder and chief scientist of New York city-based start-up, Appinions.com, from 2007-2015.