Speaker: Oren Sar Shalom, Intuit, Israel
Topic: On Reviews, Ratings and Collaborative Filtering
Oren is a principal data scientist at Intuit and holds a Ph.D. in Computer Science in the field of Recommender Systems. With more than 10 years of experience in the industry, he conducts research in both Recommender Systems and NLP related problems. He is also the lecturer of the Recommender Systems course in Tel Aviv University, a member of the ACM Future of Computing Academy (https://www.acm.org/fca) and a co-chair of the workshop on Deep Learning for Recommender Systems (DLRS 2018).
Speaker: Amin Salehi, Arizona State University, USA
Topic: From Individual Opinion Mining to Collective Opinion Mining
Opinion Mining has been a heated research topic for many years owing to its wide application to many domains such as marketing and online businesses. As defined in the literature, opinion mining determines the attitude of the writer/speaker with respect to a particular matter (e.g., an entity/event). Traditionally, "opinion mining" and "sentiment analysis" has been interchangeably used in the literature. However, in the broadest terms, opinion mining aims to identify not only opinions but also the drivers behind opinions. Therefore, we divide opinion mining approaches into two categories: individual and collective opinion mining. Individual opinion mining refers to traditional opinion mining and sentiment analysis, which identifies the opinions of individuals separately. On the other hand, collective opinion mining aims to determine the opinions of individuals collectively. Accordingly, collective opinion mining can helps us to understand the drivers behind opinions. For instance, the attitudes of like-minded individuals towards a variety of entities/events can uncover the motives behind their opinions. Moreover, collective opinion mining has the capability for better identification of opinions in comparison with individual opinion mining. For example, it is more likely the individuals with similar attitudes towards a variety of entities/events have similar opinions on a new entity/event.
Speaker: Ophélie Fraisier, IRIT, France
Topic: Politics on Twitter : A Panorama
09:00 - 09:20: Introduction
09:20 - 10:00: Invited Talk by Oren Sar Shalom, Intuit: "Reviews, Ratings and Collaborative Filtering"
10:00 - 10:30: Coffee Break
10:30 - 11:10: Invited Talk by Ophélie Fraisier, IRIT: "Politics on Twitter : A Panorama"
11:10 - 11:30: Paper 1: Sentiment polarity classification of Turkish product reviews for measuring and summarizing user satisfaction by Migena Ceyhan, Zeynep Orhan and Elton Domnori
11:30 - 11:50: Paper 2: Automatic Detection of Emotions in Twitter Data - A Scalable Decision Tree Classification Method by Jaishree Ranganathan, Nikhil Hedge, Allen Irudayaraj and Angelina Tzacheva
11:50 - 12:30: Invited Talk by Amin Salehi, Arizona State University: "From Individual Opinion Mining to Collective Opinion Mining"