סמינר מחלקתי

ConSent: Context-Based Sentiment Analysis

Dr. Gilad Katz 

Abstract:

Sentiment analysis refers to the inference of people's views, positions and attitudes in their written or spoken texts. The applications of this field are numerous, ranging from the classification of hotel reviews to the analysis of public opinion on Twitter.

In this talk I will present ConSent, a context-based approach for the task of sentiment analysis. Our approach builds on techniques from the field of information retrieval to identify key terms indicative of the existence of sentiment. We model these terms and the contexts in which they appear and use them to generate features for supervised learning. The two major strengths of the proposed model are its robustness against noise and the easy addition of features from multiple sources to the feature set. In addition, I will present a set of domain-specific features, designed specifically for sentiment analysis in automatically transcribed text.

Bio:

Gilad Katz is a fourth-year PhD student in the Department of Information Systems Engineering, Ben Gurion University. His advisers are Prof. Yuval Elovici and Prof. Bracha Shapira. His research interest include text mining, machine learning and recommender systems. 

ההרצאה תתקיים ביום חמישי,30.12.14, בשעה 14:00 בחדר 206, בנין וולפסון הנדסה, הפקולטה להנדסה, אוניברסיטת תל-אביב.