SPEAKER: Dr. Jing Gao, University at Buffalo
DATE, TIME AND LOCATION: Friday, Dec. 11 2015, 1-2pm, GOL-3445
TALK TITLE: Mining Truth from Multi-Source Data
ABSTRACT: In the era of information explosion, it is common to collect information from multiple sources for the same set of objects, which may contain conflicting information due to observation or recording errors. Among these pieces of noisy information, which one is more trustworthy, or represents the true fact? Facing the daunting scale of data, it is unrealistic to expect human to label or tell which data source is more reliable or which piece of information is correct. Our position is to detect truths without supervision, by integrating source reliability estimation and truth finding. In this talk, I will introduce our recent work on the development of truth discovery approaches that jointly estimate source reliability and infer true information from multiple sources of conflicting information. The proposed methods can be applied to a wide spectrum of domains where decisions have to be made based on the correct information from diverse sources. In particular, the effectiveness of the proposed methods is demonstrated on real-world datasets including Web data fusion and crowdsourced question answering. On a crowdsourced question answering dataset on "Who Wants to be a Millionaire" game, the proposed approach successfully decreases the error rate from 0.5 (majority voting) to 0.2 by effectively inferring users information reliability degrees. I will conclude the talk by a brief discussion of other on-going research projects in my group, including health care question answering, crowdsourcing, privacy protection, and anomaly detection.
BIOGRAPHY: Jing Gao is currently an assistant professor in the Department of Computer Science at the University at Buffalo (UB), State University of New York. She received her PhD from Computer Science Department, University of Illinois at Urbana Champaign in 2011, and subsequently joined UB in 2012. She is broadly interested in data and information analysis with a focus on information integration, truth discovery, crowdsourcing, data stream mining, transfer learning, anomaly detection and information network analysis. She has published more than 70 papers in referred journals and conferences and her work has received over 2000 citations. More information about her research can be found at: http://www.cse.buffalo.edu/~jing.