Category : 未分类
题目: Understanding and Predicting Search Satisfaction in a Heterogeneous Environment
演讲者: Yiqun Liu
In the online world, user engagement is a key concept in designing user-centered web applications. It refers to the quality of the user experience that emphasizes the phenomena associated with wanting to use an application longer and frequently.
In this talk, I will present my past efforts in modeling user engagement in the context of ad and search, seeking to provide insights on how to make an engaging experience. Firstly, to ensure long-term user engagement with Yahoo, I will present a learning framework that effectively identify ads with low quality. Secondly, in the context of search, I will talk about understanding and modeling user examination and satisfaction of the search result pages.
Ke (Adam) Zhou is an assistant professor of data science at University of Nottingham, School of Computer Science. His research interests and expertise lie in web search and analytics, evaluation metrics, text mining and human computer interaction. He has published in reputable conferences and journals (SIGIR, WWW, WSDM, TOIS, PLOS ONE), and won the best paper award in ECIR’15 and CHIIR’16, and best paper honorable mention in SIGIR’15. He also served as a co-organizer for NTCIR-11/12 IMine task, TREC FedWeb 2014 task, Heterogeneous Information Access (HIA) workshop at WSDM’15 & SIGIR’16, and AIRS’16 Poster and Demo chair.
Prior to joining University of Nottingham, he was a research scientist working in user engagement & ad quality science team in Yahoo Research London. He was previously a research associate in Language Technology Group in University of Edinburgh, working on text mining and information retrieval from 2013. Prior to this, he has conducted his PhD research on evaluation of aggregated search at the Information Retrieval Group in University of Glasgow.
More details can be found at https://sites.google.com/site/keadamzhou/.