seminar
Automated Citation Opinion Analysis for Scientific Writing
With the fast growth of academic publications, researchers face the increasingly difficult task of comprehensive literature review. Current bibliographic databases provide citation linkages but no further citation context analysis to help researchers find the most relevant citations and organize different kinds of academic opinions expressed in citation context. The Citation Opinion Retrieval and Analysis (CORA) project aims for building an automated tool that can extract the citation statements, separate substantial citations from perfunctory ones, and categorize substantial citation opinions by their purposes, topic aspects, polarities, and the opinion holders and targets. CORA is expected to save researchers a significant amount of time to find the most useful comments from a large number of citations. CORA will also provide a new, qualitative approach for assessing research impact and tracking problematic phenomena such as citation bias.
<p>Dr. Bei Yu is an Associate Professor in the School of Information Studies (the iSchool), Syracuse University. She is also the Faculty Lead for the Certificate of Advanced Study in Data Science Program in the iSchool, and the Advisor for the Information Representation and Retrieval Concentration in the Linguistics Studies Program at Syracuse University. Dr. Yu received education and training in multiple disciplines. Before joining Syracuse University she was a postdoctoral researcher at the Kellogg School of Management at Northwestern University. Dr. Yu holds a PhD degree in Library and Information Science from University of Illinois at Urbana-Champaign, a Master's degree in Computer Science from Institute of Computing Technology, Chinese Academy of Sciences, and a Bachelor's degree in Computer Science from University of Science and Technology of China.<br /><br />Dr. Yu's primary research interest is in the area of applied natural language processing. Her research focuses on using machine learning, data mining, and language technologies to study long-standing questions in social sciences, humanities, and library and information science. <br />Specifically, she conducts computational analysis of large amounts of text data to discover linguistic patterns that characterize people's opinions, sentiments, and language styles, and develop prediction models accordingly. Her current work, funded by an IMLS Early Career Award, focuses on developing an automated citation context analysis tool to help researchers retrieve and summarize academic opinions in scientific literature.<br /><br /></p>