报告人：刘晓钟 副教授,（Indiana University Bloomington，IUB）
报告题目：Scholarly Data Analysis and Mining
报告摘要：The sheer volume of scholarly publications available online significantly challenges how scholars retrieve the new information available and locate the candidate reference papers. While classical data mining and text retrieval algorithms can assist scholars in accessing needed publications, in this talk, I will introduce a number of novel applications and studies to address this problem by leveraging full-text citation analysis and heterogeneous graph mining. Meanwhile, although the scientific digital library is growing at a rapid pace, scholars/students often find reading STEM literature daunting because of their limited knowledge in the target domain and the challenging content of the readings. In this research, I propose a new solution to address this problem: scientific information understanding.
报告人简介： Dr. Xiaozhong Liu is an Associate Professor at School of Informatics and Computing, Indiana University Bloomington. His research interests include metadata, information retrieval, natural language processing, text mining, knowledge management, and human computing. His dissertation at Syracuse University explored an innovative ranking method that weighted the retrieved results by leveraging dynamic community interests. In contrast to most existing studies in scientific resource recommendation, his research developed an enhanced understanding of the scholarly network from a topical content perspective and investigated the use of full-text citation data to improve the overall recommendation ranking performance. He proposed SWALE and Collaborative PDF reader projects, which will generate innovative metadata along with next generation knowledge retrieval and question answering systems.