| Title: | ArnetMiner - Extraction and Mining of Academic Social Network |
| Date: |
December 13, 2007 (Thursday)
|
| Time: |
11:00 a.m. - 12:00 noon
|
| Venue: |
Room 121, 1/F, Ho Sin-hang Engineering Building,
The Chinese University of Hong Kong, Shatin, N.T. |
| Speaker: |
Dr. Jie Tang
Tsinghua University Beijing China |
Social network services (SNSs) have attracted much attention on the Web recently. The rapid growing Web 2.0 web sites provide considerable data for research, at the same time bring big challenges to this field. In this talk, we will present our work on social network search and mining. We have developed a system called ArnetMiner, which is available at http://www.arnetminer.org. In this system, we aim at providing services for academic researcher community, including: extraction, search, and mining services. Specifically, we try to address several challenges in SNS in novel approaches. The problems we concentrate on include: 1) Extraction of a researcher social network automatically from the existing Web; 2) Integration of the publications into the social network from existing digital libraries; 3) Expert finding on a given topic; and 4) Association search between researchers. So far, we have already extracted 448,289 researcher profiles and 725,655 papers. The system is in operation on the internet for about two years and receives accesses from about 1,500 distinct users per month. Feedbacks from users and system logs indicate that users consider the system can really help people to find and share information in the academic community.
BIOGRAPHY:
Jie Tang is an assistant professor at the Department of Computer Science and Technology, Tsinghua University. He obtained his Ph.D. degree in July, 2006 and was awarded the Excellent Thesis of Tsinghua University. His main research interests include text mining, social network mining, statistical learning, and semantic web. He proposes three methods for information extraction/semantic annotation: similar-rule learning based, classification-based, and tree-structured conditional random fields based methods. The proposed methods have been applied to different applications, for example IE from company annual reports, researcher profiling in ArnetMiner.org system. He also proposes a method for ontology alignment, and developed an alignment tool (called RiMOM). RiMOM participated in OAEI2006 and 2007 and won the first place and the third place respectively.
He has authored more than 40 research papers in the related areas and has papers published at the top conferences, including: KDD, ACL, ICDM, CIKM, ISWC, WWW (poster), and related journals, including: Journal of Web Semantics and Journal on Data Semantics. He is the principal investigator of National Science Foundation of China (Contract No.: 60703059), Minnesota/China Collaborative project, IBM innovative joint-research project, and Tsinghua 985 Funding, and also took part in research projects including National Foundational Science Research (973) under Grant No. 2007CB310803, National Science Foundation of China (Contract No.: 60443002 and 90604025), Joint-project funded by China-Greece, and Joint-project funded by Tsinghua - ITF Frontier Co-Lab.
Enquiries: Miss Temmy So at tel 2609 8444
For more information, please refer to http://www.cse.cuhk.edu.hk/seminar