活动/讲座时间：2011-09-30 下午16:00-17:30

活动/讲座地点：九里校区电气馆3215

活动/讲座嘉宾：Guandong Xu博士

嘉宾介绍：

主要内容：

报告内容提要 （Outline）:

Web advertising, a form of advertising which uses the World Wide Web to attract customers, has become one of the most important marketing channels. As one prevalent type of Web advertising, contextual advertising refers to the placement of the most relevant commercial ads within the content of a Web page, so as to provide a better user experience and thereby increase the number of user’s ad-clicks. However, some problems such as homonymy and polysemy, low intersection of keywords, and context mismatch, can lead to the selection of irrelevant ads for a generic page, making that, the traditional keyword matching techniques generally present a poor accuracy.

In this study, we introduce a new contextual advertising approach to overcome these problems, which uses Wikipedia concept and category information to enrich the content representation of a targeted page (or a candidate ad). First, we map each page (or ad) into three feature vectors: a keyword vector, a concept vector and a category vector. Second, we determine the relevant ads for a given page based on a similarity measure which combines the above three feature vectors. Last, we validate our approach by using a set of real ads, real pages, and more than 730,000 concepts and 24,000 categories chosen from Wikipedia. The experimental results show that our approach performs better than the simple keyword matching and can improve the precision of ads-selection.

Guandong Xu博士简介（Biography）:

Dr. Guandong Xu has received his PhD degree in Computer Science from Victoria University, Australia in 2008. He is now working as a Research Fellow in the Centre for Applied Informatics at Victoria University, Australia. His research interests cover Data management and Analytics, Data Mining, Machine Learning; Information retrieval and processing, Web search; Intelligent Web Systems, Web mining, Web Communities, Web Personalization and Recommender Systems; Social Network Analysis, Social Media Mining; as well as Social Informatics and Health Informatics. He has extensively published 40+ papers in referred international journals and conferences proceedings including the Computer Journal, Knowledge-based Systems, Concurrency and Computation: Practice and Experience, Web Intelligence and Agent Systems: an International Journal, Expert System with Applications, Information Processing Letter; and AAAI, CIKM, WISE, IJCNN,KES, WI, ADMA conferences etc. He has authored or is writing (editing) three scientific books with Springer and IGI publisher. He was the recipient of 2007 Chinese Government Award for Outstanding Self-financed Students Aboard by Ministry of Education of China and 2009 Vice-Chancellors Award of Excellence in Research and Research Training by Victoria University.

He has been in editorial board of two International Journals: Human-centric Computing and Information Sciences (HCIS) by Springer and International Journal of Advanced Science and Technology (IJAST). He is the assistant Editor-in-Chief for World Wide Web Journal. He served on many program committees of international conferences: APWeb, WAIM, WI, HIS, SCA, FutureTech, HumanCom, SKG, CSA, as well as the workshop co-chairs on APWeb 2008, DASFAA 2010-2012, ICDM’2011, SCA’2011. In addition, he has been serving as external reviewers for several international journals: Concurrency and Computer: Practice & Experience, The Computer Journal, Social Network Analysis & Mining, Data Mining & Knowledge Discovery, Computers & Security, World Wide Web Journal, International Journal of Machine Learning and Cybernetics, International Journal of Pattern Recognition and Artificial Intelligence. He is a guest editor of special issue on social network analysis and social web mining with World Wide Web Journal. His research received funding from Department of Education, Science and Technology of Australia and Victoria University.