A Topic-oriented Network Interface Development and Evaluation for Wikipedia: Integrating Link with Semantic Analysis Techniques

• Main Authors: Chang Chun-Ning, 張鈞甯
• Other Authors: Wu I-Chin
• Format: Others
• Language: zh-TW
• Published: 2010
• Online Access: http://ndltd.ncl.edu.tw/handle/39751248901983561308

碩士 === 輔仁大學 === 資訊管理學系 === 98 === With the emergence of the Internet and Web 2.0 technologies, the social web sites (i.e., (social networking websites, micro-blogging services) provide unprecedented opportunities for creating user-generated content, as well as for promoting communication, collaboration and information-sharing among users. Wikipedia, one of the most famous collaborative projects on the Web, has become an extremely popular reference database for people seeking information or knowledge. However, since the number of articles and a wide variety of topics in Wikipedia is constantly expanding, it is difficult for users to find information efficiently via the hypertext, i.e., the network of linked documents. To address the problem, we propose a hybrid approach that is based on the theories and techniques of link-based analysis and semantic relatedness analysis. Specifically, we propose a link strength measure to establish the preliminary topic network by analyzing relationships between articles. Furthermore, we refined the Normalized Google Distance to quantify the strength of a relationship between two articles via key terms. We then apply social network analysis indicators, i.e., closeness centrality, degree centrality and betweenness centrality to determine the relationships between topics and visualize the analyzing results to help users browse the Wikipedia efficiently. Finally, a topic-based WikiMap is generated based on the proposed hybrid approach. We further conducted a user-task oriented evaluation approach to confirm the implemented topic-based WikiMap can help users browse a topic and accomplish complicated tasks easily and efficiently.