Blog Impact and Reputation Mining by Interconnection Analysis

• Main Authors: Hao-lun Tang, 唐浩倫
• Other Authors: Hung-yu Kao
• Format: Others
• Language: en_US
• Published: 2008
• Online Access: http://ndltd.ncl.edu.tw/handle/62097317443026728704

碩士 === 國立成功大學 === 資訊工程學系碩博士班 === 96 === As the ease of use in blogs, this new form of web content has become a popular online media. Detecting the quality of blogs in the massive blogosphere is a critical issue. This study extracts some real-world blog data and analyzes the interconnection in several blog communities. We believe that the interconnections reveal the consciousness of bloggers. By analyzing this information, the impact of blogs could be derived and may refer to their qualities. We propose a blog network model which is constructed from the linking structure in the community. A ranking method called BRank is then presented for blog impact and reputation mining. The method provides two blog rankings. Local BRank analyzes the impact of blogs in a community. Global BRank additionally considers the reputation of blogs in the blogosphere. We conduct several experiments to analyze the various linking structures and discover that the importance of interactions might vary in different communities. We also find that information of blogs is spread in different ways based on the characteristics of a blog community. The comparison results with some manually ranking lists show a fair agreement on the satisfaction of human. We conclude that our method could detect high quality blogs which are influential in either a BSP community or the blogosphere.