Associated Topic Extraction for Consumer Generated Media Analysis

详细信息    查看全文

• 作者：Shinichi Nagano ; Masumi Inaba ; Yumiko Mizoguchi ; Takahiro Kawamura
• 刊名：Lecture Notes in Computer Science
• 出版年：2007
• 出版时间：2007
• 年：2007
• 卷：4504
• 期：1
• 页码：107-117
• 全文大小：783 KB
• 刊物类别：Computer Science
• 刊物主题：Artificial Intelligence and Robotics
  Computer Communication Networks
  Software Engineering
  Data Encryption
  Database Management
  Computation by Abstract Devices
  Algorithm Analysis and Problem Complexity
  
• 出版者：Springer Berlin / Heidelberg
• ISSN：1611-3349

文摘

This paper proposes a new algorithm of associated topic extraction, which detects related topics in a collection of blog entries referring to a specified topic. It is a partial feature of our product reputation information retrieval service whose aim is to detect product names rather than general terms. The main feature of the algorithm is to evaluate how important a topic is to the collection, according to the popularity of blog entries through Trackbacks and comments. Another feature is to utilize product ontology for topic filtering, which extracts products relevant to or similar to a specified product. The paper also presents a brief evaluation of the algorithm, in comparison with TF-IDF. In respect to the evaluation, it can be concluded that the proposed algorithm can capture users’ impressions of associated topics more accurately than TF-IDF.