ITC-UT: Tweet Categorization by Query Categorization for On-line Reputation Management

This paper describes our system, called ITC-UT, for the task-2 (on-line reputation management task) in WePS-3. Our idea is to categorize each query into 3 or 4 classes according to how much the tweets retrieved by the query contain the "true" entity names that refer to the target entity, and then categorize each tweet by the rules defined for each class of queries. We show the evaluation results for our system along with the details of results of query categorization.

• Type: Conference
• Year: 2010
• Where: CLEF
• Authors: Minoru Yoshida, Shin Matsushima, Shingo Ono, Issei Sato, Hiroshi Nakagawa
• Keywords: CLEF 2010, Entity Names, Information Technology, Reputation Management Task, Target Entity