Recently, the number of sites on the Internet which give users the opportunity to write their ideas and opinions for the public to read have been increasing. In addition, the number of people who want to know the opinions of others about interesting products has also been increasing. However, it is very difficult for people to read complete reviews on the Internet. This study tries to develop a new system for the analysis of reviews, a system which shows evaluation information about products using graphs of evaluation keywords. This paper focuses on the extraction of evaluation keywords from reviews on the Internet. This paper proposes a method for extracting evaluation keywords and displays its results as graphs. It employs HK Graph (Hierarchical Keyword Graph), which can visualize the relationship among words in a hierarchical network structure based on the co-occurrence information for the keyword graph.

1. [1] Kakaku.com, http://bbs.kakaku.com/bbs/
2. [2] T. Okabe, T. Yoshikawa, and T. Furuhashi, “Proposal of Multi-Connected Hierarchical Text Mining Method for Medical Incident Reports,” The 22nd Fuzzy System Symposium, pp. 211-214, 2006 (in Japanese).
3. [3] K. Tateishi, Y. Ishiguro, and T. Fukushima, “Opinion Information Retrieval from the Internet,” Information Processing Society of Japan Technical Report , Vol.2001, No.69, pp. 75-82, 2001 (in Japanese).
4. [4] N. Kobayashi, K. Inui, Y. Matsumoto, K. Tateishi, and T. Fukushima, “Collecting Evaluative Expressions by A Text Mining Technique,” Information Processing Society of Japan Technical Report, Vol.2003, No.23, pp. 77-84, 2003.
5. [5] T. Kudo and Y. Matsumoto, “Japanese Dependency Analysis using Cascaded Chunking,” The journal of Information Processing Society of Japan, Vol.43, No.6, pp. 1834-1842, 2002 (in Japanese).
6. [6]Yahoo API, http://developer.yahoo.co.jp/