A Method to Monitor a BBS Using Feature Extraction of Text Data
Electronic bulletin board (BBS) has a problem which is action to obstruct communications (the authors use “obstruction on bulletin board”). The authors introduced system that aids an operator to find such obstruction based on feature extraction of words which causes harmful psychological effects on readers. We propose a new evaluation method using “Ruination Figure” which is calculated by feature extraction. This index is displayed in two ways of stock chart for BBS operator to see trend of the index and find harmful obstruction in the BBS.
KeywordsFeature Extraction Negative Word Bulletin Board Positive Word Internet Experience
Unable to display preview. Download preview PDF.
- 1.PITCREW CO., L.: Pitcrew co., ltd. (in Japanese) (2002), http://www.pit-crew.co.jp/
- 2.Corporation, N.J.: Netview 2.0 (in Japanese) (2004), http://www.naver.co.jp/
- 3.Matsumura, N., Miura, A., Shibanai, Y., Ohsawa, Y., Ishizuka, M.: The dynamism of 2channel (in Japanese). IPSJ Journal (Japan) 45, 1053–1061 (2004)Google Scholar
- 6.Yasunobu, C., Maruoka, T.: A fuzzy reasoning method for chart technical analysis in financial trading (in Japanese). IPSJ Journal (Japan) 33, 122–129 (1992)Google Scholar