Presentation | 2012-08-30 Emotion Estimation of Commentary Tweets Yasuhiro TAJIMA, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | We propose estimation performances about emotion of tweets attached to web news articles. The estimation mathod is a naive vector model of words in tweets. We compare two machine learning methods, naive bayes and maximum entropy method. For the estimation, we obtain 0.5 to 0.6 F-value by naive bayes method, and 0.8 to 0.9 F-value for maximum entropy method. Especially, the estimation results by maximum entropy method are more stable than that of naive bayes method. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | emotion estimation / tweets / micro blog / maximum entorpy method |
Paper # | NLC2012-16 |
Date of Issue |
Conference Information | |
Committee | NLC |
---|---|
Conference Date | 2012/8/23(1days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | |
Chair | |
Vice Chair | |
Secretary | |
Assistant |
Paper Information | |
Registration To | Natural Language Understanding and Models of Communication (NLC) |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Emotion Estimation of Commentary Tweets |
Sub Title (in English) | |
Keyword(1) | emotion estimation |
Keyword(2) | tweets |
Keyword(3) | micro blog |
Keyword(4) | maximum entorpy method |
1st Author's Name | Yasuhiro TAJIMA |
1st Author's Affiliation | Okayama Prefectural University() |
Date | 2012-08-30 |
Paper # | NLC2012-16 |
Volume (vol) | vol.112 |
Number (no) | 196 |
Page | pp.pp.- |
#Pages | 4 |
Date of Issue |