| Presentation | 2007/7/17 Sentiment Classification of Sentences by Modeling Word-Level Polarity-Shifters Daisuke IKEDA, Hiroya TAKAMURA, Lev-Arie Ratinov, Manabu OKUMURA, |
|---|---|
| PDF Download Page | PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | In this paper, we propose a machine learning method that uses word-level semantic orientations for sentiment classification of sentences. The simplest solution to this problem would be the majority voting by the number of positive words and the number of negative words in the given sentence. However, the semantic orientations of words in a sentence are not always the same as that of the sentence, because there can be polarity-shifters such as negation expressions. This inconsistency of word-level orientation and sentence-level orientation often causes errors in classification by the simple majority voting method. The machine learning method that we propose in this paper models the polarity-shifters. Our model can be trained in two different levelsrword level and sentence level. While the word-level training focuses on the prediction of polarity shifts, the sentence-level training focuses more on the prediction of sentence orientations. The model can also combined with features used in previous work such as bag-of-words and dependency trees. We report that the proposed method improves the accuracy of sentence classification by up to 4.2 points compared with other simpler methods. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Sentiment Classification of Sentences / Polarity-Shifting Model / Sentiment Dictionary |
| Paper # | NLC2007-8 |
| Date of Issue |
| Conference Information | |
| Committee | NLC |
|---|---|
| Conference Date | 2007/7/17(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) | Sentiment Classification of Sentences by Modeling Word-Level Polarity-Shifters |
| Sub Title (in English) | |
| Keyword(1) | Sentiment Classification of Sentences |
| Keyword(2) | Polarity-Shifting Model |
| Keyword(3) | Sentiment Dictionary |
| 1st Author's Name | Daisuke IKEDA |
| 1st Author's Affiliation | Interdisciplinary Graduate School of Science and Engineering, Tokyo Institute of Technology() |
| 2nd Author's Name | Hiroya TAKAMURA |
| 2nd Author's Affiliation | Precision and Intelligence Laboratory, Tokyo Institute of Technology |
| 3rd Author's Name | Lev-Arie Ratinov |
| 3rd Author's Affiliation | Department of Computer Science, University of Illinois at Urbana-Champaign |
| 4th Author's Name | Manabu OKUMURA |
| 4th Author's Affiliation | Precision and Intelligence Laboratory, Tokyo Institute of Technology |
| Date | 2007/7/17 |
| Paper # | NLC2007-8 |
| Volume (vol) | vol.107 |
| Number (no) | 158 |
| Page | pp.pp.- |
| #Pages | 6 |
| Date of Issue | |