Presentation | 2008/7/10 Analyzing Context Dependent Polarity Expressions by Using Antonyms YOSHIKAZU SAKAI, KENJI ARAKI, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | This paper presents a method for automatically classifying evaluative expression extracted from large amount of Web documents. Some of the expression like "large", "small" has a problem to be difficult to classify as positive or negative based on one word. Then we are based on the research of evaluative expression consisting of multiple words, and try to classify them. Using the number of hits returned by a Web search engine and the antonyms can get rid of the cost. Through experiments, we achieves an accuracy of 74% when system covers 80% data, and confirmed the effectiveness of our proposed method. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | opinion extraction / sentiment polarity / evaluative analysis |
Paper # | NLC2008-5 |
Date of Issue |
Conference Information | |
Committee | NLC |
---|---|
Conference Date | 2008/7/10(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) | Analyzing Context Dependent Polarity Expressions by Using Antonyms |
Sub Title (in English) | |
Keyword(1) | opinion extraction |
Keyword(2) | sentiment polarity |
Keyword(3) | evaluative analysis |
1st Author's Name | YOSHIKAZU SAKAI |
1st Author's Affiliation | Graduate School of Infomation Science and Technology, Hokkaido University() |
2nd Author's Name | KENJI ARAKI |
2nd Author's Affiliation | Graduate School of Infomation Science and Technology, Hokkaido University |
Date | 2008/7/10 |
Paper # | NLC2008-5 |
Volume (vol) | vol.108 |
Number (no) | 141 |
Page | pp.pp.- |
#Pages | 6 |
Date of Issue |