Rule-Based computation of semantic orientation for chinese sentence

Authors:
Jiang Yang;Min Hou
Affiliations:
School of Foreign Studies, Hunan University of Science and Technology, Xiangtan, China;Broadcast Media Language Branch, Communication University of China, Beijing, China
Venue:
CLSW'12 Proceedings of the 13th Chinese conference on Chinese Lexical Semantics
Year:
2012

Citing 6
Cited 0

Predicting the semantic orientation of adjectives

ACL '98 Proceedings of the 35th Annual Meeting of the Association for Computational Linguistics and Eighth Conference of the European Chapter of the Association for Computational Linguistics
Thumbs up or thumbs down?: semantic orientation applied to unsupervised classification of reviews

ACL '02 Proceedings of the 40th Annual Meeting on Association for Computational Linguistics
Seeing stars: exploiting class relationships for sentiment categorization with respect to rating scales

ACL '05 Proceedings of the 43rd Annual Meeting on Association for Computational Linguistics
A holistic lexicon-based approach to opinion mining

WSDM '08 Proceedings of the 2008 International Conference on Web Search and Data Mining
Just how mad are you? finding strong and weak opinion clauses

AAAI'04 Proceedings of the 19th national conference on Artifical intelligence
Lexicon-based methods for sentiment analysis

Computational Linguistics

Quantified Score

Hi-index	0.00

Visualization

Abstract

Semantic Orientation refers to the positive or negative attitude, standpoint or opinion on a certain person, object or affair. It is of degree diversity and combinability. Rule-based computation of SO for Chinese sentence, after pre-processing the input sentence in lexical and dependency syntax analysis, takes advantage of the syntax analysis results and combines the pre-compiled dictionary resources to apply classification, recognition, combination, computation and disambiguation rules step by step respectively to the tasks of subjectiveness and objectiveness classification, SO discrimination and SO computation. Experiment on this approach achieves an accuracy of 78.25%, proving its effectiveness and validity.