Generating domain-specific affective ontology from Chinese reviews for sentiment analysis

被引：2
|
作者：
Liu L.-Z. [1 ]
Liu H. [1 ]
Wang H.-S. [1 ]
Song W. [1 ]
Zhao X.-L. [1 ]
机构：
[1] College of Information Engineering, Capital Normal University, Beijing
来源：
Journal of Shanghai Jiaotong University (Science) | 2015年 / 20卷 / 01期
关键词：
affective ontology; Chinese reviews; product features; sentimentanalysis;
D O I：
10.1007/s12204-015-1584-0
中图分类号：
TP3 [计算技术、计算机技术];
学科分类号：
0812 ;
摘要：
Considering the diversities and ambiguities of opinion expressions in Chinese online product reviews, normal sentiment analysis technologies have exposed their inadequateness in both classification accuracy and identifying effectiveness. We propose a novel approach which can easily identify product features and corresponding opinions by building a domain-specific affective ontology and thus mapping comment sentences to the objects defined in the affective ontology. Ontology is created automatically by processing the online reviews; both product features and affective words are presented as nodes which are connected to each other by their semantic relationship. Furthermore, in order to increase the accuracy, we introduce a dynamic polarity detection technique for affective words whose sentimental tendencies are dependent on particular contexts. The experimental results clearly demonstrate the performance improvement of our approach compared with others in real world online product reviews for classification tests. © 2015, Shanghai Jiaotong University and Springer-Verlag Berlin Heidelberg.
引用
收藏
页码：32 / 37
页数：5
相关论文
共 50 条
  • [1] Generating Domain-Specific Affective Ontology from Chinese Reviews for Sentiment Analysis
    刘丽珍
    刘昊
    王函石
    宋巍
    赵新蕾
    [J]. Journal of Shanghai Jiaotong University(Science), 2015, 20 (01) : 32 - 37
  • [2] Combining Domain-Specific Sentiment Lexicon with Hownet for Chinese Sentiment Analysis
    Liu, Lizhen
    Lei, Mengyun
    Wang, Hanshi
    [J]. JOURNAL OF COMPUTERS, 2013, 8 (04) : 878 - 883
  • [3] Sentiment Analysis for Domain-Specific Texts
    Yanagimoto, Hidekazu
    Yoshioka, Michifumi
    [J]. PROCEEDINGS OF THE SEVENTEENTH INTERNATIONAL SYMPOSIUM ON ARTIFICIAL LIFE AND ROBOTICS (AROB 17TH '12), 2012, : 791 - 794
  • [4] Generating domain-specific methodical knowledge for requirement analysis based on methodology ontology
    Lin, CYI
    Ho, CS
    [J]. INFORMATION SCIENCES, 1999, 114 (1-4) : 127 - 164
  • [5] ReNew: A Semi-Supervised Framework for Generating Domain-Specific Lexicons and Sentiment Analysis
    Zhang, Zhe
    Singh, Munindar P.
    [J]. PROCEEDINGS OF THE 52ND ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, VOL 1, 2014, : 542 - 551
  • [6] Generate domain-specific sentiment lexicon for review sentiment analysis
    Hongyu Han
    Jianpei Zhang
    Jing Yang
    Yiran Shen
    Yongshi Zhang
    [J]. Multimedia Tools and Applications, 2018, 77 : 21265 - 21280
  • [7] Generate domain-specific sentiment lexicon for review sentiment analysis
    Han, Hongyu
    Zhang, Jianpei
    Yang, Jing
    Shen, Yiran
    Zhang, Yongshi
    [J]. MULTIMEDIA TOOLS AND APPLICATIONS, 2018, 77 (16) : 21265 - 21280
  • [8] Domain-specific ontology of botany
    Gu, F
    Cao, CG
    Sui, YF
    Wen, TA
    [J]. JOURNAL OF COMPUTER SCIENCE AND TECHNOLOGY, 2004, 19 (02) : 238 - 248
  • [9] Domain-specific ontology of botany
    Fang Gu
    Cun-Gen Cao
    Yue-Fei Sui
    Wen Tian
    [J]. Journal of Computer Science and Technology, 2004, 19 : 238 - 248
  • [10] A Unified Approach for Domain-Specific Tweet Sentiment Analysis
    Ribeiro, Patricia L. V.
    Li Weigang
    Li, Tiancheng
    [J]. 2015 18TH INTERNATIONAL CONFERENCE ON INFORMATION FUSION (FUSION), 2015, : 846 - 853
12345