A context-dependent sentiment analysis of online product reviews based on dependency relationships

Zhijun Yan, Meiming Xing, Dongsong Zhang, Baizhang Ma, Tianmei Wang

    Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

    8 Citations (Scopus)

    Abstract

    Consumers often view online consumer product review as a main channel for obtaining product quality information. Existing studies on product review sentiment analysis usually focus on identifying sentiments of individual reviews as a whole, which may not be effective and helpful for consumers when purchase decisions depend on specific features of products. This study proposes a new feature-level sentiment analysis approach for online product reviews. The proposed method uses an extended PageRank algorithm to extract product features and construct expandable context-dependent sentiment lexicons. Moreover, consumers' sentiment inclinations toward product features expressed in each review can be derived based on term dependency relationships. The empirical evaluation using consumer reviews of two different products shows a higher level of effectiveness of the proposed method for sentiment analysis in comparison to two existing methods. This study provides new research and practical insights on the analysis of online consumer product reviews.

    Original languageEnglish
    Title of host publication35th International Conference on Information Systems "Building a Better World Through Information Systems", ICIS 2014
    PublisherAssociation for Information Systems
    ISBN (Print)9781634396943
    Publication statusPublished - 2014
    Event35th International Conference on Information Systems: Building a Better World Through Information Systems, ICIS 2014 - Auckland, New Zealand
    Duration: 14 Dec 201417 Dec 2014

    Publication series

    Name35th International Conference on Information Systems "Building a Better World Through Information Systems", ICIS 2014

    Conference

    Conference35th International Conference on Information Systems: Building a Better World Through Information Systems, ICIS 2014
    Country/TerritoryNew Zealand
    CityAuckland
    Period14/12/1417/12/14

    Keywords

    • Feature extraction
    • Online product reviews
    • PageRank
    • Sentiment analysis
    • Text mining

    Fingerprint

    Dive into the research topics of 'A context-dependent sentiment analysis of online product reviews based on dependency relationships'. Together they form a unique fingerprint.

    Cite this