Acknowledging Discourse Function for Sentiment Analysis

Phillip Smith, M. Lee

    Research output: Chapter in Book/Report/Conference proceedingChapter

    2 Citations (Scopus)


    In this paper, we observe the eects that discourse function attribute to the task of training learned classiers for sentiment analysis. Experimental results from our study show that training on a corpus of primarily persuasive documents can have a negative eect on the performance of supervised sentiment classication. In addition we demonstrate that through use of the Multinomial Nave Bayes classier we can minimise the detrimental eects of discourse function during sentiment analysis.
    Original languageEnglish
    Title of host publicationComputational Linguistics and Intelligent Text Processing: 15th International Conference, CICLing 2014, Kathmandu, Nepal, April 6-12, 2014, Proceedings
    EditorsAlexander Gelbukh
    Place of PublicationBerlin
    PublisherSpringer Verlag
    ISBN (Print)978-3-642-54903-8, 978-3-642-54902-1
    Publication statusPublished - 2014

    Bibliographical note

    The full text is not available on the repository.


    Dive into the research topics of 'Acknowledging Discourse Function for Sentiment Analysis'. Together they form a unique fingerprint.

    Cite this