Acknowledging discourse function for sentiment analysis

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Colleges, School and Institutes

Abstract

In this paper, we observe the effects that discourse function attribute to the task of training learned classifiers for sentiment analysis. Experimental results from our study show that training on a corpus of primarily persuasive documents can have a negative effect on the performance of supervised sentiment classification. In addition we demonstrate that through use of the Multinomial Naïve Bayes classifier we can minimise the detrimental effects of discourse function during sentiment analysis.

Details

Original languageEnglish
Title of host publicationComputational Linguistics and Intelligent Text Processing
Subtitle of host publication15th International Conference, CICLing 2014, Kathmandu, Nepal, April 6-12, 2014, Proceedings, Part II
EditorsAlexander Gelbukh
Publication statusPublished - 2014
EventComputational Linguistics and Intelligent Text Processing, 15th International Conference, CICLing 2014 - Kathmandu, Nepal, Nepal
Duration: 6 Apr 201412 Apr 2014

Publication series

NameLecture Notes in Computer Science
PublisherSpringer
Volume8404
ISSN (Print)0302-9743

Conference

ConferenceComputational Linguistics and Intelligent Text Processing, 15th International Conference, CICLing 2014
CountryNepal
CityKathmandu, Nepal
Period6/04/1412/04/14