Learning the mapping rules for sentiment analysis

Saravadee Sae Tan, Lay Ki Soon, Tek Yong Lim, Enya Kong Tang, Chu Kiong Loo

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

Abstract

There is an increasing popularity of people posting their feel-ings on microblogging such as Twitter. Sentiment analysis on the tweets allows organizations to monitor public' feelings towards a product or brand. In this paper, we model sentiment analysis problem as a multi-classcation approach that utilizes various feature types, including predicate-argument relation, hashtag, mention and emotion in the tweets. We describe a Content-Structure Correspondence (CSC) model that is able to represent diverse feature types in a tweet. We present a conceptual hierarchy to express the characteristics of a tweet. A multi-classsifcation approach is used to map tweet content to the conceptual hierarchy. The mapping patterns are learned to identify the sentiment of a tweet.

Original languageEnglish
Title of host publicationWeb-KR '14: Proceedings of the 5th International Workshop on Web-scale Knowledge Representation Retrieval & Reasoning
Pages19-22
Number of pages4
DOIs
Publication statusPublished - 3 Nov 2014
Externally publishedYes
EventInternational Workshop on Web-scale Knowledge Representation Retrieval and Reasoning 2014 - Shanghai, China
Duration: 3 Nov 20143 Nov 2014
Conference number: 5th
https://dl.acm.org/doi/proceedings/10.1145/2663792 (Proceedings)

Conference

ConferenceInternational Workshop on Web-scale Knowledge Representation Retrieval and Reasoning 2014
Abbreviated titleWeb-KR 2014
CountryChina
CityShanghai
Period3/11/143/11/14
Internet address

Keywords

  • Multi-classification
  • Predicate-argument relation
  • Sentiment analysis

Cite this