Every character counts a character based approach to determine political sentiment on twitter

Anastasios Dimas, Panagiotis Kokkinos, Emmanouel Varvarigos

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

Abstract

The rising popularity of social networking platforms, has transformed them into a valuable source of information. Sentiments or opinions expressed through the posts of users can be extracted and applied for various purposes. Information such as determining the political preference (e.g., Republican or Democrat) of a user can be useful, for example, in conducting opinion polls, especially around election time. In this work, we apply two different methodologies for sentiment analysis on Twitter posts and demonstrate the superiority of character based approaches over word based ones in determining political sentiment.

Original languageEnglish
Title of host publicationIC3K 2013; KDIR 2013 - 5th International Conference on Knowledge Discovery and Information Retrieval and KMIS 2013 - 5th International Conference on Knowledge Management and Information Sharing, Proc.
PublisherScitepress
Pages261-266
Number of pages6
ISBN (Print)9789898565754
Publication statusPublished - 2013
Externally publishedYes
EventInternational Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management 2013 - Vilamoura, Algarve, Portugal
Duration: 19 Sep 201322 Sep 2013
Conference number: 5th
http://www.kdir.ic3k.org/?y=2013

Conference

ConferenceInternational Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management 2013
Abbreviated titleIC3K 2013
CountryPortugal
CityVilamoura, Algarve
Period19/09/1322/09/13
Other5th International Conference on Knowledge Discovery and Information Retrieval, KDIR 2013 and the 5th International Conference on Knowledge Management and Information Sharing, KMIS 2013

KDIR
KMIS
KEOD - International Conference on Knowledge Engineering and Ontology Development
Internet address

Keywords

  • Character n-grams
  • Sentiment analysis
  • Twitter

Cite this