Determining the Polarity of Words through a Common Online Dictionary

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

6 Citations (Scopus)

Abstract

Considerable attention has been given to polarity of words and the creation of large polarity lexicons. Most of the approaches rely on advanced tools like part-of-speech taggers and rich lexical resources such as WordNet. In this paper we show and examine the viability to create a moderate-sized polarity lexicon using only a common online dictionary, five positive and five negative words, a set of highly accurate extraction rules, and a simple yet effective polarity propagation algorithm. The algorithm evaluation results show an accuracy of 84.86% for a lexicon of 3034 words.
Original languageUnknown
Title of host publicationLecture Notes in Computer Science
EditorsL Antunes, H Pinto
PublisherSpringer Berlin / Heidelberg
Pages649-663
Volume7026
ISBN (Print)978-3-642-24768-2
DOIs
Publication statusPublished - 1 Jan 2011
EventProgress in Artificial Intelligence, Procedings of the 15th Portuguese Conference on Artificial Intelligence (EPIA'11) -
Duration: 1 Jan 2011 → …

Conference

ConferenceProgress in Artificial Intelligence, Procedings of the 15th Portuguese Conference on Artificial Intelligence (EPIA'11)
Period1/01/11 → …

Cite this