Polarity classification for Spanish tweets using the COST corpus. (June 2015)

• Record Type: Journal Article
• Authors: Martínez-Cámara, Eugenio; Martín-Valdivia, M. Teresa; Ureña-López, L. Alfonso; Mitkov, Ruslan
• Is Part Of: Journal of information science. Volume 41:Number 3(2015)
• Page Start: 263
• Page End: 272
• Publication Date: 2015-06
• Subjects: Opinion mining -- polarity classification -- sentiment analysis -- short text analysis -- social networks -- Spanish corpus -- Twitter; Information science -- Periodicals; Information science; Periodicals; 020.5
• DOI: 10.1177/0165551514566564
• Languages: English
• ISSNs: 0165-5515

Abstract

It was not until 2010 when businesses, politicians and people in general began to realize the potential of Twitter in Spain. This fact has awoken research interest in the extraction of knowledge from Twitter. This paper aims to fill the gap of the lack of resources for Twitter sentiment analysis in Spanish by performing a study of different features and machine learning algorithms for classifying the polarity of Twitter posts. The result is a new corpus of Spanish tweets called COST, and we have carried out a wide-ranging experiment in which different machine learning algorithms have been used. Furthermore, we have tested the influence of using different weighting schemes for unigrams, the influence of eliminating stop-words and the application of a stemmer process.