SentiTegi: Semi-manually Created Semantic Oriented Basque Lexicon for Sentiment Analysis

Abstract

The creation of a semantic oriented lexicon of positive and negative words is often the first step to analyze the sentiment of a corpus. Various methods can be employed to create a lexicon: supervised and unsupervised. Until now, methods employed to create Basque polarity lexicons were unsupervised. The aim of this paper is to present the construction and evaluation of the first semantic oriented supervised Basque lexicon ranging from $+$5 to $-$5. Due to the lack of resources, the Basque lexicon was created translating the SO-CAL Spanish dictionary by means of two bilingual dictionaries following specific criteria and then slightly corrected with the SO-CAL English dictionary and frequency data obtained from the Basque Opinion Corpus. Evaluation results show that the correlation between human annotators is slightly better than between a gold standard lexicon (obtained from human annotation) and the translated dictionary. This shows that the quality of the translated lexicon is satisfactory, although there is a space to improve it.