Análisis de dependencias para la marcación de cuentos con emociones

Resumo

This paper presents an approach to automated marking up of English texts with emotional labels (EmoTag), stressing the employing of dependency-based parser (MINIPAR) for the finding of words related to negatives. The approach considers the representation of emotions as emotional dimensions (activation, evaluation and dominance). The first step in order to develop EmoTag was to get a corpus of example texts previously annotated by human evaluators. The results of the word processing was a List of Emotional Words (LEW). Next an algorithm for the automated mark up of text is proposed. This algorithm employs a combination of the LEW resource, the ANEW word list and WordNet for knowledge-based expansion of words not occurring in either. Finally, the algorithm for automated mark up is tested against texts from the original samples used for feature extraction to test its correctness. It is also tested against new text samples to test its coverage. The results are discussed with respect to two main issues: correctness and coverage of the proposed algorithm, and additional techniques and solutions that may be employed to improve the results.