An Emotional Word Analyzer for Portuguese

 

Maria Inês Maia and José Paulo Leal

6th Symposium on Languages, Applications and Technologies (SLATE 2017), Porto, Portugal

 

The analysis of sentiments, emotions and opinions in texts is increasingly important in the current digital world.
The existing lexicons with emotional annotations for the Portuguese language are oriented to polarities, classifying words as positive, negative or neutral. To identify the emotional load intended by the author it is necessary also to categorize the emotions expressed by individual words.
EmoSpell is an extension of a morphological analyzer with semantic annotations of the emotional value of words. It uses Jspell as the morphological analyzer and a new dictionary with emotional annotations. This dictionary incorporates the lexical base EMOTAIX.PT, which classifies words based on three different levels of emotions - global, specific and intermediate.
This paper describes the generation of the EmoSpell dictionary using three sources, the Jspell Portuguese dictionary and the lexical bases EMOTAIX.PT and SentiLex-PT. Also, this paper details the web application and web service that exploit this dictionary. It presents also a validation of the proposed approach using a corpus of student texts with different emotional loads. The validation compares the analyses provided by EmoSpell with the mentioned emotional lexical bases on the ability to recognize emotional words and extract the dominant emotion from a text.

 

Maia, M. I. & Leal, J. P. (2017). An emotional word analyzer for Portuguese. In R. Queirós, M. Pinto, A. Simões, J.P. Leal, & M. J. Varanda (Eds.). OASIcs-OpenAccess Series in Informatics, 56, 17:1-17. Leibniz: Schloss Dagstuhl-Leibniz-Zentrum fuer Informatik. DOI: 10.4230/OASIcs.SLATE.2017.17

 

Download the communication slides here.