Research Area: Machine Learning
Emotion Analysis extends the idea of Sentiment Analysis by shifting from plain positive or negative sentiments to a rich variety of emotions to get better understanding of the users thoughts and appraisals. The move from Sentiment Analysis to Emotion Analysis requires, however, better feature engineering techniques when it comes to capturing complex language phenomena, which have to do with figurative language and the way of expressing oneself. In this manuscript we detail the participation of the UMUTeam in EmoEvalEs 2021 shared task from IberLEF, concerning the identification of emotions in Spanish. Our proposal is grounded on the combination of explainable linguistic features and state-of-the-art transformers based on the Spanish version of BERT. We achieved the 6th position in the official leader board with an accuracy of 68.5990%, only 4.1667% below the best result. In addition, we apply model agnostic techniques for explainable artificial intelligence to achieve insights from the linguistic features. We observed a correlation between psycho-linguistic processes and perceptual feel with the emotions evaluated and, pecifically, with documents labelled as sadness.
Keywords:
UMUTeam
EmoEvalEs
Emosjon Analysis
Explainable Linguistic Features
Transformers
Author(s) Name: García-Díaz, José Antonio; Colomo-Palacios, Ricardo; Valencia-Garcia, Rafael
Journal name: CEUR Workshop Proceedings
Conferrence name:
Publisher name: Technical University of Aachen
DOI:
Volume Information:
