Merging datasets for emotion analysis

Abstract

Context. Applying sentiment analysis is in general a laborious task. Furthermore, if we add the task of getting a good quality dataset with balanced distribution and enough samples, the job becomes more complicated. Objective. We want to find out whether merging compatible datasets improves emotion analysis based on machine learning (ML) techniques, compared to the original, individual datasets. Method. We obtained two datasets with Covid-19-related tweets written in Spanish, and then built from them two new datasets combining the original ones with different consolidation of balance. We analyzed the results according to precision, recall, F1-score and accuracy. Results. The results obtained show that merging two datasets can improve the performance of ML models, particularly the F1-score, when the merging process follows a strategy that optimizes the balance of the resulting dataset. Conclusions. Merging two datasets can improve the performance of ML models for emotion analysis, whilst saving resources for labeling training data. This might be especially useful for several software engineering activities that leverage on ML-based emotion analysis techniques.