Context: Sentiment analysis is an NLP technique that can be used to automatically obtain the sentiment of a crowd of end-users regarding a software application. However, applying sentiment analysis is a difficult task, especially considering the need of obtaining enough good quality data for training a Machine Learning (ML) model. To address this challenge, transfer learning can help us save time and get better performance results with a limited amount of data. Objective: In this paper, we aim at identifying to which degree transfer learning improves the results of sentiment analysis of messages shared by end-users in social media. Method: We propose a tool-supported framework able to monitor and analyze the sentiment of tweets with different ML models and settings. Using the proposed framework, we apply transfer learning and conduct a set of experiments with multiple datasets. Results: The performance of different ML models with transfer learning from different datasets are obtained and discussed, showing how different factors affect the results, and discussing how they have to be considered when applying transfer learning.

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, F1score 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.