Dataset of user's emotional reactions to news articles.

This paper presents a dataset of news articles collected from several Mexican news sources and users' emotional reactions to these news articles. Users were presented with the collected news and, after reading it, were asked to indicate the emotion it provoked in them. The emotions considered were happy, surprised, inspired, moved, neutral, sad, fearful, and angry.

Dataset of controversial news posts in Spanish from the reader's perspective.

This paper presents a corpus of Spanish news posts obtained from X with the annotation of controversy made via crowdsourcing. A total of 60 tweets were obtained from 8 different newspapers. For the annotation task, a survey was developed and sent to 31 different participants to answer it with the controversy level they perceived from the news post summary and headline presented on the post.

Evolutionary Optimization of Ensemble Learning to Determine Sentiment Polarity in an Unbalanced Multiclass Corpus.

Sentiment polarity classification in social media is a very important task, as it enables gathering trends on particular subjects given a set of opinions. Currently, a great advance has been made by using deep learning techniques, such as word embeddings, recurrent neural networks, and encoders, such as BERT. Unfortunately, these techniques require large amounts of data, which, in some cases, is not available.