Applying Sentiment Analysis with Cross-Domain Models to Evaluate User eXperience in Virtual Learning Environments

Virtual Learning Environments are growing in importance as fast as e-learning is becoming highly demanded by universities and students all over the world. This paper investigates how to automatically evaluate User eXperience in this domain. Two Learning Management Systems have been evaluated, one system is an ad-hoc system called “Conecto” (in Spanish and English languages), and the other one is an open-source Moodle personalized system (in Spanish). We have applied machine learning tools to all the comments given by a total of 133 users (37 English speakers and 96 Spanish speakers) to obtain their polarity (positive, negative, or neutral) using cross-domain models trained with a corpus of a different domain (tweets for each language) and general models for the language. The obtained results are very promising and they give an insight to keep going the research of applying sentiment analysis tools on User eXperience evaluation. This is a pioneering idea to provide a better and accurate understanding on human needs in the interaction with Virtual Learning Environments. The ultimate goal is to develop further tools of automatic feed-back of user perception for designing Virtual Learning Environments centered in user’s emotions, beliefs, preferences, perceptions, responses, behaviors and accomplishments that occur before, during and after the interaction.