Towards Sentiment and Emotion Analysis of User Feedback for Digital Libraries

The possibility for people to leave comments in blogs and forums on the Internet allows to study their attitude (in terms of valence or even of specific feelings) on various topics. For some digital libraries this may be a precious opportunity to understand how their content is perceived by their users and, as a consequence, to suitably direct their future strategic choices. So, libraries might want to enrich their sites with the possibility, for their users, to provide feedback on the items they have consulted. Of course, manually analyzing all the available comments would be infeasible. Sentiment Analysis, Opinion Mining and Emotion Analysis denote the area of research in Computer Science aimed at automatically analyzing and classifying text documents based on the underlying opinions expressed by their authors. Significant problems in building an automatic system for this purpose are given by the complexity of natural language, by the need of dealing with several languages, and by the choice of relevant features and of good approaches to building the models. Following the interesting results obtained for Italian by a system based on a Text Categorization approach, this paper proposes further experiments to check whether reliable predictions can be obtained, both for opinions and for feelings.