Abstract

The integration of Sentiment Analysis and spoken conversational interfaces provides mutual benefits that enable using context-awareness information to enhance the performance of these interfaces, achieving a more efficient and proactive human-machine communication that can be dynamically adapted to the user's emotional state. In this paper, we describe a novel Sentiment Analysis approach combining a lexicon-based model for specifying the set of emotions and a statistical methodology to identify the most relevant topics in the document that are the targets of the sentiments. Our proposal also includes an heuristic learning method that allows improving the initial knowledge considering the users' feedback. We have integrated the proposed Sentiment Analysis approach into an Android-based mobile App that automatically assigns sentiments to pictures taking into account the description provided by the users.