Social networks are one of the most preferred environments for people to carry out debates. Since a large amount of people can participate in the process, there is a need for tools that can analyse these discussions and extract useful information from them. In this paper we present a novel way to determine how the debate is progressing, if there is a consensus among the participants and which alternatives are preferred. Sentiment analysis is used to measure the preference level social media users have regarding a certain set of alternatives. To test the presented scheme, a real application example that makes use of information taken from Twitter is presented. (C) 2018 Elsevier Inc. All rights reserved.