Using Social Elements to Recommend Sessions in Academic Events

Academic events bring together a large number of researchers and are composed of different types of sessions, which can cause overload of attention and difficulty deciding which sessions to participate. To deal with such problems, Recommender Systems can assist users by offering options that are appropriate for each user. This paper aims to present a recommender approach for sessions of academic events making use of social elements. We propose a recommendation using the academic event’s co-authoring network to improve the quality of session recommendation based on the users’ previous publications. For authors/participants who do not have publications in previous editions of the event, the recommendations will be generated through the Collaborative Filtering approach. In order to evaluate the viability of our approach, it was included in an Academic Event Application called AppIHC and participants were invited to answer a questionnaire about its use. The results indicate the approach is promising and other social elements could be included future versions.