A proposal for a recommender system of scientific relevance

Abstract The objective of this work is to present a proposal of a recommender system taking into account the scientific relevance of research groups and researchers by using indicators able to measure the productivity and impact of their publications. In the introduction, the related topics are presented, emphasizing the use of metadata, semantic textual similarity and bibliometric indicators. The methodology section exposes the steps for the design of the recommender system, considering the information gathering, building semantic knowledge, the use of Data and Text Mining, and the recommendations. Subsequently, a first implementation of the methodology used by a Mexican public university is presented. The results that have been obtained with Data and Text Mining techniques for the textual representation of the research groups are presented. Finally, some conclusions and future work are exposed.