Data from

Abstract

We propose a new approach to recommend scientifc literature, a domain in which the efcient organization and search of information is crucial. The proposed system relies on the hypothesis that two scientifc articles are semantically related if they are co-cited more frequently than they would be by pure chance. This relationship can be quantifed by the probability of co-citation, obtained from a null model that statistically defnes what we consider pure chance. Looking for article pairs that minimize this probability, the system is able to recommend a ranking of articles in response to a given article. This system is included in the co-occurrence paradigm of the feld. More specifcally, it is based on co-cites so it can produce more focused on relatedness than on similarity. Evaluation has been performed on the ACL Anthology collection and on the DBLP dataset, and a new corpus has been compiled to evaluate the capacity of the proposal to fnd relationships beyond similarity. Results show that the system is able to provide, not only articles similar to the submitted one, but also articles presenting other kind of relations, thus providing diversity, i.e. connections to new topics.