Recommendation System

Research paper recommenders emerged over the last decade to ease finding publications relating toresearchers’ area of interest. The challenge was not just to provide researchers with very rich publications atany time, any place and in any form but to also offer the right publication to the right researcher in the rightway. Several approaches exist in handling paper recommender systems. However, these approachesassumed the availability of the whole contents of the recommending papers to be freely accessible, which isnot always true due to factors such as copyright restrictions. This paper presents a collaborative approach forresearch paper recommender system. By leveraging the advantages of collab- orative filtering approach, weutilize the publicly available contextual metadata to infer the hidden associations that exist betweenresearch papers in order to personalize recommen- dations. The novelty of our proposed approach is that itprovides personalized recommen- dations regardless of the research field and regardless of the user’sexpertise. Using a publicly available dataset, our proposed approach has recorded a significant improvementover other baseline methods in measuring both the overall performance and the ability to return relevant anduseful publications at the top of the recommendation list.