Abstract | ||
---|---|---|
When looking for recently published scientific papers, a researcher usually focuses on the topics related to her/his scientific interests. The task of a recommender system is to provide a list of unseen papers that match these topics. The core idea of this paper is to leverage the latent topics of interest in the publications of the researchers, and to take advantage of the social structure of the researchers (relations among researchers in the same field) as reliable sources of knowledge to improve the recommendation effectiveness. In particular, we introduce a hybrid approach to the task of scientific papers recommendation, which combines content analysis based on probabilistic topic modeling and ideas from collaborative filtering based on a relevance-based language model. We conducted an experimental study on DBLP, which demonstrates that our approach is promising. |
Year | DOI | Venue |
---|---|---|
2017 | 10.1145/3106426.3106479 | WI |
Keywords | Field | DocType |
Scientific paper recommendation, Hybrid approaches, Language modeling, LDA | Recommender system,Data science,Data mining,Graph,Content analysis,Collaborative filtering,Information retrieval,Probabilistic topic modeling,Computer science,Topic model,Language model | Conference |
ISBN | Citations | PageRank |
978-1-4503-4951-2 | 3 | 0.39 |
References | Authors | |
23 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Maha Amami | 1 | 13 | 1.98 |
Rim Faiz | 2 | 98 | 36.23 |
Fabio Stella | 3 | 160 | 19.72 |
Gabriella Pasi | 4 | 1673 | 169.31 |