Recommendation of scholarly venues based on dynamic user interests. Issue 2 (May 2017)

• Record Type: Journal Article
• Authors: Alhoori, Hamed; Furuta, Richard
• Is Part Of: Journal of informetrics. Volume 11:Issue 2(2017:Apr.)
• Page Start: 553
• Page End: 563
• Publication Date: 2017-05
• Subjects: Recommender system -- User modeling -- Collaborative filtering -- Scholarly communication -- Social media -- Altmetrics; Library statistics -- Periodicals; Information science -- Statistical methods -- Periodicals; Bibliometrics -- Periodicals; Bibliothèques -- Statistiques -- Périodiques; Sciences de l'information -- Méthodes statistiques -- Périodiques; Bibliométrie -- Périodiques; 020.727
• DOI: 10.1016/j.joi.2017.03.006
• Languages: English
• ISSNs: 1751-1577

Abstract

Highlights: We described an approach to recommend scholarly venues for researchers. It is based on a researcher's current readings and interests. We developed a new weighting strategy for rating venues based on temporal analysis. Our experiments showed improvements in accuracy and ranking quality. Abstract: The ever-growing number of venues publishing academic work makes it difficult for researchers to identify venues that publish data and research most in line with their scholarly interests. A solution is needed, therefore, whereby researchers can identify information dissemination pathways in order to both access and contribute to an existing body of knowledge. In this study, we present a system to recommend scholarly venues rated in terms of relevance to a given researcher's current scholarly pursuits and interests. We collected our data from an academic social network and modeled researchers' scholarly reading behavior in order to propose a new and adaptive implicit rating technique for venues. We present a way to recommend relevant, specialized scholarly venues using these implicit ratings that can provide quick results, even for new researchers without a publication history and for emerging scholarly venues that do not yet have an impact factor. We performed a large-scale experiment with real data to evaluate the current scholarly recommendation system and showed that our proposed system achieves better results than the baseline. The results provide important up-to-the-minute signals that compared with post-publication usage-based metrics represent a closer reflection of a researcher's interests.