A Personalized Literature Recommendation Method Based on the Domain-Driven User Interest Model
Download as PDF
DOI: 10.23977/icamcs.2017.1032
Author(s)
Sheng Wenjin, Yan Jianzhuo, Chen Jianhui, Lv Ruying, Kuai Hongzhi
Corresponding Author
Sheng Wenjin
ABSTRACT
At present, literature is the most important source of scientific knowledge. However, in the face of the information overload caused by the explosive growth of scientific literatures, it is difficult for researchers to find the literature that is really needed quickly. This is particularly acute in the current universal concern field of cognitive science. This paper forms a personalized literature recommendation method based on domain–driven user interest model. By adopting the recommendation method based on BI provenances, initial literatures can be acquired from the first recommendation module. Furthermore, spread activation theory is added into the second recommendation module for obtaining user interest model. Results of experiments show that the proposed method can make full use of the advantages of the two modules, which can not only recommend literatures that relevant to the user’s research interests but also recommend literatures that in other relevant heat research domain.
KEYWORDS
literature recommendation, cognitive science, spread activation theory, domain-driven user interest model