Yeonbin Son, Tai-Woo Chang, Yerim Choi, Journal of Internet Computing and Services, Vol. 20, No. 4, pp. 73-79, Aug. 2019
10.7472/jksii.2019.20.4.73, Full Text:  HTML
Keywords: journal recommendation, importance by decision factors, paper publication history, Machine Learning, Data Analysis

Abstract

Selecting a proper journal to submit a research paper is a difficult task for researchers since there are many journals and various decision factors to consider during the decision process. For this reason, journal recommendation services are exist as a kind of intelligent research assistant which recommend potential journals. The existing services are executing a recommendation based on topic similarity and numerical filtering. However, it is impossible to calculate topic similarity when a researcher does not input paper data, and difficult to input clear numerical values for researchers. Therefore, the journal recommendation method which consider the importance of decision factors is proposed by constructing the preference matrix based on the paper publication history of a researcher. The proposed method was evaluated by using the actual publication history of researchers. The experiment results showed that the proposed method outperformed the compared methods.

Statistics
Cite this article