摘要：As the number of digital academic items increases dramatically, it is more and more difficult for a student or researcher to find the expected references in a large academic literature database. Although collaborative filtering and content-based recommendation approaches perform well in some applications, they do not produce satisfactory recommendations for academic items because they fail to reflect researchers’ unique characteristics in terms of authority, popularity, recentness, etc. In this paper, we propose two novel data structures, ALVector, which expresses various objective attributes of an article, and AUVector, which expresses users’ subjective weights for different attributes. Then, we propose a novel personalization-oriented recommendation method that utilizes both the content and non-content attributes in ALVector and AUVector for making recommendations. In order to make the overall best recommendation, the VIKOR algorithm is used with a personalization-oriented method to achieve a compromise solution. A real-world literature data set is used in the experiments. The experimental results show that our method better meets the user’s preference in multiple dimensions simultaneously.
