Title: A recommendation algorithm based on modified similarity and text content to optimise aggregate diversity
Authors: Shuhao Jiang; Hongyun Zhao; Zhenzhen Li
Addresses: School of Information Engineering, Tianjin University of Commerce, Tianjin 300134, China; School of Electrical and Information Engineering, Tianjin University, Tianjin 300072, China ' School of Science, Tianjin University of Commerce, Tianjin 300134, China ' School of Science, Tianjin University of Commerce, Tianjin 300134, China
Abstract: With the popularity of smartphones, many people use mobile phones to provide personalised recommendations in a smart city. Aggregate diversity is defined as recommending different categories of items to different users. This paper proposes a personalised recommendation method based on modified similarity and text content. The algorithm optimises the similarity value through modified similarity algorithm, solves the problem of unclear item category by extracting the text features of user browsing. And it clusters according to user category preference, and research and practice personalised recommendation algorithm based on aggregate diversity optimisation. Experimental results show that the proposed algorithm can improve the aggregate diversity of recommendation results while ensuring the accuracy of recommendation.
Keywords: personalised recommendation; aggregate diversity; similarity calculation; text features.
International Journal of Ad Hoc and Ubiquitous Computing, 2021 Vol.38 No.1/2/3, pp.151 - 157
Received: 04 Feb 2021
Accepted: 03 Mar 2021
Published online: 22 Nov 2021 *