Data Analysis and Knowledge Discovery  2020, Vol. 4 Issue (12): 76-84    DOI: 10.11925/infotech.2096-3467.2020.0327
 Current Issue | Archive | Adv Search |
Matrix Factorization Algorithm with Weighted Heterogeneous Information Network
Wang Gensheng1,2(),Pan Fangzheng1
1School of Humanities, Jiangxi University of Finance and Economics, Nanchang 330013, China
2School of International Trade and Economics, Jiangxi University of Finance and Economics,Nanchang 330013, China
 Download: PDF (1236 KB)   HTML ( 2 )  Export: BibTeX | EndNote (RIS)
Abstract

[Objective] This paper integrates the knowledge of weighted heterogeneous information network to the matrix decomposition algorithm, aiming to improve the quality of recommendation. [Methods] First, we constructed a heterogeneous information network, and calculated the weight of connection with the improved tanh function. Then, we chose the meta paths from the network and computed their weights based on information gains. Third, we decided the similarity of user interests to create a matrix, and integrated the matrix with our algorithm. [Results] We examined the proposed algorithm with the Hetrec2011-MovieLens-2k dataset. Compared with the traditional FunkSVD algorithm, the precision, recall and coverage of our algorithm increased by 4.4%, 5.4%, and 4.6%, while its root mean square error reduced by 0.06. [Limitations] The matrix decomposition algorithm could not process massive data efficiently, and we did not investigate the drifting issues of user interests. [Conclusions] The proposed algorithm could effectively generate recommendation results.

Received: 17 April 2020      Published: 25 December 2020
 ZTFLH: TP393
Corresponding Authors: Wang Gensheng     E-mail: wgs74@126.com
 Heterogeneous Information Network Instance Network Schema Example Algorithm Flow FU_w Function Typical Meta Path and Its Semantics in Heterogeneous Information of Movie Recommendation Details of Different Nodes Mixed Matrix Setting of Experimental Parameters Experimental Results in Different User and Movie Feature Dimensions Experimental Results with Different $λ1$ Experimental Comparison of tanh and Directly Based on the Original Scoring Methods Experimental Results of Different Matrix Factorization Recommendation Algorithms