Article: DenseNet-based attentive plot-aware recommendation Journal: International Journal of High Performance Systems Architecture (IJHPSA) 2020 Vol.9 No.2/3 pp.77 - 86 Abstract: Since the ratings matrix is always sparse, auxiliary information has been proved very important in recommender systems. In this paper, we propose a DenseNet-based attentive plot-aware recommendation (DAPR) model, which combines attention mechanism and densely connected convolutional networks (i.e., DenseNet) to fully mine the semantic information in the movie plot text. This method effectively fuses rating information and text information for ratings prediction. Extensive experiments on three popular datasets demonstrate that our model performs better than other state-of-the-art approaches in common recommendation tasks. Inderscience Publishers - linking academia, business and industry through research

Title: DenseNet-based attentive plot-aware recommendation

Authors: SuHua Wang; ZhiQiang Ma; XiaoXin Sun; Yue Yuan

Addresses: Department of Computer, College of Environment, College of Humanities & Sciences, Northeast Normal University, 130033 No. 2555, Jingyue street, Jingyue Development Zone, Changchun City, Jilin Province, China ' Department of Computer, College of Humanities & Sciences, Northeast Normal University, 130033 No.1488 Boshuo Road, High Tech Industrial Development Zone, Nanguan District, Changchun City, Jilin Province, China ' Department of Computer, College of Information Science and Technology, Northeast Normal University, 130033 No. 2555, Jingyue street, Jingyue Development Zone, Changchun City, Jilin Province, China ' Department of Computer, College of Information Science and Technology, Northeast Normal University, 130033 No. 2555, Jingyue street, Jingyue Development Zone, Changchun City, Jilin Province, China

Abstract: Since the ratings matrix is always sparse, auxiliary information has been proved very important in recommender systems. In this paper, we propose a DenseNet-based attentive plot-aware recommendation (DAPR) model, which combines attention mechanism and densely connected convolutional networks (i.e., DenseNet) to fully mine the semantic information in the movie plot text. This method effectively fuses rating information and text information for ratings prediction. Extensive experiments on three popular datasets demonstrate that our model performs better than other state-of-the-art approaches in common recommendation tasks.

Keywords: DenseNet; plot-aware; attention; rating prediction; deep learning; recommendation system; social networks; collaborative filtering; cold start; movie recommendation.

DOI: 10.1504/IJHPSA.2020.111556

International Journal of High Performance Systems Architecture, 2020 Vol.9 No.2/3, pp.77 - 86

Received: 30 Nov 2019
Accepted: 22 Jan 2020
Published online: 01 Dec 2020 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article

Title: DenseNet-based attentive plot-aware recommendation

Keep up-to-date