Recommender system based on scarce information mining. (September 2017)

• Record Type: Journal Article
• Authors: Lu, Wei; Chung, Fu-lai; Lai, Kunfeng; Zhang, Liang
• Is Part Of: Neural networks. Volume 93(2017)
• Page Start: 256
• Page End: 266
• Publication Date: 2017-09
• Subjects: Recommender system -- Probabilistic topic model -- Content-based filtering -- Latent structure interpretation; Neural computers -- Periodicals; Neural networks (Computer science) -- Periodicals; Neural networks (Neurobiology) -- Periodicals; Nervous System -- Periodicals; Ordinateurs neuronaux -- Périodiques; Réseaux neuronaux (Informatique) -- Périodiques; Réseaux neuronaux (Neurobiologie) -- Périodiques; Neural computers; Neural networks (Computer science); Neural networks (Neurobiology); Periodicals; 006.32
• DOI: 10.1016/j.neunet.2017.05.001
• Languages: English
• ISSNs: 0893-6080

Abstract

Abstract: Guessing what user may like is now a typical interface for video recommendation. Nowadays, the highly popular user generated content sites provide various sources of information such as tags for recommendation tasks. Motivated by a real world online video recommendation problem, this work targets at the long tail phenomena of user behavior and the sparsity of item features. A personalized compound recommendation framework for online video recommendation called Dirichlet mixture probit model for information scarcity (DPIS) is hence proposed. Assuming that each clicking sample is generated from a representation of user preferences, DPIS models the sample level topic proportions as a multinomial item vector, and utilizes topical clustering on the user part for recommendation through a probit classifier. As demonstrated by the real-world application, the proposed DPIS achieves better performance in accuracy, perplexity as well as diversity in coverage than traditional methods.