Skip to main content

Tag−Aware Personalized Recommendation Using a Deep−Semantic Similarity Model with Negative Sampling

Zhenghua Xu‚ Cheng Chen‚ Thomas Lukasiewicz‚ Yishu Miao and Xiangwu Meng


With the rapid growth of social tagging systems, many efforts have been put on tag-aware personalized recommendation. However, due to uncontrolled vocabularies, social tags are usually redundant, sparse, and ambiguous. In this paper, we propose a deep neural network approach to solve this problem by mapping both the tag-based user and item profiles to an abstract deep feature space, where the deep semantic similarities between users and their target items (resp., irrelevant items) are maximized (resp., minimized). Due to huge numbers of online items, the training of this model is usually computationally expensive in the real-world context. Therefore, we introduce negative sampling, which significantly increases the model’s training efficiency (109.6 times quicker) and ensures the scalability in practice. Experimental results show that our model can significantly outperform the state-of-the-art baselines in tag-aware personalized recommendation: e.g., its mean reciprocal rank is between 5.7 and 16.5 times better than the baselines.

Book Title
Proceedings of the 25th ACM International Conference on Information and Knowledge Management‚ CIKM 2016‚ Indianapolis‚ USA‚ October 24−28‚ 2016
Elisa Bertino and Fabio Crestani and Javed Mostafa and Jie Tang and Luo Si and Xiaofang Zhou
ACM Press