Joint Topic-Semantic-aware Social Recommendation for Online Voting

By Hongwei Wang, Jia Wang, Miao Zhao, Jiannong Cao, Minyi Guo. 2017

32 citations recorded by the source corpus.

Online voting is an emerging feature in social networks, in which users can express their attitudes toward various issues and show their unique interest. Online voting imposes new challenges on recommendation, because the propagation of votings heavily depends on the structure of social networks as well as the content of votings. In this paper, we investigate how to utilize these two factors in a comprehensive manner when doing voting recommendation. First, due to the fact that existing text mining methods such as topic model and semantic model cannot well process the content of votings that is typically short and ambiguous, we propose a novel Topic-Enhanced Word Embedding (TEWE) method to learn word and document representation by jointly considering their topics and semantics. Then we propose our Joint Topic-Semantic-aware social Matrix Factorization (JTS-MF) model for voting recommendation. JTS-MF model calculates similarity among users and votings by combining their TEWE representation and structural information of social networks, and preserves this topic-semantic-social similarity during matrix factorization. To evaluate the performance of TEWE representation and JTS-MF model, we conduct extensive experiments on real online voting dataset. The results prove the efficacy of our approach against several state-of-the-art baselines.

Subfields: Recommender Systems

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Recommender Systems

1. Xing Xie
2. Wenjie Li
3. Hongwei Wang
4. Miao Zhao
5. Fuzheng Zhang
6. Minyi Guo
7. Zhongyuan Wang
8. Jure Leskovec

Citations in the corpus

• Knowledge Graph Convolutional Networks for Recommender Systems (2019, background): “raditionalrecommendationtechniqueiscollaborativefiltering (CF),which assigns usersand items ID-based representation vectors, then models their interactions by specific operation such as inner product [16] or neural networks [8]. However, CF-based methods usually suffer from sparsity of user-item int”
• RippleNet: Propagating User Preferences on the Knowledge Graph for Recommender Systems (2018, background): “Traditional CF-basedmethods and their variants [11, 31] learn latent representations of users and items, then predict unknown ratings by directly applying a specific function to their representations such”
• DKN: Deep Knowledge-Aware Network for News Recommendation (2018, methodology): “Traditional methods [1, 43] usually represent sentences using the bag-of-words (BOW) technique, i.e., taking word counting statistics as the feature of sentences.”
• SHINE: Signed Heterogeneous Information Network Embedding for Sentiment Link Prediction (2017, background): “Our choices are enlightened by [27] and [34], respectively, in which [27] demonstrates that the structural information of social networks can greatly affect users’ preference towards online items, and [34] proves that information from knowledge base could boost the performance of recommendation.”
• Knowledge-aware Graph Neural Networks with Label Smoothness Regularization for Recommender Systems (2019, background): “3330836 based on collaborative filtering [13, 22] usually suffer from the coldstart problem and have trouble recommending brand new items that have not yet been heavily explored by the users.”
• Multi-Task Feature Learning for Knowledge Graph Enhanced Recommendation (2019, background): “Roughly speaking, deep recommender systems can be classified into two categories: (1) Using deep neural networks to process the raw features of users or items [5, 28–30, 40]; For example, Collaborative Deep Learning [29] designs autoencoders to extract short and dense features from textual input and”