Personalized Recommendation Combining User Interest and Social Circle

By Xueming Qian, He Feng, Guoshuai Zhao, Tao Mei. IEEE Transactions on Knowledge and Data Engineering, 2014

393 citations recorded by the source corpus.

Subfields: Computer Networks and Communications, Information Systems

View Paper: https://www.semanticscholar.org/paper/fa0a6c81415c34d6793166ad79d94d6783252ea9

How researchers see this paper

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

In Computer Networks and Communications

1. Le Wu
2. Peijie Sun
3. Meng Wang
4. Richang Hong

In Information Systems

1. Le Wu
2. Meng Wang
3. Richang Hong
4. Xiting Wang
5. Yanjie Fu
6. Peijie Sun
7. Xiangnan He
8. Xiang Wang

Citations in the corpus

• Short Text Topic Modeling Techniques, Applications, and Performance: A Survey (2019, neutral): “Content analysis is crucial for content recommendation for microblogging users [44], [45].”
• Ieee Transactions on Knowledge and Data Engineering, Manuscropt Id 1 Social Recommendation with Cross-domain Transferable Knowledge (neutral): “Tie strength can refer to homophily [5], circle-based influence [6][7][8], or social trust [9][10].”
• Neural Compatibility Modeling with Attentive Knowledge Distillation (2018, neutral): “Due to the sparsity of our dataset, where matrix factorization based methods [24, 32] are not applicable, we chose the following content-based baselines regarding compatibility modeling to evaluate the proposed model AKD-DBPR.”
• Neural Compatibility Modeling With Probabilistic Knowledge Distillation (2020, neutral): “Due to the sparsity of our dataset, the matrix factorization based methods [44][45][46][47] are not much suitable.”
• A Neural Influence Diffusion Model for Social Recommendation (2019, positive): “social context and social network under a collective matrix factorization framework with carefully designed regularization terms [17]. Social recommendation has also been extended with social circles [28] and the temporal context [35]. Recently, the problem of how bridge a few overlapping users in t”
• DiffNet++: A Neural Influence and Interest Diffusion Network for Social Recommendation (2020, neutral): “Social recommendation has also been extended with social circles [29], temporal context [33], rich contextual information [36], and efficient training models without negative sampling [6].”
• Explainable Outfit Recommendation with Joint Outfit Matching and Comment Generation (2018, neutral): “orative filtering, cannot learn effective latent factors [60], [61].”