Preference dynamics with multimodal user-item interactions in social media recommendation

作者：

Highlights：

• We capture preference dynamics and the multimodal user-item interactions.

• We design a joint objective function and we propose an efficient optimization algorithm.

• We evaluate our method on benchmark datasets that span at least 13 years.

• Our model significantly outperforms state-of-the-art strategies over the datasets’ time span.

摘要

•We capture preference dynamics and the multimodal user-item interactions.•We design a joint objective function and we propose an efficient optimization algorithm.•We evaluate our method on benchmark datasets that span at least 13 years.•Our model significantly outperforms state-of-the-art strategies over the datasets’ time span.

论文关键词：Recommender systems,Multimodal information,Preference dynamics,Collective matrix factorization

论文评审过程：Received 22 September 2016, Revised 4 January 2017, Accepted 4 January 2017, Available online 5 January 2017, Version of Record 9 January 2017.

论文官网地址：https://doi.org/10.1016/j.eswa.2017.01.005