Journal of Computer Applications ›› 2021, Vol. 41 ›› Issue (2): 324-329.DOI: 10.11772/j.issn.1001-9081.2020050666

Special Issue: 人工智能

• Artificial intelligence • Previous Articles     Next Articles

Personalized social event recommendation method integrating user historical behaviors and social relationships

SUN Heli, XU Tong, HE Liang, JIA Xiaolin   

  1. Faculty of Electronic and Information Engineering, Xi'an Jiaotong University, Xi'an Shaanxi 710049, China
  • Received:2020-05-19 Revised:2020-07-20 Online:2021-02-10 Published:2020-09-15
  • Supported by:
    This work is partially supported by the National Natural Science Foundation of China (61672417).


孙鹤立, 徐统, 何亮, 贾晓琳   

  1. 西安交通大学 电子与信息学部, 西安 710049
  • 通讯作者: 贾晓琳
  • 作者简介:孙鹤立(1983-),女,辽宁铁岭人,副教授,博士,CCF会员,主要研究方向:数据挖掘、复杂网络分析;徐统(1994-),男,河南许昌人,硕士研究生,主要研究方向:社交网络、深度学习;何亮(1975-),男,陕西西安人,讲师,博士,CCF会员,主要研究方向:数据挖掘、机器学习;贾晓琳(1963-),女,陕西西安人,高级工程师,博士,CCF会员,主要研究方向:数据挖掘、机器学习。
  • 基金资助:

Abstract: In order to improve the recommendation effect of social events in Event-based Social Network (EBSN), a personalized social event recommendation method combining historical behaviors and social relationships of users was proposed. Firstly, deep learning technology was used to build a user model from two aspects:the user's historical behaviors and the potential social relationships between users. Then, when modeling user preferences, the negative vector representation of user preferences was introduced, and the attention weight layer was used to assign different weights to different events in the user's historical behaviors and different friends in the user's social relationships according to different candidate recommendation events, at the same time, the various characteristics of events and groups were considered. Finally, a lot of experiments were carried out on the real datasets. Experimental results show that this personalized social event recommendation method is better than the comparative Deep User Modeling framework for Event Recommendation (DUMER) and DIN (Deep Interest Network) model combined with attention mechanism in terms of Hits Ratio (HR), Normalized Discounted Cumulative Gain (NDCG) and Mean Reciprocal Rank (MRR) evaluation indicators.

Key words: Event-Based Social Network (EBSN), deep learning, personalized recommendation method, attention mechanism, user modeling

摘要: 为了提升基于事件的社交网络(EBSN)中社交事件的推荐效果,提出了融合用户历史行为和社交关系的个性化社交事件推荐方法。首先采用深度学习技术从用户的历史行为以及用户之间的潜在社交关系两个方面建立用户模型;然后在对用户偏好建模时,引入用户偏好的负向量表示,并使用注意力权重层根据不同的候选推荐事件为用户历史行为中不同的事件和用户社交关系中不同的好友分配不同的权重,同时考虑了事件以及群组的多种特征;最后在真实数据集上进行了大量实验。实验结果表明,该个性化社交事件推荐方法在命中率(HR)、归一化折损累计增益(NDCG)、平均倒数排名(MRR)评价指标上优于对比的深度用户社交事件推荐(DUMER)模型和融合注意力机制的深度兴趣网络(DIN)模型。

关键词: 基于事件的社交网络, 深度学习, 个性化推荐方法, 注意力机制, 用户建模

CLC Number: