LARGE: A leadership perception framework for group recommendation

被引:1
|
作者
Gan, Dingyi [1 ,2 ]
Gao, Min [1 ,2 ]
Li, Wentao [3 ]
Wang, Zongwei [1 ,2 ]
Guo, Linxin [1 ,2 ]
Jiang, Feng [2 ,4 ]
Song, Yuqi [5 ]
机构
[1] Chongqing Univ, Key Lab Dependable Serv Comp Cyber Phys Soc, Minist Educ, Chongqing 401331, Peoples R China
[2] Chongqing Univ, Sch Big Data & Software Engn, Chongqing 400044, Peoples R China
[3] Hong Kong Univ Sci & Technol Guangzhou, Data Sci & Analyt DSA, Guangzhou 511453, Peoples R China
[4] Chongqing Business Vocat Coll, Sch Finance & Management, Chongqing 400036, Peoples R China
[5] Univ Southern Maine, Portland, ME 04104 USA
基金
中国国家自然科学基金;
关键词
Group recommendation; Leadership group; Graph neural network; Attention mechanism; Representation learning;
D O I
10.1016/j.eswa.2024.125416
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Group recommendation systems are crucial in applications such as group travel or collective entertainment. Conventional approaches have achieved notable success by matching the aggregated preferences of all group members, under the assumption that the preferences of each member can influence group decisions. Challenging this paradigm, our paper introduces a transformative hypothesis centered on the concept of the leadership group, where the dominant preferences of a leader significantly influence group recommendations, potentially diminishing the contributions of other members. To bridge this innovative hypothesis with practical applications, our research unfolds in two main phases. First, we use real-world datasets to empirically investigate the presence and influence of leadership groups, providing compelling evidence to support our hypothesis. Following that, informed by these insights, we develop advanced methodologies for identifying leadership groups and integrate this concept into a novel recommendation framework. This framework is meticulously designed to capture the essence of group decision- making dynamics, therefore enhancing recommendation accuracy and user satisfaction. Its compatibility with various underlying models ensures broad applicability and potential for widespread adoption. Comprehensive experiments, benchmarked against state-of-the-art group recommendation systems, demonstrate that our innovative framework significantly improves accuracy, underscoring the importance of accounting for leadership dynamics in group recommendations.
引用
收藏
页数:10
相关论文
共 50 条
  • [21] A Fairness Group Recommendation Algorithm Based On User Activity
    Jia, Junjie
    Wang, Fen
    Wang, Huijuan
    Liu, Shilong
    INTERNATIONAL JOURNAL OF COMPUTATIONAL INTELLIGENCE SYSTEMS, 2024, 17 (01)
  • [22] A Design of Group Recommendation Mechanism Considering Opportunity Cost and Personal Activity Using Spark Framework
    Yoon, Byungho
    Park, Kiejin
    Kang, Suk-kyoon
    PROCEEDINGS OF THE 7TH INTERNATIONAL CONFERENCE ON EMERGING DATABASES: TECHNOLOGIES, APPLICATIONS, AND THEORY, 2018, 461 : 289 - 298
  • [23] Member-Augmented Group Recommendation With Multi-Interest Framework and Knowledge Graph Embeddings
    Lin, Sin-Jing
    Chen, Chiao-Ting
    Huang, Szu-Hao
    IEEE TRANSACTIONS ON COMPUTATIONAL SOCIAL SYSTEMS, 2024, 11 (03): : 3193 - 3206
  • [24] Social Group Recommendation With TrAdaBoost
    Huang, Zhenhua
    Ni, Juan
    Yao, Juanjuan
    Xu, Xin
    Zhang, Bo
    Chen, Yunwen
    Tan, Naiyu
    Xue, Chao
    IEEE TRANSACTIONS ON COMPUTATIONAL SOCIAL SYSTEMS, 2020, 7 (05) : 1278 - 1287
  • [25] Space efficiency in group recommendation
    Roy, Senjuti Basu
    Amer-Yahia, Sihem
    Chawla, Ashish
    Das, Gautam
    Yu, Cong
    VLDB JOURNAL, 2010, 19 (06): : 877 - 900
  • [26] Attention Network for Group Recommendation
    Chen, Qingwei
    Yang, Juan
    PROCEEDINGS OF 2020 IEEE 11TH INTERNATIONAL CONFERENCE ON SOFTWARE ENGINEERING AND SERVICE SCIENCE (ICSESS 2020), 2020, : 150 - 153
  • [27] Space efficiency in group recommendation
    Senjuti Basu Roy
    Sihem Amer-Yahia
    Ashish Chawla
    Gautam Das
    Cong Yu
    The VLDB Journal, 2010, 19 : 877 - 900
  • [28] Personalized Recommendation for Individual Users Based on the Group Recommendation Principles
    Kompan, Michal
    Bielikova, Maria
    STUDIES IN INFORMATICS AND CONTROL, 2013, 22 (03): : 331 - 342
  • [29] GRHAM: Towards Group Recommendation Using Hierarchical Attention Mechanism
    Lin, Nanzhou
    Zhang, Juntao
    Yang, Xiandi
    Song, Wei
    Peng, Zhiyong
    WEB AND BIG DATA, APWEB-WAIM 2021, PT II, 2021, 12859 : 295 - 309
  • [30] Socially-driven multi-interaction attentive group representation learning for group recommendation
    Wang, Peipei
    Li, Lin
    Wang, Ru
    Xu, Guandong
    Zhang, Jianwei
    PATTERN RECOGNITION LETTERS, 2021, 145 : 74 - 80