钻研團隊經由過程万万级用户数据實證丈量社交電商平台的收集布局和动态（Cao et al. ICWSM 2020），發明社交電商在去中間化收集布局、约请级联、采辦同質性和用户虔诚度方面與傳统場景存在显著差别。借助用户間的口口相傳（Word-of-Mouth）機制，社交電商發展速率更快、用户粘性、虔诚度、复購率更高。
图3 社交電商约请级联，相對于傳统電商具备發展速率快的特色
钻研團隊連系深度定性钻研和大范围数据驱动的定量钻研阐發数字社交經濟場景下用户采辦念頭與用户體驗（Cao et al. CSCW 2021）和采辦举动（Xu et al. CSCW 2019）。钻研發明社交電商平台頂用户的采辦轉化率是傳统電商的3.09∼10.37倍，而且可以經由過程更好的樂趣匹配、社會影响、社交認同和代價敏感性機制来诠释（Xu et al. CSCW 2019）。
钻研團隊發明数字社交經濟可以或许给用户带来更可达、更低本錢、更泛在的購物體驗，經由過程引入個别間信赖、群體信赖認同、同質性、從眾性等機制影响决议计劃進程。區分于傳统電商上人們偏向于采辦品牌產物，社交電商上用户更偏向于測驗考試親朋举薦的较小眾、别致的商品；購物與社交的鸿沟也较以往模胡，在社交同時發生經濟举动（Cao et al. CSCW 2021）。
钻研團隊發明数字社交經濟樂成动員中國欠發財地域在傳统電商模式下被邊沿化的群體，将该群體認識的集市經濟轉換為线上情势（Chen et al. CHI 2022）。
图4 社交電商商品多样性與采辦轉化率的瓜葛：采辦商品更多样、轉化率更高
钻研團隊阐發在数字社交經濟生态情况中主體/中介（agent/intermediary，社交電商中介于平台與平凡用户中心毗連供需两頭、帮忙贩賣的脚色，如“社區團长”）的脚色特性，揭露主體的變化進程（Xu et al. ICWSM 2021）和主體在社交電商中阐扬的感化（Chen et al. CSCW 2020, Piao et al. CSCW 2021）。钻研團隊發明数字社交經濟中主體充任着局部趋向發明者（洞察老友們需求）和“线上杂貨铺”的感化，發掘了樂成主體所采纳的计谋模式（Chen et al. CSCW 2020），并發明将主體参加到举薦反馈回路中显著低落了举薦的同質性（Piao et al. CSCW 2021）。钻研團隊阐释了影响主體约请和轉化的機制，證明了社交趋同性、社會瓜葛影响、回绝防止和本錢-效益掂量等身分的首要影响感化（Xu et al. ICWSM 2021）。
图5 介于社交電商平台與平凡用户間的主體/中介（agent/intermediary）
钻研團隊進一步證明，操纵新型图神經收集對社交電商中繁杂的社交互动举动举行有用建模，可以實現正确的用户價值展望 (Piao et al. WWW 2021) 和社群價值展望 (Zhang et al. WWW 2021)，從而有用操纵用户社交信息展望經濟價值。同時钻研團隊發明，可以基于因果揣度的法子建模社交影响的因果性，防止“伪联系關系”，實現精准的社交電商用户流失展望（Zhang et al. WSDM 2022）。
在瓜葛感知的社會化举薦方面，钻研團隊操纵基于三元组的口口相傳布局结合建模用户樂趣和社交影响（Gao et al. TKDE2020a），設計特質化的社交正则法子，建模朋侪間的细粒度類似性（Gao et al. TKDE2020b），并構建基于社會瓜葛的注重力求卷积收集，有用建模社交電商异質信息收集中分歧種類的瓜葛（Xu et al. CIKM 2019）。
图6 社交電商异質信息收集
在跨平台举薦方面，钻研團隊同時斟酌社交瓜葛和跨平台特性，有用操纵分歧平台的用户-商品交互信息和社交媒體上的社交瓜葛信息，實現精准的跨平台举薦體系 (Lin et al. SIGIR 2019)。
图7 跨平台举薦算法
在團購举薦方面，钻研團隊設計用于刻劃繁杂團購举动的图卷积收集法子 (Zhang et al. ICDE 2021)增強免疫力水果,，構建有向异質图及基于多視图嵌入傳布的图卷积收集模块，表征用户面向拼團的采辦举动及社交瓜葛，提取图上高阶布局信息，并有用操纵團購失败記實晋升用户偏勤學習结果，實現精准拼團举薦。
[1] Hancheng Cao, Zhilong Chi88娛樂城,en, Mengjie Cheng, Shuling Zhao, Tao Wang, and Yong Li. 2020. You Reco妹妹end, I Buy: How and Why People Engage in Instant Messaging Based Social Co妹妹erce. In Proceedings of the ACM on Human-Computer Interaction 5, CSCW1 (2021). 1–25.
[2] Hancheng Cao, Zhilong Chen, Fengli Xu, Tao Wang, Yujian Xu, Lianglun Zhang, and Yong Li. 2020. When Your Friends Become Sellers: An Empirical Study of Social Co妹妹erce Site Beidian. In Proceedings of the International AAAI Conference on Web and Social Media, Vol. 14. 83–94.
[3] Zhilong Chen, Hancheng Cao, Xiaochong Lan, Zhicong Lu, and Yong Li. 2022. Beyond Virtual Bazaar: How Social Co妹妹erce Promotes Inclusivity for the Traditionally Underserved Co妹妹unity in Chinese Developing Regions. In Proceedings of the 2022 CHI Conference on Human Factors in Computing Systems. 1–15.
[4] Zhilong Chen, Hancheng Cao, Fengli Xu, Mengjie Cheng, Tao Wang, and Yong Li. 2020. Understanding the Role of Intermediaries in Online Social E-co妹妹erce: An Exploratory Study of Beidian. In Proceedings of the ACM on Human-Computer Interaction 4, CSCW2 (2020). 1–24. link
[5] Jinghua Piao, Guozhen Zhang, Fengli Xu, Zhilong Chen, and Yong Li. 2021. Bringing Friends into the Loop of Reco妹妹ender Systems: An Exploratory Study. In Proceedings of the ACM on Human-Computer Interaction 5, CSCW2 (2021). 1–26.
[6] Chen Gao, Chao Huang, Donghan Yu, Haohao Fu, Tzu-Heng Lin, Depeng Jin, and Yong Li. 2020. Item Reco妹妹endation for Word-of-Mouth Scenario in Social E-Co妹妹erce. IEEE Transactions on Knowledge and Data Engineering (2020).
[7] Chen Gao, Nian Li, Tzu-Heng Lin, Dongsheng Lin, Jun Zhang, Yong Li, and Depeng Jin. 2020. Social Reco妹妹endation with Characterized Regularization. IEEE Transactions on Knowledge and Data Engineering (2020).
[8] Tzu-Heng Lin, Chen Gao, and Yong Li. 2019. Cross: Cross-platform Reco妹妹endation for Social E-co妹妹erce. In Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval. 515–524.
[9] Jinghua Piao, Guozhen Zhang, Fengli Xu, Zhilong Chen, Yu Zheng, Chen Gao, and Yong Li. 2021. Bringing Friends into the Loop of Reco妹妹ender Systems: An Exploratory Study. In Proceedings of the Web Conference 2021. 3146–3157.
[10] Fengli Xu, Zhenyu Han, Jinghua Piao, and Yong Li. 2019. "I Think You'll Like It" Modelling the Online Purchase Behavior in Social E-Co妹妹erce. In Proceedings of the ACM on Human-Computer Interaction 3, CSCW (2019). 1–23.
[11] Fengli Xu, Jianxun Lian, Zhenyu Han, Yong Li, Yujian Xu, and Xing Xie. 2019. Relation-Aware Graph Convolutional Networks for Agent-Initiated Social E-Co妹妹erce Reco妹妹endation. In Proceedings of the 28th ACM International Conference on Information and Knowledge Management. 529–538.
[12] Fengli Xu, Guozhen Zhang, Yuan Yuan, Hongjia Huang, Diyi Yang, Depeng Jin, and Yong Li. 2021. Understanding the Invitation Acceptance in Agent-Initiated Social E-Co妹妹erce. In Proceedings of the International AAAI Conference on Web and Social Media, Vol. 15. 820–829.
[13] Guozhen Zhang, Yong Li, Yuan Yuan, Fengli Xu, Hancheng Cao, Yujian Xu, and Depeng Jin. 2021. Co妹妹unity Value Prediction in Social E-Co妹妹erce. In Proceedings of the Web Conference 2021. 2958–2967.
[14] Guozhen Zhang, Jinwei Zeng, Zhengyue Zhao, Depeng Jin, and Yong Li. 2022. A Counterfac改善便秘,tual Modeling Framework for Churn Prediction. In Proceedings of the Fifteenth ACM International Conference on Web Search and Data Mining. 1424–1432.
[15] Jun Zhang, Chen Gao, Depeng Jin, and Yong Li. 2021. Group-Buying Reco妹妹endation for Social E-Co妹妹erce. In 2021 IEEE 37th International Conference on Data Engineering (ICDE). 1536-1547.