基于生成式人工智能的事后解释型推荐模型研究

doi:10.3772/j.issn.1000-0135.2025.09.004

情报学报

2025, Vol. 44

Issue (9): 1114-1127 DOI: 10.3772/j.issn.1000-0135.2025.09.004

情报理论与方法

本期目录 | 过刊浏览 | 高级检索

基于生成式人工智能的事后解释型推荐模型研究

李伟卿^1,4, 王伟军², 黄英辉³, 黄炜¹, 张瑞¹

1.湖北工业大学经济与管理学院，武汉 430068
2.华中师范大学青少年网络心理与行为教育部重点实验室，武汉 430079
3.武汉理工大学管理学院，武汉 430070
4.湖北数字工业经济发展研究中心，武汉 430068

Research on the Post-hoc Explanation Recommendation Model Based on Generative AI

Li Weiqing^1,4, Wang Weijun², Huang Yinghui³, Huang Wei¹, Zhang Rui¹

1.School of Economics and Management, Hubei University of Technology, Wuhan 430068
2.Key Laboratory of Adolescent Cyberpsychology and Behavior (Central China Normal University), Ministry of Education, Wuhan 430079
3.School of Management, Wuhan University of Technology, Wuhan 430070
4.Hubei Research Center for Digital Industrial Economy Development, Wuhan 430068

摘要
图/表
参考文献
相关文章 (4)

全文: PDF (2322 KB) HTML (1 KB)
输出: BibTeX | EndNote (RIS)

摘要本文提出一种基于生成式人工智能（generative artificial intelligence，GenAI）的事后解释型推荐模型，并将消费价值观理论应用于推荐系统中，在提升推荐效果的同时，为用户生成个性化的文字解释。首先，采用GenAI提示工程方法，评估商品评论中体现的细粒度消费价值观倾向，包括功能性价值、象征性价值、经济性价值和情感性价值。其次，以此构建用户-项目（价值观）-偏好的交互矩阵，并实现基于用户价值观的推荐模型。最后，将推荐结果及相关用户和项目的消费价值观倾向得分输入基于GenAI的解释机器人中，生成推荐解释。研究结果表明，基于GenAI的打分机器人在准确率、一致性和差异性方面表现良好，可有效评估消费价值观倾向，为推荐模型和解释系统提供重要支持。本文提出的推荐模型通过融合消费价值观显著提升了推荐结果的准确率和多样性，并在冷启动和数据稀疏性场景下表现优异，为解决推荐系统的“信息茧房”和过度特化问题提供了思路。此外，基于GenAI的解释机器人生成的推荐解释语句流畅且多样化，能够有效揭示推荐机制与价值观倾向，相较于传统方法，其更为灵活、高效且个性化，为提升推荐系统的透明性和用户信任度提供了新路径。

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	李伟卿
	王伟军
	黄英辉
	黄炜
	张瑞

关键词 ：可解释推荐, 消费价值观, 事后解释, 生成式人工智能, GPT

收稿日期: 2025-01-14

基金资助:国家自然科学基金项目“面向大学生价值观引导的智能算法分发信息服务方法与机制研究”（72304090），“面向青少年网络社会心态引导的多目标信息推荐方法研究”（72204095），“面向青少年网络适应的个性化信息服务优化方法研究”（71974072）。

作者简介: 李伟卿，男，1989年生，博士，讲师，主要研究领域为可解释人工智能及个性化推荐；王伟军，男，1965年生，博士，教授，博士生导师，主要研究领域为网络心理与行为、个性化信息服务；黄英辉，通信作者，男，1993年生，博士，副教授，硕士生导师，主要研究领域为网络用户行为与个性化推荐，E-mail：yhhuang@ccnu.edu.cn；黄炜，男，1979年生，博士，教授，博士生导师，主要研究领域为大数据管理与应用；张瑞，女，1992年生，博士，讲师，主要研究领域为知识计量与信息管理；

引用本文:

李伟卿, 王伟军, 黄英辉, 黄炜, 张瑞. 基于生成式人工智能的事后解释型推荐模型研究[J]. 情报学报, 2025, 44(9): 1114-1127.
Li Weiqing, Wang Weijun, Huang Yinghui, Huang Wei, Zhang Rui. Research on the Post-hoc Explanation Recommendation Model Based on Generative AI. 情报学报, 2025, 44(9): 1114-1127.

链接本文:

https://qbxb.istic.ac.cn/CN/10.3772/j.issn.1000-0135.2025.09.004 或 https://qbxb.istic.ac.cn/CN/Y2025/V44/I9/1114

1 Zhou X F, Zhou Y S, Gong Y F, et al. “Bee and I need diversity!” Break filter bubbles in recommendation systems through embodied AI learning[C]// Proceedings of the 23rd Annual ACM Interaction Design and Children Conference. New York: ACM Press, 2024: 44-61.
2 姜婷婷, 许艳闰. 国外过滤气泡研究: 基础、脉络与展望[J]. 情报学报, 2021, 40(10): 1108-1117.
3 Zhang Y F, Chen X. Explainable recommendation: a survey and new perspectives[J]. Foundations and Trends? in Information Retrieval, 2020, 14(1): 1-101.
4 高广尚. 可解释推荐模型中的可解释性方法研究综述[J]. 数据分析与知识发现, 2024, 8(8/9): 6-19.
5 Tintarev N. Explanations of recommendations[C]// Proceedings of the 2007 ACM Conference on Recommender Systems. New York: ACM Press, 2007: 203-206.
6 Turbé H, Bjelogrlic M, Lovis C, et al. Evaluation of post-hoc interpretability methods in time-series classification[J]. Nature Machine Intelligence, 2023, 5(3): 250-260.
7 Chakraborty D, Paul J. Healthcare apps’ purchase intention: a consumption values perspective[J]. Technovation, 2023, 120: 102481.
8 杨珂欣, 张奇, 余乐安, 等. 基于消费者价值观和有限理性的新能源汽车购买意愿与助推政策研究[J]. 管理评论, 2023, 35(1): 146-158.
9 Chang Y P, Wang X, Wang J D, et al. A survey on evaluation of large language models[J]. ACM Transactions on Intelligent Systems and Technology, 2024, 15(3): Article No.39.
10 罗震, 张涛. 融合用户特征与知识图谱的可解释电影推荐方法[J]. 管理工程学报, 2024, 38(6): 128-139.
11 Chatti M A, Guesmi M, Muslim A. Visualization for recommendation explainability: a survey and new perspectives[J]. ACM Transactions on Interactive Intelligent Systems, 2024, 14(3): Article No.19.
12 李伟卿, 王伟军, 黄炜, 等. 可解释信息推荐研究综述[J]. 情报学报, 2023, 42(7): 870-882.
13 Retzlaff C O, Angerschmid A, Saranti A, et al. Post-hoc vs ante-hoc explanations: xAI design guidelines for data scientists[J]. Cognitive Systems Research, 2024, 86: 101243.
14 Guidotti R, Monreale A, Ruggieri S, et al. A survey of methods for explaining black box models[J]. ACM Computing Surveys, 2019, 51(5): Article No.93.
15 Rehman Zafar M, Khan N M. DLIME: a deterministic local interpretable model-agnostic explanations approach for computer-aided diagnosis systems[OL]. (2019-06-24). https://arxiv.org/pdf/1906.10263.
16 Brunot L, Canovas N, Chanson A, et al. Preference-based and local post-hoc explanations for recommender systems[J]. Information Systems, 2022, 108: 102021.
17 Zhong J F, Negre E. Shap-enhanced counterfactual explanations for recommendations[C]// Proceedings of the 37th ACM/SIGAPP Symposium on Applied Computing. New York: ACM Press, 2022: 1365-1372.
18 Le N L, Abel M H, Gouspillou P. Combining embedding-based and semantic-based models for post-hoc explanations in recommender systems[C]// Proceedings of the 2023 IEEE International Conference on Systems, Man, and Cybernetics. Piscataway: IEEE, 2023: 4619-4624.
19 Wang X T, Chen Y R, Yang J, et al. A reinforcement learning framework for explainable recommendation[C]// Proceedings of the 2018 IEEE International Conference on Data Mining. Piscataway: IEEE, 2018: 587-596.
20 Wang X M, Li Q, Yu D E, et al. Reinforced path reasoning for counterfactual explainable recommendation[J]. IEEE Transactions on Knowledge and Data Engineering, 2024, 36(7): 3443-3459.
21 Amin S, Tarun M T. Effect of consumption values on customers’ green purchase intention: a mediating role of green trust[J]. Social Responsibility Journal, 2021, 17(8): 1320-1336.
22 Gutman J. A means-end chain model based on consumer categorization processes[J]. Journal of Marketing, 1982, 46(2): 60-72.
23 董雅丽, 杜振涛, 李治国. 消费价值观对消费行为影响的实证研究[J]. 调研世界, 2011(10): 47-50.
24 Adeola O, Moradeyo A A, Muogboh O, et al. Consumer values, online purchase behaviour and the fashion industry: an emerging market context[J]. PSU Research Review, 2024, 8(1): 68-83.
25 Alavi M, Leidner D E, Mousavi R. Knowledge management perspective of generative artificial intelligence[J]. Journal of the Association for Information Systems, 2024, 25(1): 1-12.
26 Zhao W X, Zhou K, Li J Y, et al. A survey of large language models[OL]. (2025-03-11). https://arxiv.org/pdf/2303.18223.
27 Demszky D, Yang D Y, Yeager D S, et al. Using large language models in psychology[J]. Nature Reviews Psychology, 2023, 2(11): 688-701.
28 Rathje S, Mirea D M, Sucholutsky I, et al. GPT is an effective tool for multilingual psychological text analysis[J]. Proceedings of the National Academy of Sciences of the United States of America, 2024, 121(34): e2308950121.
29 Biró A, Cuesta-Vargas A I, Szilágyi L. Precognition of mental health and neurogenerative disorders using AI-parsed text and sentiment analysis[J]. Acta Universitatis Sapientiae, Informatica, 2023, 15(2): 359-403.
30 Chen B Y, Wu Z X, Zhao R R. From fiction to fact: the growing role of generative AI in business and finance[J]. Journal of Chinese Economic and Business Studies, 2023, 21(4): 471-496.
31 Zhang Q, Wang Y L, Ariffin S K.Consumers purchase intention in live-streaming e-commerce:a consumption value perspective and the role of streamer popularity[J]. PLoS One, 2024, 19(2):e0296339.
32 Joshi Y, Uniyal D P, Sangroya D. Investigating consumers’ green purchase intention: examining the role of economic value, emotional value and perceived marketplace influence[J]. Journal of Cleaner Production, 2021, 328: 129638.
33 Tandon A, Kaur P, Bhatt Y, et al. Why do people purchase from food delivery apps? A consumer value perspective[J]. Journal of Retailing and Consumer Services, 2021, 63: 102667.
34 Zhang N, Liu R, Zhang X Y, et al. The impact of consumer perceived value on repeat purchase intention based on online reviews: by the method of text mining[J]. Data Science and Management, 2021, 3: 22-32.
35 Stray J, Halevy A, Assar P, et al. Building human values into recommender systems: an interdisciplinary synthesis[J]. ACM Transactions on Recommender Systems, 2024, 2(3): Article No.20.
36 Zhao Y Y, Wang Y, Liu Y C, et al. Fairness and diversity in recommender systems: a survey[J]. ACM Transactions on Intelligent Systems and Technology, 2025, 16(1): Article No.2.
37 李伟卿, 池毛毛, 王伟军. 面向用户长短期偏好调节的可解释个性化推荐方法研究[J]. 图书情报工作, 2021, 65(12): 101-111.
38 Jin B B, Lian D F, Liu Z, et al. Sampling-decomposable generative adversarial recommender[C]// Proceedings of the 34th Conference on Neural Information Processing Systems. Cham: Springer, 2020: 22629-22639.
39 Li J H, Li J H, Wang C J, et al. Wide & deep generative adversarial networks for recommendation system[J]. Intelligent Data Analysis, 2023, 27(1): 121-136.
40 Wu L K, Zheng Z, Qiu Z P, et al. A survey on large language models for recommendation[J]. World Wide Web, 2024, 27(5): Article No.60.
41 Deldjoo Y, He Z K, McAuley J, et al. Recommendation with generative models[OL]. (2024-09-18). https://arxiv.org/pdf/2409.15173.
42 Zhong W L, Jin R, Yang C, et al. Stock constrained recommendation in tmall[C]// Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York: ACM Press, 2015: 2287-2296.