面向学术信息推荐的用户信任可解释模型构建

doi:10.3772/j.issn.1000-0135.2025.09.009

情报学报

2025, Vol. 44

Issue (9): 1192-1203 DOI: 10.3772/j.issn.1000-0135.2025.09.009

情报用户与行为

本期目录 | 过刊浏览 | 高级检索

面向学术信息推荐的用户信任可解释模型构建

陈韵怡¹, 吴丹^1,2, 夏子硕¹

1.武汉大学信息管理学院，武汉 430072
2.武汉大学人机交互与用户行为研究中心，武汉 430072

Construction of User-Trusted Explainable Models for Academic Information Recommendation

Chen Yunyi¹, Wu Dan^1,2, Xia Zishuo¹

1.School of Information Management, Wuhan University, Wuhan 430072
2.Center for Studies of Human-Computer Interaction and User Behavior, Wuhan University, Wuhan 430072

摘要
图/表
参考文献
相关文章 (1)

全文: PDF (1461 KB) HTML (1 KB)
输出: BibTeX | EndNote (RIS)

摘要随着人工智能先进程度的提高，无法解释的“黑匣”正在阻碍人们对系统的理解和信任，限制了人与人工智能的合作关系。本文以提升人工智能的可解释性为核心，面向学术信息智能推荐这一应用场景，提出并验证了分阶段的、以问题为导向的、面向学术信息推荐的用户信任可解释模型。该模型从人机交互的过程出发，将交互全流程划分为初次接触、开始交互、深入协作三阶段，规定了各阶段应对哪些问题进行解释，以实现提升用户信任、促进人机交互的效果。然后，验证了该模型的有效性与合理性，并基于扎根理论对访谈内容进行开放式编码、主轴式编码、选择性编码三级编码，采用编码结果对模型进行阐释与完善，提出可解释实践优化策略。本文提出的分阶段、问题导向的可解释模型能够多层面提升用户信任，其解释内容、呈现形式、语言风格与用户的系统认知、使用意愿和使用行为之间存在映射关系。基于此，本文针对各阶段解释问题，从解释内容和呈现形式两个方面提出各交互阶段的具体指导策略，以期为可解释人工智能的构建提供助力。

	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
	陈韵怡
	吴丹
	夏子硕

关键词 ：可解释人工智能, 用户信任, 学术信息推荐, 人机交互

收稿日期: 2024-12-12

基金资助:国家自然科学基金重大研究计划培育项目“人机交互视角下数据与知识双驱动的可解释智能决策方法研究”（92370112）；2023年度湖北省自然科学基金创新群体项目“以人为本的人工智能创新应用”（2023AFA012）。

作者简介: 陈韵怡，女，2002年生，硕士研究生，主要研究方向为人机交互与用户信息行为；吴丹，女，1978年生，通信作者，博士，教授，博士生导师，主要研究方向为人机交互与用户信息行为，E-mail：woodan@whu.edu.cn；夏子硕，男，1999年生，博士研究生，主要研究方向为人机交互与虚拟现实；

引用本文:

陈韵怡, 吴丹, 夏子硕. 面向学术信息推荐的用户信任可解释模型构建[J]. 情报学报, 2025, 44(9): 1192-1203.
Chen Yunyi, Wu Dan, Xia Zishuo. Construction of User-Trusted Explainable Models for Academic Information Recommendation. 情报学报, 2025, 44(9): 1192-1203.

链接本文:

https://qbxb.istic.ac.cn/CN/10.3772/j.issn.1000-0135.2025.09.009 或 https://qbxb.istic.ac.cn/CN/Y2025/V44/I9/1192

1 IBM. 什么是可解释AI?[EB/OL]. [2024-04-29]. https://www.ibm.com/cn-zh/topics/explainable-ai.
2 Gunning D. DARPA’s explainable artificial intelligence (XAI) program[C]// Proceedings of the 24th International Conference on Intelligent User Interfaces. New York: ACM Press, 2019: ii.
3 发展负责任的人工智能: 新一代人工智能治理原则发布[EB/OL]. (2019-06-17) [2023-04-29]. https://www.most.gov.cn/kjbgz/201906/t20190617_147107.html.
4 吴丹, 孙国烨. 迈向可解释的交互式人工智能: 动因、途径及研究趋势[J]. 武汉大学学报(哲学社会科学版), 2021, 74(5): 16-28.
5 Harper R H R. The role of HCI in the age of AI[J]. International Journal of Human–Computer Interaction, 2019, 35(15): 1331-1344.
6 熊回香, 唐明月, 叶佳鑫, 等. 融合加权异质网络与网络表示学习的学术信息推荐研究[J]. 现代情报, 2023, 43(5): 23-34.
7 Liu H F, Jing L P, Wen J X, et al. Interpretable deep generative recommendation models[J]. Journal of Machine Learning Research, 2021, 22(1): Article No.202.
8 Wang W J, Lin X Y, Feng F L, et al. Generative recommendation: towards next-generation recommender paradigm[OL]. (2024-02-25). https://arxiv.org/pdf/2304.03516.
9 Durán J M. Dissecting scientific explanation in AI (sXAI): a case for medicine and healthcare[J]. Artificial Intelligence, 2021, 297: 103498.
10 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.
11 靳庆文, 朝乐门, 孟刚. AI治理中的算法解释及其实现方法研究[J]. 情报资料工作, 2022, 43(5): 16-23.
12 Belle V, Papantonis I. Principles and practice of explainable machine learning[J]. Frontiers in Big Data, 2021, 4: 688969.
13 王冬丽, 杨珊, 欧阳万里, 等. 人工智能可解释性: 发展与应用[J]. 计算机科学, 2023, 50(S1): 19-25.
14 孟韬, 陈梦圆, 张天锴, 等. 交互失误情境下交互式人工智能拟人化的负面影响——基于ChatGPT和搜索引擎的实验证据[J]. 情报理论与实践, 2024, 47(1): 84-91.
15 Weisberg D S, Landrum A R, Hamilton J, et al. Knowledge about the nature of science increases public acceptance of science regardless of identity factors[J]. Public Understanding of Science, 2021, 30(2): 120-138.
16 张乐, 李森林. 知识、理解与信任: 个体对人工智能的信任机制[J]. 社会学评论, 2023, 11(3): 59-83.
17 Schr?der A M, GhajargarM. Unboxing the algorithm: designing an understandable algorithmic experience in music recommender systems[C]// Proceedings of the Perspectives on the Evaluation of Recommender Systems Workshop 2021. Aachen: CEUR-WS Team, 2021: Paper 12.
18 Nunes I, Jannach D. A systematic review and taxonomy of explanations in decision support and recommender systems[J]. User Modeling and User-Adapted Interaction, 2017, 27: 393-444.
19 Amershi S, Weld D, Vorvoreanu M, et al. Guidelines for human-AI interaction[C]// Proceedings of the 2019 CHI Conference on Human Factors in Computing Systems. New York: ACM Press, 2019: Paper No.3.
20 IBM. IBM design for AI: explainability[EB/OL]. [2024-05-03]. https://www.ibm.com/design/ai/ethics/explainability.
21 Google. Google AI: responsible AI practices[EB/OL]. [2024-05-03]. https://ai.google/responsibilities/responsible-ai-practices/category=interpretability.
22 Dhanorkar S, Wolf C T, Qian K, et al. Who needs to know what, when?: Broadening the explainable AI (XAI) design space by looking at explanations across the AI lifecycle[C]// Proceedings of the 2021 ACM Designing Interactive Systems Conference. New York: ACM Press, 2021: 1591-1602.
23 Cabour G, Morales-Forero A, Ledoux é, et al. An explanation space to align user studies with the technical development of Explainable AI[J]. AI & Society, 2023, 38(2): 869-887.
24 Wang D D, Yang Q, Abdul A, et al. Designing theory-driven user-centric explainable AI[C]// Proceedings of the 2019 CHI Conference on Human Factors in Computing Systems. New York: ACM Press, 2019: Paper No.601.
25 Endsley M R. Level of automation forms a key aspect of autonomy design[J]. Journal of Cognitive Engineering and Decision Making, 2018, 12(1): 29-34.
26 Jin W N, Fan J Y, Gromala D, et al. EUCA: the end-user-centered explainable AI framework[OL]. (2022-03-01). https://arxiv.org/pdf/2102.02437.
27 Liao Q V, Gruen D, Miller S. Questioning the AI: informing design practices for explainable AI user experiences[C]// Proceedings of the 2020 CHI Conference on Human Factors in Computing Systems. New York: ACM Press, 2020: 1-15.
28 Liao Q V, Pribi? M, Han J, et al. Question-driven design process for explainable AI user experiences[OL]. (2021-09-03). https://arxiv.org/pdf/2104.03483.
29 Schneider J, Handali J. Personalized explanation in machine learning: a conceptualization[C]// Proceedings of the 27th European Conference on Information Systems. Cham: Springer, 2019: 1-17.
30 Wolf C T. Explainability scenarios: towards scenario-based XAI design[C]// Proceedings of the 24th International Conference on Intelligent User Interfaces. New York: ACM Press, 2019: 252-257.
31 李韬奋, 杨水利, 祝明伟. 体验型产品个性化推荐的结构维度实证研究——以图书产品为例[J]. 软科学, 2021, 35(6): 139-144.
32 ?man P, Liikkanen L A. Interacting with context factors in music recommendation and discovery[J]. International Journal of Human–Computer Interaction, 2017, 33(3): 165-179.
33 Jahanbakhsh F, Awadallah A H, Dumais S T, et al. Effects of past interactions on user experience with recommended documents[C]// Proceedings of the 2020 Conference on Human Information Interaction and Retrieval. New York: ACM Press, 2020: 153-162.
34 Kunkel J, Donkers T, Michael L, et al. Let me explain: impact of personal and impersonal explanations on trust in recommender systems[C]// Proceedings of the 2019 CHI Conference on Human Factors in Computing Systems. New York: ACM Press, 2019: Paper No.487.
35 Barbu C M, Carbonell G, Ziegler J. The influence of trust cues on the trustworthiness of online reviews for recommendations[C]// Proceedings of the 34th ACM/SIGAPP Symposium on Applied Computing. New York: ACM Press, 2019: 1687-1689.
36 李贺, 侯力铁, 祝琳琳. 移动图书馆情景感知信息推荐服务用户接受行为研究[J]. 图书情报工作, 2019, 63(12): 94-104.
37 Yang X. Influence of informational factors on purchase intention in social recommender systems[J]. Online Information Review, 2020, 44(2): 417-431.
38 王伟军, 王阳, 王玉珠, 等. 移动商务用户个性化推荐采纳行为影响因素的实证研究[J]. 系统管理学报, 2017, 26(5): 816-823.
39 吴继飞, 于洪彦, 朱翊敏, 等. 人工智能推荐对消费者采纳意愿的影响[J]. 管理科学, 2020, 33(5): 29-43.
40 陈炳霖, 薛可, 余明阳. 人工智能推荐产品类型对消费者采纳意愿的影响机理研究——基于算法透明度的调节作用[J]. 江西社会科学, 2023, 43(1): 194-205, 208.
41 曹树金, 王雅琪. 图书馆微信公众号图书阅读推广文章采纳行为影响因素[J]. 图书馆论坛, 2021, 41(1): 99-110.
42 于微微, 王心妍, 相静. 个性化推荐系统用户接受意愿和采纳行为影响因素研究[J]. 图书情报导刊, 2018, 3(4): 74-79.
43 梅潇, 查先进, 严亚兰. 智能推荐环境下移动社交媒体用户隐私风险感知影响机理研究[J]. 情报理论与实践, 2024, 47(1): 57-64.
44 王雪, 查先进, 梅潇, 等. 隐私担心视角下移动社交媒体智能推荐用户信息规避行为研究[J]. 情报学报, 2023, 42(5): 598-610.
45 占南, 闫香玉. 电商智能推荐用户信息隐私披露意愿影响机制研究[J]. 现代情报, 2023, 43(10): 35-53.
46 Hoffman R R, Mueller S T, Klein G, et al. Metrics for explainable AI: challenges and prospects[J]. (2019-02-01). https://arxiv.org/pdf/1812.04608.
47 Cramer H, Evers V, Ramlal S, et al. The effects of transparency on trust in and acceptance of a content-based art recommender[J]. User Modeling and User-Adapted Interaction, 2008, 18(5): 455-496.
48 吴世友. 如何运用ATLAS.ti分析定性数据和发掘研究主题[J]. 社会工作, 2017(6): 23-40, 111.