图书情报工作

图书情报工作 >

2026 , Vol. 70 >Issue 3: 21 - 32

DOI: https://doi.org/10.13266/j.issn.0252-3116.2026.03.003

研究论文

搜索即学习过程中的学习状态识别及演化分析

  • 赵一鸣 ,
  • 房泽伟 ,
  • 蔡梦梁
展开
  • 1 武汉大学信息资源研究中心 武汉 430072;
    2 武汉大学信息管理学院 武汉 430072;
    3 武汉大学大数据研究院 武汉 430072;
    4 武汉数据智能研究院 武汉 430072;
    5 武汉大学图书情报国家级实验教学示范中心 武汉 430072
赵一鸣，教授，博士，博士生导师，E-mail: zhaoyiming@whu.edu.cn；房泽伟，硕士；蔡梦梁，硕士研究生。

收稿日期: 2024-12-13

  修回日期: 2025-02-18

  网络出版日期: 2026-02-09

基金资助

本文系国家自然科学基金面上项目“‘搜索即学习’视角下的用户学习状态感知与智能响应研究”（项目编号：72274146）和国家自然科学基金青年项目“人智交互情境下对话式信息搜索的用户认知加工与学习体验研究”（项目编号：72304177）研究成果之一。

收起

Identification and Evolutionary Analysis of Learning States in the “Searching as Learning”

  • Zhao Yiming ,
  • Fang Zewei ,
  • Cai Mengliang
Expand
  • 1 Center for Studies of Information Resources, Wuhan University, Wuhan 430072;
    2 School of Information Management, Wuhan University, Wuhan 430072;
    3 Big Data Institute, Wuhan University, Wuhan 430072;
    4 Wuhan Institute of Data Intelligence, Wuhan 430072;
    5 National Demonstration Center for Experimental Library and Information Science Education, Wuhan University, Wuhan 430072

Received date: 2024-12-13

  Revised date: 2025-02-18

  Online published: 2026-02-09

Supported by

This work is supported by the project of National Natural Science Foundation of China, titled “User Learning State Perception and Intelligent Response from the Perspective of ‘Search-as-Learning’” (Grant No. 72274146); and “Research on User’s Cognitive Processing and Learning Experience of Conversational Information Search in Human-AI Interaction Context” (Grant No. 72304177).

Fold

摘要

[目的/意义] 在搜索引擎发生跨越式发展的背景下，构建搜索过程中以用户为中心的学习状态感知模型，并探究其动态演化机制，以提升搜索系统对用户学习路径的优化能力。[方法/过程] 通过实验法获取用户搜索录屏数据及主观状态数据并编码分析，从内在认知和外显交互的双路径视角搭建学习状态识别体系框架，运用聚类和马尔可夫模型的组合方法挖掘学习状态时序模式。[结果/结论] 用户在搜索过程中存在探索式、评估式、颠覆式及爆发增长式4类学习状态模式，呈现出长期积累、快速增长的演化机制。生成式人工智能搜索引擎表现出更明显的颠覆与爆发增长状态，表明用户使用大语言模型的知识获取效率优于传统搜索引擎。

关键词： 学习状态; 状态识别; 状态演化; 搜索即学习

本文引用格式

赵一鸣 , 房泽伟 , 蔡梦梁 . 搜索即学习过程中的学习状态识别及演化分析[J]. 图书情报工作, 2026 , 70(3) : 21 -32 . DOI: 10.13266/j.issn.0252-3116.2026.03.003

Abstract

[Purpose/Significance] With the rapid advancement of AI-driven search engines, this study constructs a user-centered learning state model and explores its dynamic evolutionary mechanisms, contributing to the optimization of search recommendation strategies. [Method/Process] User experiments were conducted to collect subjective data and screen recordings, followed by data encoding and analysis. A dual-path framework for learning state recognition was developed from the perspectives of intrinsic cognition and explicit interaction. A combination of clustering and Markov models was employed to identify sequential patterns of learning states. [Result/Conclusion] Four types of learning state patterns are identified during the search process: exploratory, evaluative, disruptive, and explosive growth patterns, exhibiting long-term accumulation and rapid growth evolutionary mechanisms. Compared to traditional search engines, generative AI search engines demonstrate more pronounced disruptive and explosive growth states, suggesting that users achieve higher efficiency in knowledge acquisition.

Key words： learning state; state recognition; state evolution; searching as learning

参考文献

[1] CNNIC. 第54次中国互联网络发展状况统计报告[R]. 中国互联网络信息中心, 2024. (CNNIC. The report of the 54th China Internet development statistics[R]. Information Center of the China Internet Network, 2024.)
[2] 宋筱璇, 刘畅, 陈建龙. 搜索即学习主题的相关研究综述[J]. 图书情报工作, 2021, 65(10): 113-126. (SONG X X, LIU C, CHEN J L. A review of research from the perspective of searching as learning[J]. Library and information service, 2021, 65(10): 113-126.)
[3] 赵一鸣, 陈湛, 张帆. 探寻式搜索中用户满意度状态识别与演化规律研究[J]. 数据分析与知识发现, 2024, 8(1): 90-103. (ZHAO Y M, CHEN Z, ZHANG F. Identifying user satisfaction levels and evolution patterns in exploratory search[J]. Data analysis and knowledge discovery, 2024, 8(1): 90-103.)
[4] COLE M J, HENDAHEWA C, BELKIN N J, et al. User activity patterns during information search[J]. ACM transactions on information systems, 2015, 33(1): 1-39.
[5] VAKKARI P. A theory of the task-based information retrieval process: a summary and generalization of a longitudinal study[J]. Journal of documentation, 2001, 57(1): 44-60.
[6] LIU J Q, YU R. State-aware meta-evaluation of evaluation metrics in interactive information retrieval[C]// Proceedings of the 30th ACM international conference on information & knowledge management. New York: ACM, 2021: 3258-3262.
[7] CAPRA R, ARGUELLO J. Using trails to support users with tasks of varying scope[C]//Proceedings of the 42nd international ACM SIGIR conference on research and development in information retrieval. New York: ACM, 2019: 977-980.
[8] WITTROCK M C. Generative learning processes of the brain[J]. Educational psychologist, 1992, 27(4): 531-541.
[9] VAKKARI P. Searching as learning: a systematization based on literature[J]. Journal of information science, 2016, 42(1): 7-18.
[10] HASSAN A, GURRIN C, SANDERSON M, et al. Task intelligence workshop@ wsdm 2019[C]//Proceedings of the twelfth ACM international conference on Web search and data mining. New York: ACM, 2019: 848-849.
[11] 袁红, 李秋. 搜索任务和搜索能力对用户探索式搜索行为的影响研究[J]. 图书情报工作, 2015, 59(15): 94-105. (YUAN H, LI Q. Research on impact of search task and search ability on users’ exploratory search behaviors[J]. Library and information service, 2015, 59(15): 94-105.)
[12] NEWELL A, SIMON H A. Human problem solving[M]. Englewood Cliffs, NJ: Prentice-hall, 1972.
[13] BATES M J. The design of browsing and berry picking techniques for the online search interface[J]. Online review, 1989, 13(5): 407-424.
[14] KUHLTHAU C C. Inside the search process: information seeking from the user’s perspective[J]. Journal of the American Society for Information Science, 1991, 42(5): 361-371.
[15] VAKKARI P, PENNANEN M. Sources, relevance and contributory information of documents in writing a research proposal: a longitudinal case study[J]. The new review of information behavior research, 2001, 2(November): 217-232.
[16] VAKKARI P, HAKALA N. Changes in relevance criteria and problem stages in task performance[J]. Journal of documentation, 2000, 56(5): 540-562.
[17] CHI Y, HAN S, HE D, et al. Exploring knowledge learning in collaborative information seeking process[C]// Proceedings of SIGIR 2016 workshop: searching as learning. Italy: CEUR-WS, 2016.
[18] ROY N, MORAES F, HAUFF C. Exploring users’ learning gains within search sessions[C]//Proceedings of the 2020 conference on human information interaction and retrieval. New York: ACM, 2020: 432-436.
[19] ZHANG P, SOERGEL D. Process patterns and conceptual changes in knowledge representations during information seeking and sense making: a qualitative user study [J]. Journal of information science, 2016, 42(1): 59-78.
[20] KALYANI R, GADIRAJU U. Understanding user search behavior across varying cognitive levels[C]// Proceedings of the 30th ACM conference on hypertext and social media. New York: ACM, 2019: 123-132.
[21] LIU C, SONG X, LIU H, et al. Modelling knowledge change behaviors in learning-related tasks[C]//Proceedings of CIKM 2020 workshop:1st international workshop on investigating learning during web search. Ireland: CEUR-WS, 2020.
[22] 王佳. 任务驱动下社会化问答平台的用户信息搜寻行为研究[D]. 武汉: 华中师范大学, 2017. (WANG J. Research on user information seeking behavior driven by task in the social Q&A platform[D]. Wuhan: Central China Normal University, 2017.)
[23] 赵一鸣, 程宗, 陈忆金. 探寻式搜索路径与搜索意图转换路径的协同分析[J]. 情报资料工作, 2021, 42(6): 82-90. (ZHAO Y M, CHENG Z, CHEN Y J. Collaborative analysis of exploratory search path and search intention conversion path[J]. Information and documentation services, 2021, 42(6): 82-90.)
[24] LIU J Q, SARKAR S, SHAH C. Identifying and predicting the states of complex search tasks[C]//Proceedings of the 2020 conference on human information interaction and retrieval. New York: ACM, 2020: 193-202.
[25] LIU J Q, SHAH C. Leveraging user interaction signals and task state information in adaptively optimizing usefulness-oriented search sessions[C]//Proceedings of the 22nd ACM/IEEE joint conference on digital libraries. New York: ACM, 2022: 1-11.
[26] GAKKHAR S, MARCOLLI M. Syntactic structures and the general Markov models[J]. Mathematics in computer science, 2024, 18(1): 4.
[27] JOO S, XIE I. Exploring search tactic patterns in searching digital libraries[C]//The outreach of digital libraries: a globalized resource network. Berlin: Springer, 2012: 349-350.
[28] MARCHIONINI G. Exploratory search: from finding to understanding[J]. Communications of the ACM, 2006, 49(4): 41-46.
[29] 陈忆金, 赵一鸣, 林雨婷, 等. 不同搜寻方式下健康信息用户的学习结果差异研究[J]. 图书情报工作, 2023, 67(16): 88-98. (CHEN Y J, ZHAO Y M, LIN Y T, et al. Investigating on the differences in learning outcomes of health information users under different search methods[J]. Library and information service, 2023, 67(16): 88-98.)
[30] 陈忆金, 林雨婷. 探寻式搜索过程中的用户认知转换特征分析[J]. 图书情报工作, 2024, 68(22): 105-114. (CHEN Y J, LIN Y T. Analysis on characteristics of cognitive transitions in the process of exploratory search[J]. Library and information service, 2024, 68(22): 105-114.)
[31] 刘玮, 陈锦博. 搜索即学习视角下知识捕获与学习效果的影响因素研究——以健康信息学习型搜索为例[J]. 信息资源管理学报, 2023, 13(6): 133-143, 155. (LIU W, CHEN J B. Identifying the influential factors of knowledge capture and learning performance in learning-related search: a perspective of SAL[J]. Journal of information resources management, 2023, 13(6): 133-143, 155.)
[32] 姜雪, 李雨佳, 张元哲, 等. 先验知识差异对协同信息搜索和学习效果的影响研究[J]. 图书情报工作, 2022, 66(8): 32-41. (JIANG X, LI Y J, ZHANG Y Z, et al. Research on the effect of prior knowledge differences on collaborative information search and learning[J]. Library and information service, 2022, 66(8): 32-41.)
[33] 王馨悦, 刘畅. 时间限制与时间压力下的信息行为研究综述[J]. 图书情报工作, 2022, 66(9): 141-151. (WANG X Y, LIU C. A review of information behavior studies under time constraints and time pressure[J]. Library and information service, 2022, 66(9): 141-151.)
[34] RUMELHART D E, NORMAN D A. Accretion, tuning and restructuring: three modes of learning[M]. Center for human information processing. San Diego: University of California, 1976.
[35] JONASSEN D H. Computers as mindtools for schools: Engaging critical thinking[M]. Merrill. 2nd ed. NJ: Prentice Hall, 2000.
[36] 周涛, 李松洮, 邓胜利. 用户信息搜寻转移意向研究：从搜索引擎到生成式AI[J]. 图书情报工作, 2024, 68(3): 49-58. (ZHOU T, LI S T, DENG S L. Research on users’ switching intention of information seeking: from search engines to generative AI[J]. Library and information service, 2024, 68(3): 49-58.)
[37] CHEN Y J, ZHAO Y M, WANG Z Y. Understanding online health information consumers’ search as a learning process: search platform sequences, query reformulation and conceptual changes[J]. Library hi tech, 2020, 38(4): 859-881.
[38] ZHAO Y F, ZHOU Y H, OU M, et al. Maximizing cumulative user engagement in sequential recommendation: an online optimization perspective[C]//Proceedings of the 26th ACM SIGKDD international conference on knowledge discovery & data mining. New York: ACM, 2020: 2784-2792.
[39] MORRIS E. The design and evaluation of link: a computer‐based learning system for correlation[J]. British journal of educational technology, 2001, 32(1): 39-52.
[40] ZIAKIS C, VLACHOPOULOU M, KYRKOUDIS T, et al. Important factors for improving Google search rank[J]. Future Internet, 2019, 11(2): 32.
[41] 邱均平, 宓秦泽, 徐中阳, 等. 高校学术用户信息搜寻转移行为影响因素[J]. 图书馆论坛, 2024, 44(10): 121-130. (QIU J P, MI Q Z, XU Z Y, et al. Factors influencing the information seeking transfer behavior of academic users in colleges and universities[J]. Library tribune, 2024, 44(10): 121-130.)
[42] FITRIA T N. Artificial intelligence (AI) technology in OpenAI ChatGPT application: a review of ChatGPT in writing English essay[J]. ELT forum: journal of English language teaching, 2023, 12(1): 44-58.
[43] WHITE R W. Advancing the search frontier with AI agents[J]. Communications of the ACM, 2024, 67(9): 54-65.
Options
文章导航

/

〈 〉