•  
  •  
 

Journal of Scientific Information Research

Keywords

ancient book large language models, dropout behavior, psychological resilience, large language model users, technical resilience

Abstract

[Purpose/significance]The deep integration of ancient book digitization and large language models is the future development trend. In order to clarify the influence factors and formation mechanisms of dropout behavior among users of domain ancient book large language models, mobilize the willingness of users to use large language models, achieve high-quality user retention, and promote the non-human high-quality development of domain large language models. [Method/process]This study takes users in the field of ancient books as an example, based on resilience theory, and draws on grounded theory research methods to code and deconstruct first-hand data obtained from in-depth interviews with 30 users of ancient book large language models. The focus is on extracting influencing factors and conceptual categories from the perspective of resilience theory, and then constructing a research model on the mechanism of dropout behavior formation among users of ancient book large language models from the perspective of resilience theory. [Result/conclusion]The research results show that resilience factors, psychological resilience, cognitive factors, and situational factors are important factors affecting the dropout behavior of users of the ancient book large language model.Resilience factors include three dimensions:information resilience, technological resilience, and environmental resilience. Psychological resilience mainly goes through three stages: emotional stress, emotional resilience, and cognitive resilience.The research results provide necessary reference for effectively preventing users of ancient language models from dropout and achieving high-quality user retention.

First Page

48

Last Page

57

Submission Date

06-Jul-2024

Revision Date

18-Oct-2024

Acceptance Date

13-Nov-2024

Published Date

01-Apr-2025

Reference

[1] ZHAO W X, ZHOU K, LI J, et al. A survey of large language models[J]. arXiv preprint arXiv: 2303. 18223, 2023.
[2] 谢靖, 张海, 王东波. 信息资源管理学科融合新质生产力: 构成要素、研究体系及推进路径[J]. 图书馆工作与研究, 2024 (04): 5-12, 60.
[3] 段荟, 张海, 孔晔晗. AIGC应用平台用户持续使用行为影响因素研究[J]. 图书馆工作与研究, 2024 (06): 21-31.
[4] 张海, 赵雪, 王东波. 大语言模型下古籍智能信息处理: 构成要素、框架体系与实践路径研究[J]. 信息资源管理学报, 2024, 14 (05): 36-44.
[5] ONG J C, KUO T F, MANBER R. Who is at risk for dropout from group cognitive-behavior therapy for insomnia?[J]. Journal of Psychosomatic Research, 2008, 64 (04): 419-425.
[6] TUREL O. Untangling the complex role of guilt in rational decisions to discontinue the use of a hedonic Information System[J]. European Journal of Information Systems, 2016, 25 (05): 432-447.
[7] 张敏, 孟蝶, 张艳. 社交网络用户间歇性中辍行为关键问题研究综述[J]. 图书情报工作, 2019, 63 (21): 128-136.
[8] 刘鲁川, 李旭, 张冰倩. 基于扎根理论的社交媒体用户倦怠与消极使用研究[J]. 情报理论与实践, 2017, 40 (12): 100-106, 51.
[9] 张敏, 孟蝶, 张艳. 逃离还是回归?: 用户社交网络间歇性中辍行为实证研究的影响因素综述[J]. 图书馆论坛, 2019, 39 (06): 43-52.
[10] 姚丽琴, 张海. AIGC用户中辍行为影响因素模型构建与实证研究[J]. 农业图书情报学报, 2024, 36 (05): 79-92.
[11] LEE A R, SON S M, KIM K K. Information and communication technology overload and social networking service fatigue: A stress perspective[J]. Computers in Human Behavior, 2016, 55 (FEB): 51-61.
[12] KLEIN R. Resilience to natural hazards: How useful is this concept[J]. Global Environmental Change Part B Environmental Hazards, 2003, 5 (01-02): 35-45.
[13] HOLLING C S. Resilience and stability of ecological systems[J]. Annual Review of Ecology and Systematics, 1973, 4 (01): 1-23.
[14] 张秀娥, 杨柳. 组织韧性对中小企业成长的影响: 基于双元学习和组织惯例更新的链式中介作用[J]. 武汉大学学报 (哲学社会科学版), 2024, 77 (05): 111-122.
[15] 李姗姗. 创业失败学习、创业韧性与企业双元创新的关系研究[D]. 长春: 吉林大学, 2024.
[16] 栾宇, 张海涛, 李依霖, 等. 基于韧性理论的突发事件情报决策体系研究[J]. 情报理论与实践, 2024, 47 (03): 95-103.
[17] 包鑫, 柯平. 图书馆赋能社区韧性: 国外经验与启示[J]. 图书馆论坛, 2023, 43 (11): 120-129.
[18] CICCHETTI D. Resilience in development: Progress and transformation[J]. Developmental Psychopathology, 2016, 4 (03): 271-333.

Digital Object Identifier (DOI)

10.19809/j.cnki.kjqbyj.2025.02.005

Share

COinS