A Study on the Causal Evolutionary Logic of Social Media Burnout Behaviors

Zhao Youlin; Liu Zhuochen; Wang Jiajie; Feng Li; Shi Yanqing

doi:10.13266/j.issn.0252-3116.2025.18.011

Library and Information Service >

2025 , Vol. 69 >Issue 18: 131 - 146

DOI: https://doi.org/10.13266/j.issn.0252-3116.2025.18.011

RESEARCH PAPERS

A Study on the Causal Evolutionary Logic of Social Media Burnout Behaviors

Zhao Youlin ,
Liu Zhuochen ,
Wang Jiajie ,
Feng Li ,
Shi Yanqing

Expand

1 School of Business, Hohai University, Nanjing 211100;
2 School of Information Management, Nanjing University, Nanjing 210023;
3 Library of Hohai University, Nanjing 211100;
4 School of Information Management, Nanjing Agricultural University, Nanjing 210095

Zhao Youlin, Associate Professor, PhD, Doctoral Supervisor, E-mail: sobzyl@hhu.edu.cn; Liu Zhuochen, Master’s Candidate; Wang Jiajie, Doctoral Candidate; Feng Li, Librarian, Master’s Degree; Shi Yanqing, Associate Professor, PhD, Master’s Supervisor.

Received date: 2024-07-25

Revised date: 2024-12-09

Online published: 2025-08-20

Supported by

This work is supported by the project of National Social Science Fund of China titled “Research on the Knowledge Organization of Spatiotemporal Data in User Profiling Driven by Social Perception” (Grant No. 21BTQ055).

Fold

Abstract

[Purpose/Significance] Exploring the driving factors and characteristics of social media burnout behavior from the perspective of causal evolutionary logic helps understand users’ negative engagement with social media. It is crucial for social media operating companies in formulating effective strategies to enhance user experience and maintain user engagement. [Method/Process] Based on the exploration of explicit causal relationships, implicit causal relationships were first derived through similarity calculations and event representation is constructed by extracting subject-verb-object structures. Then the LERT-Large pre-trained model was utilized to map the events into a vector space enabling event merging. This was followed by event generalization, during which the GraphSAGE model was employed to predict potential causal relationships. Finally, a multi-pathway analysis was used to extract the core causal evolutionary logic under each generalized event. [Result/Conclusion] In terms of predicting potential causal relationships, the GraphSAGE model outperforms both the Node2Vec model and the GAT model by 7.54% and 9.91%, respectively, on the AUC metric, indicating its superior predictive performance. The findings suggest that the pressure factors contributing to social media burnout can be categorized into four dimensions based on the information ecosystem theory: information environment, information technology, information content, and information individuals. The core causal evolutionary logic under these four pressure factors follows the “stimulus-emotional experience-behavioral response” paradigm. Stimuli within the same pressure factor drive social media burnout behavior across different pressure factors, while a multi-level relational evolution characteristic of “emotional experience-behavioral response” also exists between diverse burnout behaviors across varying pressure factors. The methods proposed in this study effectively reveal the causal dynamic evolution characteristics of social media burnout behavior.

Key words： causal evolutionary logic; social media burnout behavior; information ecosystem theory; explicit causal relationships; implicit causal relationships; potential causal relationships

Cite this article

Zhao Youlin , Liu Zhuochen , Wang Jiajie , Feng Li , Shi Yanqing . A Study on the Causal Evolutionary Logic of Social Media Burnout Behaviors[J]. Library and Information Service, 2025 , 69(18) : 131 -146 . DOI: 10.13266/j.issn.0252-3116.2025.18.011

References

[1] PANG H, RUAN Y. Determining influences of information irrelevance, information overload and communication overload on wechat discontinuance intention: the moderating role of exhaustion[J]. Journal of retailing and consumer services, 2023, 72: 103289.
[2] AHLGREN M. The rise of threads on meta: key statistics & trends [2024 update][EB/OL]. [2024-12-31]. https://www.websiterating.com/blog/research/meta-threads-statistics.
[3] 甘春梅, 明昕宇. SOR视角下短视频用户间歇性中辍意愿的实证研究[J]. 情报科学, 2023, 41(6): 153-160. (GAN C M, MING X Y. An empirical study on short video users’intermittent discontinuous intention from the SOR perspective[J]. Information science, 2023, 41(6): 153-160.)
[4] FAROOQ A, DAHABIYEH L, MAIER C. Social media discontinuation: a systematic literature review on drivers and inhibitors[J]. Telematics and informatics, 2023(77): 101924.
[5] 李源, 马新宇, 杨国利, 等. 面向知识图谱和大语言模型的因果关系推断综述[J]. 计算机科学与探索, 2023, 17(10): 2358-2376. (LI Y, MA X Y, YANG G L, et al. Survey of causal inference for knowledge graphs and large language models[J]. Journal of frontiers of computer science & technology, 2023, 17(10): 2358-2376.)
[6] 缪峰, 王萍, 李太勇. 基于事件动作方向的隐式因果关系抽取方法[J]. 计算机科学, 2022, 49(3): 276-280. (MIU F, WANG P, LI T Y. Implicit causality extraction method based on event action direction[J]. Computer science, 2022, 49(3): 276-280.)
[7] 季忠洋, 李北伟, 朱婧祎, 等. 情感体验和感知控制双重视角下社交媒体用户倦怠行为机理研究[J]. 情报理论与实践, 2019, 42(4): 129-135. (JI Z Y, LI B W, ZHU J Y, et al. Mechanism of social media users’ fatigue behavior from the dual-perspective of emotional experience and perceived control[J]. Information studies: theory & application, 2019, 42(4): 129-135.)
[8] BURKE M, MARLOW C, LENTO T. Social network activity and social well-being[C]//Proceedings of the SIGCHI conference on human factors in computing systems. New York: SIGCHI, 2010: 1909-1912.
[9] 刘鲁川, 李旭, 张冰倩. 社交媒体用户的负面情绪与消极使用行为研究评述[J]. 情报杂志, 2018, 37(1): 105-113, 121. (LIU L C, LI X, ZHANG B Q. Research on negative emotions and passive use behaviors of social media users[J]. Journal of intelligence, 2018, 37(1): 105-113, 121.)
[10] 张艳丰, 刘亚丽, 彭丽徽, 等. 移动社交媒体倦怠行为的影响因素与作用路径研究[J]. 图书情报工作, 2020, 64(13): 111-119. (ZHANG Y F, LIU Y L, PENG L H, et al. Research on influencing factors and action path of mobile social media fatigue behavior[J]. Library and information service, 2020, 64(13): 111-119.)
[11] ZHANG Y, LIU Y, LI W, et al. A study of the influencing factors of mobile social media fatigue behavior based on the grounded theory[J]. Information discovery and delivery, 2020, 48(2): 91-102.
[12] 范春竹, 邓小昭, 韩毅. 社交媒体用户消极使用行为：多源数据融合视角[J]. 图书情报工作, 2022, 66(15): 76-85. (FAN C Z, DENG X Z, HAN Y. Researches on passive behavior for social media users: from the perspective of the fusion of multi-source data[J]. Library and information service, 2022, 66(15): 76-85.)
[13] XIE X, TSAI N. The effects of negative information-related incidents on social media discontinuance intention: evidence from sem and fsqca[J]. Telematics and informatics, 2021(56): 101503.
[14] ZHANG M, LI S, LIN W, et al. Escape or return? Users’ intermittent discontinuance behavior in strong-ties social functions[J]. Information & management, 2024, 61(1): 103902.
[15] 刘挺. 从知识图谱到事理图谱[EB/OL]. [2025-02-20]. https://www.leiphone.com/category/ai/Fx6Mgs9WRPBshnIG.html. (LIU T. From knowledge graph to event logic graph[EB/OL]. [2025-02-20]. https://www.leiphone.com/category/ai/Fx6Mgs9WRPBshnIG.html.)
[16] 魏建香, 梁帅.朱云霞, 等. 事理图谱研究进展[J]. 情报资料工作, 2023(6): 35-43. (WEI J X, LIANG S, ZHU Y X, et al. Progress in the study of event evolution graph[J]. Information and documentation services, 2023(6): 35-43.)
[17] 温学兵, 宋雨泽, 王秋萍. 事理图谱研究进展[J]. 沈阳师范大学学报(自然科学版), 2023, 41(2): 153-157. (WEN X B, SONG Y Z, WANG Q P. Research progress of rational map[J]. Journal of Shenyang Normal University (natural science edition), 2023, 41(2): 153-157.)
[18] 孙传明, 陈熙, 王萍. 基于在线评论的非遗纪录片受众需求事理图谱构建研究[J]. 情报科学, 2023, 41(9): 107-114. (SUN C M, CHEN X, WANG P. The construction of audience needs event logic graph of intangible cultural heritage documentary based on online reviews[J]. Information science, 2023, 41(9): 107-114.)
[19] 鞠海龙, 彭珺. 基于评论挖掘的用户购买行为因果事理图谱分析[J]. 情报科学, 2021, 39(10): 170-177. (JU H L, PENG J. Mining competitive intelligence based on event logic graph[J]. Information science, 2021, 39(10): 170-177.)
[20] 杨纪星, 杨波, 朱剑林, 等. 金融领域事件因果关系发现及事理图谱构建与应用[J]. 中文信息学报, 2023, 37(7): 131-142. (YANG J X, YANG B, ZHU J L, et al. Event causality extraction, eventic graph construction and application in financial domain[J]. Journal of Chinese information processing, 2023, 37(7): 131-142.)
[21] MCCOY R T, PAVLICK E, LINZEN T. Right for the wrong reasons: diagnosing syntactic heuristics in natural language inference[C]//Proceedings of the 57th annual meeting of the Association for Computational Linguistics. Florence: Association for Computational Linguistics, 2019: 3428-3448.
[22] YANG S, WANG F, ZHA D, et al. Nargnn: narrative graph neural networks for new script event prediction problem[C]//2020 IEEE intl conf on parallel & distributed processing with applications, big data & cloud computing, sustainable computing & communications. Exeter: IEEE, 2020: 481-488.
[23] SORGENTE A, VETTIGLI G, MELE F. Automatic extraction of cause-effect relations in natural language text[C]//Proceedings of the international conference of the Italian Association for Artificial Intelligence. Turin: DART@ AI* IA, 2013: 37-48.
[24] 田依林, 李星. 基于事理图谱的新冠肺炎疫情网络舆情演化路径分析[J]. 情报理论与实践, 2021, 44(3): 76-83. (TIAN Y L, LI X. Analysis on the evolution path of covid-19 network public opinion based on the event evolutionary graph[J]. Information studies: theory & application, 2021, 44(3): 76-83.)
[25] 单晓红, 庞世红, 刘晓燕, 等. 基于事理图谱的政策影响分析方法及实证研究[J]. 复杂系统与复杂性科学, 2019, 16(1): 74-82. (DAN X H, PANG S H, LIU X Y, et al. Analysis and empirical study of policy impact based on event evolution graph[J]. Complex systems and complexity science, 2019, 16(1): 74-82.)
[26] 王佳琦, 韩军, 孙启童. 基于依存句法的中文语义模型及语义提取方法[J]. 中文信息学报, 2023, 37(10): 16-25. (WANG J Q, HAN J, SUN Q T. Chinese semantic model and semantic extraction method based on dependency syntax[J]. Journal of Chinese information processing, 2023, 37(10): 16-25.)
[27] ZHAO S, WANG Q, MASSUNG S, et al. Constructing and embedding abstract event causality networks from text snippets[C]//Proceedings of the tenth ACM international conference on Web search and data mining. Cambridge: ACM, 2017: 335-344.
[28] HAO H, SUN X E, WEI J. A semantic union model for open domain Chinese knowledge base question answering[J]. Sci rep, 2023, 13(1): 11903.
[29] 王春柳, 杨永辉, 邓霏, 等. 文本相似度计算方法研究综述[J]. 情报科学, 2019, 37(3): 158-168. (WANG C L, YANG Y H, DENG F, et al. A review of text similarity approaches[J]. Information science, 2019, 37(3): 158-168.)
[30] 陈二静, 姜恩波. 文本相似度计算方法研究综述[J]. 数据分析与知识发现, 2017, 1(6): 1-11. (CHEN E J, JIANG E B. Review of studies on text similarity measures[J]. Data analysis and knowledge discovery, 2017, 1(6): 1-11.)
[31] 张东鑫, 张敏. 图情领域LDA主题模型应用研究进展述评[J]. 图书情报知识, 2022, 39(6): 143-157. (ZHANG D X, ZHANG M. A review on application studies of LDA topic models in library and information science field[J]. Document, informaiton & knowledge, 2022, 39(6): 143-157.)
[32] GROVER A, LESKOVEC J. Node2vec: scalable feature learning for networks[C]//Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining. San Francisco: ACM, 2016: 855-864.
[33] VELIČKOVIĆ P, CUCURULL G, CASANOVA A, et al. Graph attention networks[J]. arxiv preprint arxiv, 2017, 1710: 10903.
[34] HAMILTON W L, YING R, LESKOVEC J. Inductive representation learning on large graphs[C]//Proceedings of the 31st international conference on neural information processing systems. New York: Curran Associates, 2017: 1025-1035.
[35] LI Z, ZHAO S, DING X, et al. Eeg: knowledge base for event evolutionary principles and patterns[C]//Social media processing: 6th national conference. Beijing: Springer, 2017: 40-52.
[36] XU Z, PU C, YANG J. Link prediction based on path entropy[J]. Physica a: statistical mechanics and its applications, 2016, 456: 294-301.
[37] KIMA E H J, JEONGB Y K, KIMC Y, et al. Exploring scientific trajectories of a large-scale dataset using topic-integrated path extraction[J]. Journal of informetrics, 2022, 16(1): 101242.
[38] QUESTMOBILE研究院. Questmobile2023年新媒体生态洞察：行业用户规模10.88亿，用户流转、分流进入新阶段，平台以两大途径谋增长、冲变现[EB/OL]. [2025-02-20]. https://www.tmtpost.com/6799426.html. (INSTITUTE Q R. Questmobile 2023 new media eco insights: industry user scale 1.088 billion, user flow, triage entering a new stage, platforms seek growth and dash for cash in two major ways[EB/OL]. [2025-02-20]. https://www.tmtpost.com/6799426.html.)
[39] MING X. Text2vec: a tool for text to vector[EB/OL]. [2025-02-20]. https://github.com/shibing624/text2vec.
[40] ZHANG G, ZHOU Y, BOLLEGALA D. Evaluating unsupervised dimensionality reduction methods for pretrained sentence embeddings[C]//Proceedings of the 2024 joint international conference on computational linguistics, language resources and evaluation. Torino: ELRA and ICCL, 2024: 6530-6543.
[41] 徐颖, 于雨禾, 张桓森. 何因生倦怠，何素调节之？—— 一项关于社交媒体倦怠的元分析研究[J]. 图书情报工作, 2021, 65(13): 31-43. (XU Y, YU Y H, ZHANG H S. What can produce fatigue? What factors regulate it? A meta-analysis study on social media fatigue[J]. Library and information service, 2021, 65(13): 31-43.)
[42] FU S, LI H, LIU Y, et al. Social media overload, exhaustion, and use discontinuance: examining the effects of information overload, system feature overload, and social overload[J]. Information processing & management, 2020, 57(6): 102307.
[43] FU S, LI H. Understanding social media discontinuance from social cognitive perspective: evidence from facebook users[J]. Journal of information science, 2022, 48(2): 544-560.

Options

Outlines

模态框（Modal）标题

Abstract

Cite this article

References