|
|
|
| Impacts of Task Types on Generative Artificial Intelligence Interaction Outcomes from the Emotional Experience Perspective: Evidence from DeepSeek |
| Zhang Min, Zhang Dongxin, Zhang Ke, Qin Kenan, Yang Han |
| School of Information Management, Central China Normal University, Wuhan 430079 |
|
|
|
|
Abstract From the emotional experience perspective, exploring the impact of task types on the interaction outcomes of generative artificial intelligence (GAI) is highly significant for enhancing users’ intelligent interaction behavior and improving the design and service quality of human-AI interactions. This study uses generalized structural equation modeling, GAI-assisted coding, and interpretable machine learning with shapley additive explanations to conduct an in-depth analysis of 5560 app reviews related to DeepSeek’s text-generation application. The findings reveal that users predominantly use DeepSeek for instrumental tasks, followed by emotional and creative tasks. Both incidental emotions and overall satisfaction perform better in emotional and creative tasks, and task attributes significantly affect overall satisfaction, with high emotional exposure tasks more likely to elicit positive emotions and higher satisfaction. Moreover, incidental emotions exert a cumulative effect on overall emotions; however, the two differ in formation mechanisms: incidental emotions are shaped by multiple technical factors, whereas overall satisfaction is mainly constructed through functional features and emotional resonance. This study highlights that the GAI interaction design should prioritize emotionally intelligent responses across task types while guiding users to adjust their interaction strategies based on task characteristics, thus systematically improving the overall quality of interaction experiences.
|
|
Received: 10 September 2025
|
|
|
|
1 姜婷婷, 许艳闰, 傅诗婷, 等. 人智交互体验研究: 为人本人工智能发展注入新动力[J]. 图书情报知识, 2022, 39(4): 43-55.
2 李华锋, 袁振豪, 孙晓宁, 等. 用户体验视角下生成式人工智能对话管理能力测度研究[J]. 情报理论与实践, 2025, 48(8): 105-112, 123.
3 李蕾, 刘钊, 王栩彦. 用户体验视角下ChatGPT辅助信息检索的可用性研究[J]. 情报理论与实践, 2025, 48(2): 75-82.
4 王俊, 谢青伶, 刘畅. 日常生活情境下用户与生成式人工智能交互行为分析[J]. 图书情报知识, 2025, 42(2): 60-69, 93.
5 Liu-Thompkins Y, Okazaki S, Li H R. Artificial empathy in marketing interactions: bridging the human-AI gap in affective and social customer experience[J]. Journal of the Academy of Marketing Science, 2022, 50(6): 1198-1218.
6 王若佳, 范科鸣, 刘智锋, 等. 生成式人工智能环境下用户信息检索式行为研究[J]. 数据分析与知识发现, 2024, 8(8/9): 20-30.
7 李雨佳, 冉晓雅, 刘畅. 任务认知层次对用户与生成式人工智能交互行为与系统评价的影响研究[J]. 情报资料工作, 2025, 46(2): 51-60.
8 Huang M H, Rust R T. Engaged to a robot? The role of AI in service[J]. Journal of Service Research, 2021, 24(1): 30-41.
9 Schepers J, Belanche D, Casaló L V, et al. How smart should a service robot be?[J]. Journal of Service Research, 2022, 25(4): 565-582.
10 赵浜, 曹树金. 国内外生成式AI大模型执行情报领域典型任务的测试分析[J]. 情报资料工作, 2023, 44(5): 6-17.
11 曹茹烨, 曹树金. ChatGPT完成知识组织任务的效果及启示[J]. 情报资料工作, 2023, 44(5): 18-27.
12 Song Y, Huang L C, Zheng L Q, et al. Interactions with generative AI chatbots: unveiling dialogic dynamics, students’ perceptions, and practical competencies in creative problem-solving[J]. International Journal of Educational Technology in Higher Education, 2025, 22(1): Article No.12.
13 Kishimoto T, Hao X M, Chang T, et al. Single online self-compassion writing intervention reduces anxiety: with the feedback of ChatGPT[J]. Internet Interventions, 2025, 39: 100810.
14 郑博文, 王鼎庆. 生成式人工智能环境下用户学习型搜索行为及效果研究——基于认知风格和任务类型[J]. 现代情报, 2025, 45(6): 74-86, 111.
15 Urban M, Děchtěrenko F, Lukavsky J, et al. ChatGPT improves creative problem-solving performance in university students: an experimental study[J]. Computers & Education, 2024, 215: 105031.
16 傅诗婷, 姜婷婷, 宋德凤. 对话式搜索系统主动性对人智协作效果的影响研究[J]. 信息资源管理学报, 2025, 15(4): 42-55.
17 Lerner J S, Keltner D. Beyond valence: toward a model of emotion-specific influences on judgement and choice[J]. Cognition and Emotion, 2000, 14(4): 473-493.
18 Han S, Lerner J S, Keltner D. Feelings and consumer decision making: the appraisal-tendency framework[J]. Journal of Consumer Psychology, 2007, 17(3): 158-168.
19 V?stfj?ll D, Slovic P, Burns W J, et al. The arithmetic of emotion: integration of incidental and integral affect in judgments and decisions[J]. Frontiers in Psychology, 2016, 7: 325.
20 Oliver R L. A cognitive model of the antecedents and consequences of satisfaction decisions[J]. Journal of Marketing Research, 1980, 17(4): 460-469.
21 曾文, 徐红姣, 车尧, 等. 基于图书出版行业大数据的 选题决策分析模型研究[J]. 情报学报, 2018, 37(8): 813-821.
22 刘甲学, 陶易. 基于情感分析的评论数据用户满意度影响因素研究[J]. 现代情报, 2017, 37(7): 66-69.
23 Dalakas V. The effect of cognitive appraisals on emotional responses during service encounters[J]. Services Marketing Quarterly, 2006, 27(1): 23-41.
24 Huang M H, Rust R T. Artificial intelligence in service[J]. Journal of Service Research, 2018, 21(2): 155-172.
25 Norman D A. Emotional design: why we love (or hate) everyday things[M]. New York: Basic Books, 2004.
26 沈棋琦, 张雪, 赵杨. 基于评论主题挖掘的移动图书馆App用户情感体验评价体系构建[J]. 图书馆学研究, 2023(4): 41-51.
27 Turobov A, Coyle D, Harding V. Using ChatGPT for thematic analysis[PP/OL]. V1. arXiv (2024-05-13) [2025-07-16]. https://doi.org/10.48550/arXiv.2405.08828.
28 Nguyen-Trung K. ChatGPT in thematic analysis: can AI become a research assistant in qualitative research?[J]. Quality & Quantity, 2025, 59(6): 4945-4978.
29 Deiner M S, Deiner N A, Hristidis V, et al. Use of large language models to assess the likelihood of epidemics from the content of tweets: infodemiology study[J]. Journal of Medical Internet Research, 2024, 26: e49139.
30 徐琳宏, 林鸿飞, 潘宇, 等. 情感词汇本体的构造[J]. 情报学报, 2008, 27(2): 180-185.
31 Mitku A A, Zewotir T, North D, et al. Impact of ambient air pollution exposure during pregnancy on adverse birth outcomes: generalized structural equation modeling approach[J]. BMC Public Health, 2023, 23(1): article No.45.
32 穆学英, 崔璨, 崔军茹. 空间机会结构视角下的住房分化——基于中国新生代流动人口的实证研究[J]. 社会学研究, 2022, 37(2): 202-225.
33 Vasconcelos A G G, Almeida R M V, Nobre F F. The path analysis approach for the multivariate analysis of infant mortality data[J]. Annals of Epidemiology, 1998, 8(4): 262-271.
34 Endawkie A, Keleb A, Dilnesa T, et al. Generalized structural equation modeling of direct and indirect determinants of chronic undernutrition among under-five children in Ethiopia: further analysis of the 2019 mini Ethiopian demographic and health survey[J]. Journal of Health, Population and Nutrition, 2025, 44(1): Article No.73.
35 Lazarus R S. Emotion and adaptation[M]. Oxford: Oxford University Press, 1991.
36 Li B K, Yao R X, Nan Y F. How does anthropomorphism promote consumer responses to social chatbots: mind perception perspective[J]. Internet Research, 2025, 35(6): 2471-2495.
37 Park T, Lim C. Design principles for improving emotional affordances in an online learning environment[J]. Asia Pacific Education Review, 2019, 20(1): 53-67.
38 Ferrer R A, Ellis E M. Preliminary evidence for differential effects of integral and incidental emotions on risk perception and behavioral intentions: a meta-analysis of eight experiments[J]. Journal of Behavioral Decision Making, 2021, 34(2): 275-289. |
|
|
|
