To identify the key mechanisms underlying behavioral transitions, a multi-path structural model was developed encompassing user expectations, perceived service quality, overall satisfaction, complaint behavior, and continued usage intention. Empirical data were used to estimate the relationships among these variables. Building on this foundation, an agent-based simulation model was constructed, dividing users into four behavioral states “non-adoption, initial contact, active use, and regular adoption”. The model simulates the evolution of user behavior throughout the service process. Simulation results indicate that the transition rate from “active use to regular adoption” is only 36.36%, while the downgrade risk for regular adopters reaches 53.81%, representing a structural bottleneck for platform operations. Under strategy intervention scenarios, improving service reliability increases the proportion of regular adopters from 28.7% to 32.4% and reduces their downgrade rate to 50.15%. In contrast, a complaint mitigation strategy mainly targets the negative feedback pathway; although it can temporarily increase the proportion of regular adopters to 31.5%, it fails to effectively curb subsequent attrition, with the downgrade rate rising to 55.73%. This suggests that its capacity to stabilize user behavior is limited and insufficient for sustaining long-term usage relationships. The findings provide strategic support for optimizing platform service processes and managing user structure.
模型拟合优度整体表现良好。拟合优度指数(Goodness-of-fit index,GFI)为0.875,规范拟合指数(Normed fit index,NFI)为0.905,比较拟合指数(Comparative fit index,CFI)达到0.961,均已接近或超过常用评价标准。均方根近似误差(Root mean square error of approximation,RMSEA)为0.044,低于0.05的阈值,模型结构与观测数据的适配性得到了进一步印证。
ParmarJ, DasP, DaveS M. Study on demand and characteristics of parking system in urban areas: a review[J]. Journal of Traffic and Transportation Engineering (English Edition), 2020, 7(1): 111-124.
GuanHong-zhi, ZhangChun-hui, HanYan. Study on parking reservation choice behavior in tourist attractions considering psychological factors[J]. Journal of Dalian Jiaotong University, 2024, 45(3): 1-7.
[6]
WangA, GuanH, GuoJ,et al. An empirical study on the segmentation of potential users of shared parking spaces considering individual heterogeneity[J]. Journal of Advanced Transportation, 2022,336:No.130403.
[7]
KimD J, HwangY. A study of mobile internet user´s service quality perceptions from a user´s utilitarian and hedonic value tendency perspectives[J]. Information Systems Frontiers, 2012, 14: 409-421.
[8]
NiuZ, HuX, QiS, et al. Determinants to parking mode alternatives: a model integrating technology acceptance model and satisfaction-loyalty model[J]. Transportation Research Part A: Policy and Practice, 2021, 152: 216-234.
[9]
ZhangC, LiuY, LuW, et al. Evaluating user satisfaction index based on PLS-SEM model: evidence from Chinese public transport service[J]. Transportation Research Part A: Policy and Practice, 2019, 120:149-164.
[10]
ZainalS K, IsmailA. Assessment of factors affecting student's satisfaction and loyalty on the crossed parking system at residential colleges of Universiti Kebangsaan Malaysia[J]. Jurnal Kejuruteraan, 2019, 31(1): 123-129.
[11]
AkaiK, AokiK, UedaY,et al. Redesigning parking facilities using a parking service satisfaction survey at Izumo local airport in Japan[J]. Transportation Research Interdisciplinary Perspectives, 2021, 11:No.100433.
[12]
TsamiM, AdamosG, NathanailE, et al. A decision tree approach for achieving high customer satisfaction at urban interchanges[J]. Transport and Telecommunication, 2018, 19: No.194.
XiongZhi-hua, DongDai-yue, DongChun-jiao, et al. Combined decision-making choice behavior of spectator groups considering individual preferences[J]. Journal of Jilin University (Engineering and Technology Edition), 2024, 54(4): 979-986.
[15]
ChannamalluS S, KermanshachiS, RosenbergerJ M, et al. Determinants of user satisfaction in smart parking applications[J].Transport Economics and Management, 2025,3: 214-221.
[16]
XieM H, LinS Y, WeiS,et al. Online configuration of reservable parking spaces: an agent-based deep reinforcement learning approach[J]. Transportation Research Part E: Logistics and Transportation Review,2025, 194: No.103887.
[17]
DogaI, SakmanE. Successful complaint handling on social media predicts increased repurchase intention: the roles of trust in company and propensity to trust[J].European Management Journal, 2024, 42(1): 11-22.