Artificial intelligence has been widely applied to e-commerce and the online business service field. However, few studies have focused on studying the differences in the effects of types of customer service on customer purchase intentions. Based on service encounter theory and superposition theory, we designed two shopping experiments to capture customers’ thoughts and feelings, in order to explore the differences in the effects of three different types of online customer service (AI customer service, manual customer service, and human–machine collaboration customer service) on customer purchase intention, and analyses the superposition effect of human–machine collaboration customer service. The results show that the consumer’s perceived service quality positively influences the customer’s purchase intention, and plays a mediating role in the effect of different types of online customer service on customer purchase intention; the product type plays a moderating role in the relationship between online customer service and customer purchase intention, and human–machine collaboration customer service has a superposition effect. This study helped to deepen the understanding of AI developers and e-commerce platforms regarding the application of AI in online business service, and provides reference suggestions for the formulation of more perfect business service strategies.

BackgroundWith the rapid development of “Internet + medicine” and the impact of the COVID-19 epidemic, online health communities have become an important way for patients to seek medical treatment. However, the mistrust between physicians and patients in online health communities has long existed and continues to impact the decision-making behavior of patients. The purpose of this article is to explore the influencing factors of patient decision-making in online health communities by identifying the relationship between physicians' online information and patients' selection behavior.MethodsIn this study, we selected China's Good Doctor (www.haodf.com) as the source of data, scrapped 10,446 physician data from December 2020 to June 2021 to construct a logit model of online patients' selection behavior, and used regression analysis to test the hypotheses.ResultsThe number of types of services, number of scientific articles, and avatar in physicians' personal information all has a positive effect on patients' selection behavior, while the title and personal introduction hurt patients' selection behavior. Online word-of-mouth positively affected patients' selection behavior and disease risk had a moderating effect.ConclusionFocusing on physician-presented information, this article organically combines the Elaboration likelihood model with trust source theory and online word-of-mouth from the perspective of the trusted party–physician, providing new ideas for the study of factors influencing patients' selection behavior in online health communities. The findings provide useful insights for patients, physicians, and community managers about the relationship between physician information and patients' selection behavior.

PurposeEnterprises build online product community to expect users to contribute: opinion sharing (content contribution) and product consumption (product contribution). Previous literature rarely focused on both. The purpose of this paper is to explain user contribution mechanism by identifying content contribution and product contribution.Design/methodology/approachThis research chose Xiaomi-hosted online product community (bbs.xiaomi.cn) and Huawei-hosted online product community (club.huawei.com) where users can freely share ideas and buy products at the same time. Data were crawled from 109,665 community users to construct dependent variable measurement, and 611 questionnaires were used to verify research hypotheses.FindingsThe results indicate that both cognitive needs and personal integration needs have a significant positive impact on browse behavior; social integration needs and hedonic needs have a significant positive impact on content contribution behavior. Browse behavior not only directly affects but also indirectly influences product contribution through content contribution behavior.Research limitations/implicationsFindings of this research provide community managers with useful insights into the relationship between content contribution and product contribution.Originality/valueThis study explains the formation mechanism of user product contribution and reveals the relationship between user content contribution and product contribution in online product community. This paper provides a different way of theorizing user contributions by incorporating uses and gratifications theory into the “Motivation-Behavior-Result” framework.

PurposeWith the proliferation of ideas submitted by users in firm-built online user innovation communities, community managers are faced with the problem of user idea overload. The purpose of this paper is to explore the influencing factors on the idea adoption to identify high quality ideas, and then propose a method to quickly filter high value ideas.Design/methodology/approachThe authors collected more than 110,000 data submitted by Xiaomi community users and analyzed the factors affecting idea adoption using a multinomial logistic regression model. In addition, the authors also used BP neural network to predict the idea adoption process.FindingsThe empirical results show that idea semantics, number of likes, number of comments, number of related posts, the existence of pictures and self-presentation have positive impact on idea adoption, while idea length and idea timeliness had negative impact on idea adoption. In addition, this paper calculates the idea evaluation value through the idea adoption process predicted by neural network and the mean value of idea term frequency inverse document frequency (TF-IDF).Originality/valueThis empirical study expands the theoretical perspective of idea adoption research by using dual-process theory and enriches the research methods in the field of idea adoption research through the multinomial logistic regression method. Based on our findings, firms can quickly identify valuable ideas and effectively alleviate the information overload problem of online user innovation communities.