Is a Chatbot More Effective? Investigating the Effect of Service Recovery Agents and Consumer Loss on Consumer Forgiveness

What the paper says

As chatbots are increasingly deployed to address service failures, understanding their role in facilitating consumer forgiveness has become essential. Several studies have compared consumers’ reactions to service recovery efforts conducted by a human versus a chatbot. Through three scenario-based experiments (total N = 1875) with Chinese participants, our study examines the interaction between service recovery agents (chatbot vs. human), types of consumer loss (utilitarian vs. symbolic), and service failure severity (low vs. high) in influencing consumer forgiveness. The results reveal that in cases of symbolic loss, consumers perceive humans—rather than chatbots—as more capable of providing emotional support during service recovery, thus promoting forgiveness more effectively. However, this discrepancy diminishes in the case of utilitarian loss. Our findings further suggest that the combined effect of service recovery agents and consumer loss on forgiveness is moderated by service failure severity. In the case of low-severity failures, recovery services provided by humans (vs. chatbots) are more effective in fostering forgiveness for consumers experiencing symbolic losses. However, for high-severity failures, regardless of the type of loss, consumers exhibit a higher level of forgiveness toward recovery services provided by humans. This research offers the following practical implications for managers dealing with service failures: strategic escalation to human agents is recommended for symbolic losses or high-severity failures, but chatbots represent a cost-efficient solution for utilitarian losses in low-severity scenarios.