Verbal harassment is a growing source of psychological stress for people around the world. It occurs both online and offline and relies on language to demean, threaten, or discredit its targets. Unlike other stressors such as loss or uncertainty, verbal harassment aims at silencing its targets by eroding their sense of being heard and weakening their perceived ability to respond. Many individuals lack access to adequate and timely support, however, when they experience such harassment. People increasingly turn to conversational artificial intelligence (AI) such as ChatGPT or dedicated AI companions for emotional support, raising questions about whether it can facilitate the same psychological benefits as actual human empathy. We focus on online contexts as a prevalent application of verbal harassment. We develop and test a psychological framework identifying three key linguistic signals of empathic listening (perspective-taking, emotional validation, and action orientation), that together restore a sense of feeling heard and enhance coping in the context of verbal harassment. We find that LLMs consistently produce language exhibiting stronger empathic-listening markers than human non-experts and trained mental health professionals, promoting more approach-oriented (vs. avoidance-oriented) coping strategies. A subsequent behavioral study shows that these linguistic signals boost recipients' sense of feeling heard and increase their coping self-efficacy. These findings reveal how specific linguistic features create empathic connections between humans and advanced conversational AI and can enhance people's psychological resilience. Our results highlight the potential for AI to serve as a scalable source of emotional support, especially when human support is unavailable or insufficient.

This research shows that AI-based conversational interfaces can have a profound impact on consumer-brand relationships. We develop a conceptual model of verbal embodiment in technology-mediated communication that integrates three key properties of human-to-human dialogue-(1) turn-taking (i.e., alternating contributions by the two parties), (2) turn initiation (i.e., the act of initiating the next turn in a sequence), and (3) grounding between turns (i.e., acknowledging the other party's contribution by restating or rephrasing it). These fundamental conversational properties systematically shape consumers' perception of an AI-based conversational interface, their perception of the brand that the interface represents, and their behavior in connection with that brand. Converging evidence from four studies shows that these dialogue properties enhance the perceived humanness of the interface, which in turn promotes more intimate consumer-brand relationships and more favorable behavioral brand outcomes (greater recommendation acceptance, willingness to pay a price premium, brand advocacy, and brand loyalty). Moreover, we show that these effects are reduced in contexts requiring less mutual understanding between the consumer and the brand. This research highlights how fundamental principles of human-to-human communication can be harnessed to design more intimate consumer-brand interactions in an increasingly AI-driven marketplace.

Prior research revealed a striking heterogeneity of how consumers view smart objects, from seeing them as helpful partners to merely a useful tool. We draw on mind perception theory to assess whether the attribution of mental states to smart objects reveals differences in consumer-smart object relationships and device usage. We train a language model to unobtrusively predict mind perception in smart objects from consumer-generated text. We provide a rich set of interpretable linguistic markers for mind perception, drawing on a diverse collection of text-mining techniques, and demonstrate that greater mind perception is associated with expressing a more communal (vs. instrumental) relationship with the device and using it more expansively. We find converging evidence for these associations using over 20,000 real-world customer reviews and also provide causal evidence that inducing a more communal (vs. instrumental) relationship with a smart object enhances mind perception and in turn increases the number of tasks consumers engage in with the device. These findings have important implications for the role of mind perception as a novel lens to study consumer-smart object relationships. We offer an easy-to-use web interface to access our language model using researchers own data or to fine-tune the model to entirely new domains.

Voice-based interfaces provide new opportunities for firms to interact with consumers along the customer journey. The current work demonstrates across four studies that voice-based (as opposed to text-based) interfaces promote more flow-like user experiences, resulting in more positively-valenced service experiences, and ultimately more favorable behavioral firm outcomes (i.e., contract renewal, conversion rates, and consumer sentiment). Moreover, we also provide evidence for two important boundary conditions that reduce such flow-like user experiences in voice-based interfaces (i.e., semantic disfluency and the amount of conversational turns). The findings of this research highlight how fundamental theories of human communication can be harnessed to create more experiential service experiences with positive downstream consequences for consumers and firms. These findings have important practical implications for firms that aim at leveraging the potential of voice-based interfaces to improve consumers’ service experiences and the theory-driven “conversational design” of voice-based interfaces.

The current research demonstrates how conversational robo advisors as opposed to static, non-conversational robo advisors alter perceptions of trust, the evaluation of a financial services firm, and consumer financial decision making. We develop and empirically test a novel conceptualization of conversational robo advisors building on prior work in human-to-human communication and interpersonal psychology, showing that conversational robo advisors cause greater levels of affective trust compared to non-conversational robo advisors and evoke a more benevolent evaluation of a financial services firm. We demonstrate that this increase in affective trust not only affects firm perception (in terms of benevolence attributions or a more positively-valenced onboarding experience), but has important implications for investor behavior, such as greater recommendation acceptance and an increase in asset allocation toward conversational robo advisors. These findings have important implications for research on trust formation between humans and machines, the effective design of conversational robo advisors, and public policy in the digital economy.

This work examines the effects of conversational chatbot interfaces on consumers’ brand perceptions and purchase decisions. Evidence from four experiments shows that incorporating such interfaces into the shopping process promotes more intimate consumer-brand relationships and increases consumers’ inclination to choose more higher-priced premium offers compared to traditional interfaces.

This work examines the effects of conversational interfaces on consumers’ brand perceptions and purchase decisions. Evidence from four experiments shows that incorporating such interfaces into the shopping process promotes more intimate consumer-brand relationships and increases consumers’ inclination to choose high-priced premium offers compared to traditional interfaces.

This paper proposes an original account of decision anomalies and a computational alternative to existing dynamic models of multi-attribute choice. To date, most models attempting to account for the “Big Three” decision anomalies (similarity, attraction, and compromise effects) are variants of evidence accumulation models, or rational Bayesian analysis. This paper provides an existence proof of a new approach in the form of a multi-agent system based on the principles of voting geometry. Assuming there are a number of neural systems (agents) within an individual’s brain, the Big Three decision anomalies can arise as a natural consequence of aggregating preferences across these agents. We operationalize these principles in VAMP, (Voting Agent Model of Preferences), and compare its performance to existing computational models as well as to empirical data. This provides a fundamentally different lens for understanding decision anomalies in multi-attribute choice.

Abstract The implementation of bot interfaces varies tremendously in current industry practice. They range from the human-like to those that merely present a brand logo or a digital avatar. Some applications provide a maximum amount of information with limited turn-taking between the user and the interface; others offer only short pieces of information and require more turn-taking. Instead of simply implementing the default option provided by chatbot providers and platforms, companies should consider very carefully how the specifics of the chatbot interface might affect the user experience. Simple mechanics such as increasing the frequency of interactions leads to greater trust and a more enjoyable user experience. Also, personalizing chatbots with basic consumer characteristics such as gender increases trust and improves the perceived closeness between the customer and the chatbot – and ultimately the brand. Brand managers should therefore consider chatbots not as merely another digital marketing fad or a way to save costs through service automation. When implemented wisely, they are even able to increase a company’s upselling potential.