Conversational Interface Research Articles

Investigating Usability of Conversational User Interfaces for Integrated System-Physical Interactions: A Medical Device Perspective

The use of Conversational User Interfaces (CUIs) as human-machine interfaces in AI-infused systems has become increasingly popular. However, the existing design guidelines for CUIs are inadequate for meeting the complex interaction requirements of applications involving integrated System-Physical Interaction. In this study, the real-life context of using CUIs as the front-end of AI-enabled medical devices is examined, investigating interaction and usability issues in clinical task operations. Voice- and text-based CUIs were tested with 40 participants to perform clinical tasks. Based on user testing results, a team of seven experts identified 116 unique usability issues and synthesized 16 heuristics using a multilevel thematic coding process. These heuristics were compared to past guidelines to assess their alignment and novelty. Further, 12 usability experts evaluated the heuristics across various clinical systems. The study established that the proposed 16 heuristics provide comprehensive guidance for designing and evaluating CUIs, addressing a wide range of usability requirements.

Modeling and enforcing access control policies in conversational user interfaces

Conversational user interfaces (CUIs), such as chatbots, are becoming a common component of many software systems. Although they are evolving in many directions (such as advanced language processing features, thanks to new AI-based developments), less attention has been paid to access control and other security concerns associated with CUIs, which may pose a clear risk to the systems they interface with. In this paper, we apply model-driven techniques to model and enforce access-control policies in CUIs. In particular, we present a fully fledged framework to integrate the role-based access-control (RBAC) protocol into CUIs by: (1) modeling a set of access-control rules to specify permissions over the bot resources using a domain-specific language that tailors core RBAC concepts to the CUI domain; and (2) describing a mechanism to show the feasibility of automatically generating the infrastructure to evaluate and enforce the modeled access control policies at runtime.

Assessing the Feasibility and Acceptability of Smart Speakers in Behavioral Intervention Research With Older Adults: Mixed Methods Study.

Smart speakers, such as Amazon's Echo and Google's Nest Home, combine natural language processing with a conversational interface to carry out everyday tasks, like playing music and finding information. Easy to use, they are embraced by older adults, including those with limited physical function, vision, or computer literacy. While smart speakers are increasingly used for research purposes (eg, implementing interventions and automatically recording selected research data), information on the advantages and disadvantages of using these devices for studies related to health promotion programs is limited. This study evaluates the feasibility and acceptability of using smart speakers to deliver a physical activity (PA) program designed to help older adults enhance their physical well-being. Community-dwelling older adults (n=18) were asked to use a custom smart speaker app to participate in an evidence-based, low-impact PA program for 10 weeks. Collected data, including measures of technology acceptance, interviews, field notes, and device logs, were analyzed using a concurrent mixed analysis approach. Technology acceptance measures were evaluated using time series ANOVAs to examine acceptability, appropriateness, feasibility, and intention to adopt smart speaker technology. Device logs provided evidence of interaction with and adoption of the device and the intervention. Interviews and field notes were thematically coded to triangulate the quantitative measures and further expand on factors relating to intervention fidelity. Smart speakers were found to be acceptable for administering a PA program, as participants reported that the devices were highly usable (mean 5.02, SE 0.38) and had strong intentions to continue their use (mean 5.90, SE 0.39). Factors such as the voice-user interface and engagement with the device on everyday tasks were identified as meaningful to acceptability. The feasibility of the devices for research activity, however, was mixed. Despite the participants rating the smart speakers as easy to use (mean 5.55, SE 1.16), functional and technical factors, such as Wi-Fi connectivity and appropriate command phrasing, required the provision of additional support resources to participants and potentially impaired intervention fidelity. Smart speakers present an acceptable and appropriate behavioral intervention technology for PA programs directed at older adults but entail additional requirements for resource planning, technical support, and troubleshooting to ensure their feasibility for the research context and for fidelity of the intervention.

Generating voice user interfaces from web sites

ABSTRACT Virtual assistants allow users to interact with apps using a conversational mode. A particular kind of device supporting virtual assistants is the smart speaker, which allows end users to access contents and services, perform searches and command smart environments via voice interaction. These devices are gaining relevance among users, and the number of apps available for giving them more conversational capabilities grows constantly. However, there is a gap between what can be achieved using these devices and the information available on the web, i.e. most web apps don't have one smart speaker app counterpart. In this work, we present a two-step approach to defining conversational interfaces for virtual assistants based on existing web sites. During the first step, the user creates web content blocks, which describe target contents and the strategy for retrieving them. In the second step, the user uses web content blocks to specify the conversational interface. Although the approach could be considered generic enough for any kind of conversational interface, we focus our research on voice user interfaces, considering smart speaker apps as a major target. With our approach, apps based on voice user interfaces for smart speakers may be developed in a no-code manner. We describe and illustrate the approach by presenting usage examples and an evaluation using the Alexa service and an Amazon Echo device. The evaluation shows promising results for two case studies where there is no significant difference between the user experience when comparing solutions developed using the Alexa SDK versus apps using our approach.

Exploring Young Adults' Views About Aroha, a Chatbot for Stress Associated With the COVID-19 Pandemic: Interview Study Among Students.

In March 2020, New Zealand was plunged into its first nationwide lockdown to halt the spread of COVID-19. Our team rapidly adapted our existing chatbot platform to create Aroha, a well-being chatbot intended to address the stress experienced by young people aged 13 to 24 years in the early phase of the pandemic. Aroha was made available nationally within 2 weeks of the lockdown and continued to be available throughout 2020. In this study, we aimed to evaluate the acceptability and relevance of the chatbot format and Aroha's content in young adults and to identify areas for improvement. We conducted qualitative in-depth and semistructured interviews with young adults as well as in situ demonstrations of Aroha to elicit immediate feedback. Interviews were recorded, transcribed, and analyzed using thematic analysis assisted by NVivo (version 12; QSR International). A total of 15 young adults (age in years: median 20; mean 20.07, SD 3.17; female students: n=13, 87%; male students: n=2, 13%; all tertiary students) were interviewed in person. Participants spoke of the challenges of living during the lockdown, including social isolation, loss of motivation, and the demands of remote work or study, although some were able to find silver linings. Aroha was well liked for sounding like a "real person" and peer with its friendly local "Kiwi" communication style, rather than an authoritative adult or counselor. The chatbot was praised for including content that went beyond traditional mental health advice. Participants particularly enjoyed the modules on gratitude, being active, anger management, job seeking, and how to deal with alcohol and drugs. Aroha was described as being more accessible than traditional mental health counseling and resources. It was an appealing option for those who did not want to talk to someone in person for fear of the stigma associated with mental health. However, participants disliked the software bugs. They also wanted a more sophisticated conversational interface where they could express themselves and "vent" in free text. There were several suggestions for making Aroha more relevant to a diverse range of users, including developing content on navigating relationships and diverse chatbot avatars. Chatbots are an acceptable format for scaling up the delivery of public mental health and well-being-enhancing strategies. We make the following recommendations for others interested in designing and rolling out mental health chatbots to better support young people: make the chatbot relatable to its target audience by working with them to develop an authentic and relevant communication style; consider including holistic health and lifestyle content beyond traditional "mental health" support; and focus on developing features that make users feel heard, understood, and empowered.

Designing a Framework for Conversational Interfaces

Combining the latest advances in machine learning with earlier approaches.

Conversational assistants in academic libraries: enhancing reference services through Bing Chat

Purpose This research aims to explore the integration of Bing Chat, an artificial intelligence (AI)-powered conversational assistant, into academic libraries and its potential impact on reference services. Design/methodology/approach This study analyzes existing literature to investigate the integration of Bing Chat in academic libraries. This research focuses on its features, capabilities and implications for enhancing user experiences and addressing information needs. Findings The findings highlight that Bing Chat’s conversational interface facilitates more dynamic and context-aware reference interactions, fostering user empowerment and personalized learning pathways. The integration of Bing Chat with existing library resources enhances resource discovery, navigational assistance and engagement with visual content. However, challenges related to accuracy, privacy and algorithmic bias require careful consideration. Originality/value This research contributes to the literature by providing an in-depth exploration of Bing Chat’s integration into academic libraries, emphasizing its transformative potential for reference services. This study addresses ethical and social dimensions associated with AI-driven tools in library environments, offering insights into ensuring fairness, privacy and user trust.

Exploring the Potential of Conversational Interfaces for Care of Older Adults: Insights from Stakeholder Workshops.

This study aimed to explore the utilisation of conversational interfaces (CIs) by local care service providers (CSPs) and their potential applications in improving the quality of life for older adults. Two workshops were conducted with stakeholders to gather insights and requirements. Although currently not yet utilised by CSPs, stakeholders expressed their openness towards CIs and believed that older adults are very likely to appear receptive to them. Loneliness and isolation were identified as significant challenges, even among older adults living in care institutions. Key requirements for chatbots included complementarity to in-person interactions, user-friendliness, 24/7 availability, and seamless integration into daily life. Ethical considerations, data privacy, and security were emphasised, also highlighting the importance of transparency and limited data retention. Various use cases were discussed, such as assistance, self-management tools, and reminders. The financing issues remained inconclusive, but health insurances showed their potential interest in solutions targeting loneliness.

A systematic review A Conversational interface agent for the export business acceleration

Conversational agents, which understand, respond to, and learn from each interaction using Automatic Speech Recognition (ASR), Natural Language Processing (NLP), Advanced Dialog Management, and Machine Learning (ML), have become more common in recent years. Conversational agents, also referred to as chatbots, are used to have real-time conversations with individuals. As a result, conversational agents are now being used in a variety of sectors, including those in education, healthcare, marketing, customer assistance, and entertainment. Conversational agents, which are frequently used as chatbots and virtual or AI helpers, show how computational linguistics is used in everyday life. It can be challenging to pinpoint the variables that affect the use of conversational agents for business acceleration and to defend their utility in order to enhance export company. This paper provides a summary of the evolution of conversational agents from a straightforward model to a sophisticated intelligent system, as well as how they are applied in various practical contexts. This study contributes to the body of literature on information systems by contrasting the different conversational agent types based on the export business acceleration interface. This paper also identifies the challenges conversational applications experience today and makes recommendations for further research.

Explaining machine learning models with interactive natural language conversations using TalkToModel

Practitioners increasingly use machine learning (ML) models, yet models have become more complex and harder to understand. To understand complex models, researchers have proposed techniques to explain model predictions. However, practitioners struggle to use explainability methods because they do not know which explanation to choose and how to interpret the explanation. Here we address the challenge of using explainability methods by proposing TalkToModel: an interactive dialogue system that explains ML models through natural language conversations. TalkToModel consists of three components: an adaptive dialogue engine that interprets natural language and generates meaningful responses; an execution component that constructs the explanations used in the conversation; and a conversational interface. In real-world evaluations, 73% of healthcare workers agreed they would use TalkToModel over existing systems for understanding a disease prediction model, and 85% of ML professionals agreed TalkToModel was easier to use, demonstrating that TalkToModel is highly effective for model explainability.

A chatbot for hypertension self-management support: user-centered design, development, and usability testing.

Health-related chatbots have demonstrated early promise for improving self-management behaviors but have seldomly been utilized for hypertension. This research focused on the design, development, and usability evaluation of a chatbot for hypertension self-management, called "Medicagent." A user-centered design process was used to iteratively design and develop a text-based chatbot using Google Cloud's Dialogflow natural language understanding platform. Then, usability testing sessions were conducted among patients with hypertension. Each session was comprised of: (1) background questionnaires, (2) 10 representative tasks within Medicagent, (3) System Usability Scale (SUS) questionnaire, and (4) a brief semi-structured interview. Sessions were video and audio recorded using Zoom. Qualitative and quantitative analyses were used to assess effectiveness, efficiency, and satisfaction of the chatbot. Participants (n = 10) completed nearly all tasks (98%, 98/100) and spent an average of 18 min (SD = 10 min) interacting with Medicagent. Only 11 (8.6%) utterances were not successfully mapped to an intent. Medicagent achieved a mean SUS score of 78.8/100, which demonstrated acceptable usability. Several participants had difficulties navigating the conversational interface without menu and back buttons, felt additional information would be useful for redirection when utterances were not recognized, and desired a health professional persona within the chatbot. The text-based chatbot was viewed favorably for assisting with blood pressure and medication-related tasks and had good usability. Flexibility of interaction styles, handling unrecognized utterances gracefully, and having a credible persona were highlighted as design components that may further enrich the user experience of chatbots for hypertension self-management.

Parametric Evaluation Techniques for Reliability of Internet of Things (IoT)

Reliability analysis aims to assess the dependability and performance of a system over time, considering factors such as device failures, communication issues, and data integrity. By integrating taxonomy and reliability analysis, researchers can systematically analyze and enhance the reliability of IoT systems by addressing specific components and categories identified in the taxonomy. IoT based on its reliable applications is classified among various categories such as smart home devices, smart watches, electric vehicles with IoT capabilities, industrial, healthcare, agriculture, soil monitoring sensors, smart city infrastructure, environmental monitoring devices, and smart energy management devices. The need for a consistent taxonomy was one of the problems recognized and examined in this paper even though IoT management technology is developing. To examine the reliability analysis of IoT systems, we created a brand-new taxonomy for IoT gadgets that places a strong focus on administration. We have released a completely new IoT reliability RBD model analysis at different gateways and Round-Trip Time is to be analyzed. It features an aircraft for dependability. Our goal is to help administrators of networks, as well as designers, put processes in place that will analyze and enhance the reliability of IoT systems. To implement techniques to increase the IoT system's reliability, we may utilize the management capabilities to keep an eye on the devices. ChatGPT can act as the conversational interface for ISABELA. By integrating ChatGPT with ISABELA's functionality, users can have natural language conversations with ISABELA, making the interaction more intuitive and user-friendly. A use case study of ISABELA has enhanced the position of the CHATGPT system in the IoT system which increase the efficiency and reliability of IoT designs and networks.

Towards Hybrid Automation by Bootstrapping Conversational Interfaces for IT Operation Tasks

Process automation has evolved from end-to-end automation of repetitive process branches to hybrid automation where bots perform some activities and humans serve other activities. In the context of knowledge-intensive processes such as IT operations, implementing hybrid automation is a natural choice where robots can perform certain mundane functions, with humans taking over the decision of when and which IT systems need to act. Recently, ChatOps, which refers to conversation-driven collaboration for IT operations, has rapidly accelerated efficiency by providing a cross-organization and cross-domain platform to resolve and manage issues as soon as possible. Hence, providing a natural language interface to bots is a logical progression to enable collaboration between humans and bots. This work presents a no-code approach to provide a conversational interface that enables human workers to collaborate with bots executing automation scripts. The bots identify the intent of users' requests and automatically orchestrate one or more relevant automation tasks to serve the request. We further detail our process of mining the conversations between humans and bots to monitor performance and identify the scope for improvement in service quality.

A lifestyle monitoring system for cardiovascular care: protocol of a prospective observational trial

Abstract Funding Acknowledgements Type of funding sources: Foundation. Main funding source(s): Dutch Heart Foundation. Background In cardiac rehabilitation, technological innovations can improve patient-relevant outcomes and are associated with reductions in health care costs by enabling personalized care. Lifestyle factors such as physical fitness, dietary habits, mental stress, and sleep quality, are strong predictors of the occurrence, clinical course, and overall treatment outcomes of common cardiovascular diseases such as coronary artery disease and atrial fibrillation. However, these lifestyle factors are rarely monitored, nor used in daily clinical practice and personalized cardiac care. Moreover, non-adherence to long-term self-reporting is common. Purpose The main purpose of this study is to evaluate adherence to a continuous unobtrusive and patient-friendly lifestyle monitoring system. Methods In a prospective observational trial we investigate usability and adherence of a monitoring system for lifestyle factors, i.e., daily physical activity levels, dietary habits, mental stress, smoking habit, and sleep quality. Patients (n = 100) scheduled for or who recently underwent coronary artery bypass surgery, an electrophysiology study and/or radiofrequency catheter ablation, a transcatheter aortic valve implantation, a fractional flow reserve test and/or a percutaneous coronary intervention, and/or valve surgery are asked to participate. The monitoring system consists of a care platform with a custom-built conversational interface—a chatbot—and a wrist-worn wearable medical device. The wrist-worn device collects continuous objective data on physical activity and the chatbot collects subjective data (e.g., sleep quality, nutrition intake and mental stress levels), both for 7 separate days per month repeatedly during the study period. Data collection starts one week before treatment and continues until 1-year after discharge. Via a dashboard, patients can observe their lifestyle measures and adherence to self-reporting, track personal goals, and share their lifestyle data with practitioners and relatives. The primary outcome of the trail is adherence to using the integrated platform for self-tracking data. The secondary outcomes include system usability, determinants of adherence and the relation between baseline lifestyle behaviour and long-term patient-relevant outcomes. Discussion Systematic monitoring during daily life is key to gain insights into patients’ lifestyle behaviours. In this context, adherence to monitoring systems is critical for cardiologists and other care providers to obtain crucial information to personalize care. In this project, we present insights into the evaluation of adherence to monitoring technology including a conversational agent and continuous monitoring, focusing on multiple lifestyle domains for one year. This work contributes to our understanding of adherence, patient-centred data collection and interpretation, to enable personalized cardiac interventions, improve patient-relevant outcomes, and reduce health care costs.

Design Proposal for a Virtual Shopping Assistant for People with Vision Problems Applying Artificial Intelligence Techniques

Accessibility is an increasingly important topic for Ecommerce, especially for individuals with vision problems. To improve their online experience, the design of a voice assistant has been proposed to allow these individuals to browse and shop online more quickly and efficiently. This voice assistant forms an intelligent system that can understand and respond to users’ voice commands. The design considers the visual limitations of the users, such as difficulty reading information on the screen or identifying images. The voice assistant provides detailed product descriptions and ideas in a clear, easy-to-understand voice. In addition, the voice assistant has a series of additional features to improve the shopping experience. For example, the assistant can provide product recommendations based on the user’s previous purchases and information about special promotions and discounts. The main goal of this design is to create an accessible and inclusive online shopping experience for the visually impaired. The voice assistant is based on a conversational user interface, allowing users to easily navigate an eCommerce website, search for products, and make purchases.

Adherence to a lifestyle monitoring system in patients with heart disease: protocol for the care-on prospective observational trial

BackgroundLifestyle factors such as physical fitness, dietary habits, mental stress, and sleep quality, are strong predictors of the occurrence, clinical course, and overall treatment outcomes of common cardiovascular diseases. However, these lifestyle factors are rarely monitored, nor used in daily clinical practice and personalized cardiac care. Moreover, non-adherence to long-term self-reporting of these lifestyle factors is common. In the present study, we evaluate adherence to a continuous unobtrusive and patient-friendly lifestyle monitoring system using evidence-based assessment tools.MethodsIn a prospective observational trial (N = 100), the project investigates usability of and adherence to a monitoring system for multiple lifestyle factors relevant to cardiovascular disease, i.e., daily physical activity levels, dietary habits, mental stress, smoking, and sleep quality. Patients with coronary artery disease, valvular disease and arrhythmias undergoing an elective intervention are asked to participate. The monitoring system consists of a secured online platform with a custom-built conversational interface—a chatbot—and a wrist-worn wearable medical device. The wrist-worn device collects continuous objective data on physical activity and the chatbot is used to collect self-report data. Participants collect self-reported lifestyle data via the chatbot for a maximum of 4 days every other week; in the same week physiological data are collected for 7 days for 24 h. Data collection starts one week before the intervention and continues until 1-year after discharge. Via a dashboard, patients can observe their lifestyle measures and adherence to self-reporting, set and track personal goals, and share their lifestyle data with practitioners and relatives. The primary outcome of the trial is adherence to using the integrated platform for self-tracking data. The secondary outcomes include system usability, determinants of adherence and the relation between baseline lifestyle behaviour and long-term patient-relevant outcomes.DiscussionSystematic monitoring during daily life is essential to gain insights into patients’ lifestyle behaviour. In this context, adherence to monitoring systems is critical for cardiologists and other care providers to monitor recovery after a cardiac intervention and to detect clinical deterioration. With this project, we will evaluate patients’ adherence to lifestyle monitoring technology. This work contributes to the understanding of patient-centered data collection and interpretation, to enable personalized care after cardiac interventions in order to ultimately improve patient-relevant outcomes and reduce health care costs.Trial registrationNetherlands Trial Registry (NTR) NL9861. Registered 6th of November 2021.

Artificial intelligence-based text generators in hepatology: ChatGPT is just the beginning.

Since its release as a "research preview" in November 2022, ChatGPT, the conversational interface to the Generative Pretrained Transformer 3 large language model built by OpenAI, has garnered significant publicity for its ability to generate detailed responses to a variety of questions. ChatGPT and other large language models generate sentences and paragraphs in response to word patterns in training data that they have previously seen. By allowing users to communicate with an artificial intelligence model in a human-like way, however, ChatGPT has crossed the technological adoption barrier into the mainstream. Existing examples of ChatGPT use-cases, such as negotiating bills, debugging programing code, and writing essays, indicate that ChatGPT and similar models have the potential to have profound (and yet unknown) impacts on clinical research and practice in hepatology. In this special article, we discuss the general background and potential pitfalls of ChatGPT and associated technologies-and then we explore its uses in hepatology with specific examples.

Creating ‘a Simple Conversation’: Designing a Conversational User Interface to Improve the Experience of Accessing Support for Study

Administrative processes are ubiquitous in modern life and have been identified as a particular burden to those with accessibility needs. Students who have accessibility needs often have to understand guidance, fill in complex forms, and communicate with multiple parties to disclose disabilities and access appropriate support. Conversational user interfaces (CUIs) could allow us to reimagine such processes, yet there is currently limited understanding of how to design these to be accessible, or whether such an approach would be preferred. In the ADMINS (Assistants for the Disclosure and Management of Information about Needs and Support) project, we implemented a virtual assistant (VA) which is designed to enable students to disclose disabilities and to provide guidance and suggestions about appropriate support. ADMINS explores the potential of CUIs to reduce administrative burden and improve the experience of arranging support by replacing a static form with written or spoken dialogue. This article reports the results of two trials conducted during the project. A beta trial using an early version of the VA provided understanding of accessibility challenges and issues in user experience. The beta trial sample included 22 students who had already disclosed disabilities and 3 disability support advisors. After improvements to the design, a larger main trial was conducted with 134 students who disclosed their disabilities to the university using both the VA and the existing form-based process. The results show that the VA was preferred by most participants to completing the form (64.9% vs 23.9%). Qualitative and quantitative feedback from the trials also identified accessibility and user experience barriers for improving CUI design, and an understanding of benefits and preferences that can inform further development of accessible CUIs for this design space.

The Role of ChatGPT in Data Science: How AI-Assisted Conversational Interfaces Are Revolutionizing the Field

ChatGPT, a conversational AI interface that utilizes natural language processing and machine learning algorithms, is taking the world by storm and is the buzzword across many sectors today. Given the likely impact of this model on data science, through this perspective article, we seek to provide an overview of the potential opportunities and challenges associated with using ChatGPT in data science, provide readers with a snapshot of its advantages, and stimulate interest in its use for data science projects. The paper discusses how ChatGPT can assist data scientists in automating various aspects of their workflow, including data cleaning and preprocessing, model training, and result interpretation. It also highlights how ChatGPT has the potential to provide new insights and improve decision-making processes by analyzing unstructured data. We then examine the advantages of ChatGPT’s architecture, including its ability to be fine-tuned for a wide range of language-related tasks and generate synthetic data. Limitations and issues are also addressed, particularly around concerns about bias and plagiarism when using ChatGPT. Overall, the paper concludes that the benefits outweigh the costs and ChatGPT has the potential to greatly enhance the productivity and accuracy of data science workflows and is likely to become an increasingly important tool for intelligence augmentation in the field of data science. ChatGPT can assist with a wide range of natural language processing tasks in data science, including language translation, sentiment analysis, and text classification. However, while ChatGPT can save time and resources compared to training a model from scratch, and can be fine-tuned for specific use cases, it may not perform well on certain tasks if it has not been specifically trained for them. Additionally, the output of ChatGPT may be difficult to interpret, which could pose challenges for decision-making in data science applications.

Machine Talk: How Verbal Embodiment in Conversational AI Shapes Consumer–Brand Relationships

Abstract 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.