Conversational Interface Research Articles

Talk2Care: Facilitating Asynchronous Patient-Provider Communication with Large-Language-Model

Despite the plethora of telehealth applications to assist home-based older adults and healthcare providers, basic messaging and phone calls are still the most common communication methods, which suffer from limited availability, information loss, and process inefficiencies. One promising solution to facilitate patient-provider communication is to leverage large language models (LLMs) with their powerful natural conversation and summarization capability. However, there is a limited understanding of LLMs' role during the communication. We first conducted two interview studies with both older adults (N=10) and healthcare providers (N=9) to understand their needs and opportunities for LLMs in patient-provider asynchronous communication. Based on the insights, we built an LLM-powered communication system, Talk2Care, and designed interactive components for both groups: (1) For older adults, we leveraged the convenience and accessibility of voice assistants (VAs) and built an LLM-powered conversational interface for effective information collection. (2) For health providers, we built an LLM-based dashboard to summarize and present important health information based on older adults' conversations with the VA. We further conducted two user studies with older adults and providers to evaluate the usability of the system. The results showed that Talk2Care could facilitate the communication process, enrich the health information collected from older adults, and considerably save providers' efforts and time. We envision our work as an initial exploration of LLMs' capability in the intersection of healthcare and interpersonal communication.

ChatGPT and me: First-time and experienced users’ perceptions of ChatGPT’s communicative ability as a dialogue partner

Chatbots like ChatGPT have the potential to produce more natural conversational user interface interactions. Yet, we currently know little about perceptions of ChatGPT as a dialogue partner, and if interaction changes these. Through an online, two-stage, mixed methods study conducted in July 2023, in which first-time and experienced users living in the UK or Ireland engaged in tasks with ChatGPT, we show that interaction improves attitudes towards the system for first-time users, while these attitudes are already positive and stable in experienced users. We further show that first-time users’ perceptions of ChatGPT’s communicative ability (competence, human-likeness, and flexibility) are more dynamic than those of experienced users, although the experienced users’ perceptions also peak post-interaction. When reflecting on their interaction experience with ChatGPT, both groups were positive with little mention of limitations. We discuss the implications of these findings for user perceptions of ChatGPT as a dialogue partner, and highlight the potential risks of uncritical adoption of such technology.

ForestQB: Enhancing Linked Data Exploration through Graphical and Conversational UIs Integration

This article introduces the Forest Query Builder (ForestQB), an innovative toolkit designed to enhance the exploration and application of observational Linked Data (LD) within the field of wildlife research and conservation. Addressing the challenges faced by non-experts in navigating Resource Description Framework (RDF) triplestores and executing SPARQL queries, ForestQB employs a novel integrated approach. This approach combines a graphical user interface (GUI) with a conversational user interface (CUI), thereby greatly simplifying the process of query formulation and making observational LD accessible to users without expertise in RDF or SPARQL. Developed through insights derived from a comprehensive ethnographic study involving wildlife researchers, ForestQB is specifically designed to improve the accessibility of SPARQL endpoints and facilitate the exploration of observational LD in wildlife research contexts. To evaluate the effectiveness of our approach, we conducted a user experiment. The results of this evaluation affirm that ForestQB is not only efficient and user-friendly but also plays a crucial role in eliminating barriers for users, facilitating the effective use of observational LD in wildlife conservation and extending its benefits to wider domains. (GitHub Link: github.com/i3omar/ForestQB).

Large language models meet user interfaces: The case of provisioning feedback

Incorporating Generative Artificial Intelligence (GenAI), especially Large Language Models (LLMs), into educational settings presents valuable opportunities to boost the efficiency of educators and enrich the learning experiences of students. A significant portion of the current use of LLMs by educators has involved using conversational user interfaces (CUIs), such as chat windows, for functions like generating educational materials or offering feedback to learners. The ability to engage in real-time conversations with LLMs, which can enhance educators' domain knowledge across various subjects, has been of high value. However, it also presents challenges to LLMs' widespread, ethical, and effective adoption. Firstly, educators must have a degree of expertise, including tool familiarity, AI literacy and prompting to effectively use CUIs, which can be a barrier to adoption. Secondly, the open-ended design of CUIs makes them exceptionally powerful, which raises ethical concerns, particularly when used for high-stakes decisions like grading. Additionally, there are risks related to privacy and intellectual property, stemming from the potential unauthorised sharing of sensitive information. Finally, CUIs are designed for short, synchronous interactions and often struggle and hallucinate when given complex, multi-step tasks (e.g., providing individual feedback based on a rubric on a large scale). To address these challenges, we explored the benefits of transitioning away from employing LLMs via CUIs to the creation of applications with user-friendly interfaces that leverage LLMs through API calls. We first propose a framework for pedagogically sound and ethically responsible incorporation of GenAI into educational tools, emphasizing a human-centred design. We then illustrate the application of our framework to the design and implementation of a novel tool called Feedback Copilot, which enables instructors to provide students with personalized qualitative feedback on their assignments in classes of any size. An evaluation involving the generation of feedback from two distinct variations of the Feedback Copilot tool, using numerically graded assignments from 338 students, demonstrates the viability and effectiveness of our approach. Our findings have significant implications for GenAI application researchers, educators seeking to leverage accessible GenAI tools, and educational technologists aiming to transcend the limitations of conversational AI interfaces, thereby charting a course for the future of GenAI in education.

Conversational user interfaces for maritime autonomous surface ships

We propose integrating conversational user interfaces (CUIs) into Maritime Autonomous Surface Ships (MASS) to facilitate direct communication with other ships without human intervention. The aim is to enable other ships and shore stations to inquire about and discuss the autonomous vessel's status, decisions, and future intentions in natural language, offloading VHF radio conversations for MASS operators. Recent advancements in Natural Language Processing (NLP) technology show promise. This paper presents an experimental study conducted in a ship simulator using a functional prototype CUI system. While the CUI system was capable of providing coherent answers to questions, the results indicate that interacting with the system is less trustworthy than interacting with a human ship officer. Key challenges contributing to this included: (1) a missing connection between the CUI and an autonomy system, leading to inaccurate and incorrect answers, (2) speech that lacked intonation and human-like qualities, and (3) a perceived inability of the system to collaborate. The paper discusses several aspects of utilising CUI systems in a maritime shipping environment and concludes by proposing an approach to develop and implement them safely.

Towards interculturally adaptive conversational AI

Abstract Among the many ways that AI technologies are becoming embedded in our social worlds is the proliferation of Conversational User Interfaces, such as voice assistants (e.g. Apple Siri and Amazon Alexa), chatbots and voice-based conversational agents. Such conversational AI technologies are designed to draw upon the designers’ understanding of interactional practices employed in human–human conversation, and therefore have implications for intercultural communication (ICC). In this paper, we highlight some of the current shortcomings of conversational AI, and how these relate to ICC. We also draw on findings from Conversation Analysis to discuss how pragmatic norms vary across linguacultural groups (see Risager, Karen. 2019. Linguaculture. In Carol A. Chapelle (ed.). Encyclopedia of applied linguistics. Wiley-Blackwell for a discussion of the term ‘linguaculture’), noting that this poses further challenges for designers of conversational AI systems. We argue that the solution is to work towards what we call interculturally adaptive conversational AI. Finally, we propose a framework for how this can be conceptualised and researched, and argue that researchers with expertise in language and ICC are uniquely placed to contribute to this endeavour.

12 Conversational Archetypes for Human-AI Interaction

Artificial Intelligence (AI), once exclusive to sophisticated technological spheres, now plays a transformative role across all aspects of society, driving significant progress and innovation. In this backdrop, basic conversational interface aka chat emerged as the easiest, and the simplest way to interact with AI systems. However, the current Human-AI conversations are fraught with a host of challenges necessitating a critical exploration into their design, approach, and implications. As AI technologies continue to permeate our lives, the need for seamless, intuitive, and human-like conversations is amplified. While our larger research embarks on a research study to suggest a conceptual framework to help design more effective and engaging Human-AI conversations, this paper focuses on a critical aspect that surfaced as a primary gap during our literature review. Conversations are effective and engaging only when their fundamental purpose is identified and understood by their participants. Hence, formulating a purpose driven conversational typology emerged as a key design imperative to inform an array of frameworks that could help create meaningful Human-AI conversations. This study evaluates a dataset of over hundred Human-AI and Human-to-Human conversations, proposing twelve conversational archetypes central to a conceptual framework intended to enhance Human-AI conversations. Employing a hybrid methodology that integrates content analysis with case study research, this paper examines the issue from a human perspective. It aims to provide a useful resource for designers, developers, researchers, and industry professionals who seek to foster deeper connections and trust in human-AI interactions.

Positive Impacts of Chat GPT on English Teachers

The integration of ChatGPT, an AI-driven language model, presents a myriad of benefits for English teachers seeking to enhance their instructional practices. This article explores the advantages afforded by leveraging ChatGPT in educational settings. Firstly, ChatGPT serves as a versatile tool for generating diverse and contextually relevant learning materials, including prompts, quizzes, and writing exercises, tailored to students’ proficiency levels and interests. Secondly, it facilitates personalized feedback by analyzing students’ responses in real-time, identifying areas for improvement, and offering targeted suggestions to foster language acquisition and mastery. Moreover, ChatGPT functions as a virtual assistant, augmenting teachers’ administrative tasks through automated grading, lesson planning support, and curriculum enrichment. Additionally, it fosters interactive and engaging learning experiences through its conversational interface, promoting active student participation and collaboration. Furthermore, ChatGPT can aid in fostering cultural understanding and global awareness by providing access to diverse perspectives and authentic language usage from around the world. Lastly, its continuous learning capabilities enable adaptation to evolving pedagogical needs and linguistic trends, ensuring relevance and effectiveness in English language instruction. In conclusion, the integration of ChatGPT empowers English teachers with innovative tools and resources to create dynamic, personalized, and impactful learning environments, ultimately advancing students’ language proficiency and fluency.

National Implementation of an Artificial Intelligence-Based Virtual Dietitian for Patients With Cancer.

Nutritional status is an established driver of cancer outcomes, but there is an insufficient workforce of registered dietitians to meet patient needs for nutritional counseling. Artificial intelligence (AI) and machine learning (ML) afford the opportunity to expand access to guideline-based nutritional support. An AI-based nutrition assistant called Ina was developed on the basis of a learning data set of >100,000 expert-curated interventions, peer-reviewed literature, and clinical guidelines, and provides a conversational text message-based patient interface to guide dietary habits and answer questions. Ina was implemented nationally in partnership with 25 advocacy organizations. Data on demographics, patient-reported outcomes, and utilization were systematically collected. Between July 2019 and August 2023, 3,310 users from all 50 states registered to use Ina. Users were 73% female; median age was 57 (range, 18-91) years; most common cancer types were genitourinary (22%), breast (21%), gynecologic (19%), GI (14%), and lung (12%). Users were medically complex, with 50% reporting Stage III to IV disease, 37% with metastases, and 50% with 2+ chronic conditions. Nutritional challenges were highly prevalent: 58% had overweight/obese BMIs, 83% reported barriers to good nutrition, and 42% had food allergies/intolerances. Levels of engagement were high: 68% texted questions to Ina; 79% completed surveys; median user retention was 8.8 months; 94% were satisfied with the platform; and 98% found the guidance helpful. In an evaluation of outcomes, 84% used the advice to guide diet; 47% used recommended recipes, 82% felt the program improved quality of life (QoL), and 88% reported improved symptom management. Implementation of an evidence-based AI virtual dietitian is feasible and is reported by patients to be beneficial on diet, QoL, and symptom management. Ongoing evaluations are assessing impact on other outcomes.

Bridging the Gap: a Conversational Interface for Exploring PDF Documents

Our research paper, "Bridging the Gap: A Conversational Interface for Exploring PDF Documents," explores the development and evaluation of a novel conversational interface aimed at enhancing the user experience of exploring PDF documents. This innovative interface provides a user-friendly and efficient way for users to interact with and extract information from PDF documents, potentially revolutionizing how individuals engage with this common file format. Through rigorous design, development, and evaluation processes, we have sought to address the existing limitations in PDF document exploration and contribute valuable insights to the field of conversational interfaces.The chatbot serves as an innovative tool for interacting with PDF files, offering a user-friendly interface to extract information efficiently.The paper outlines the design principles, implementation details, and evaluation results of the GUI PDF chatbot, highlighting its potential impact on user productivity and document accessibility.

Talk2Care: An LLM-based Voice Assistant for Communication between Healthcare Providers and Older Adults

Despite the plethora of telehealth applications to assist home-based older adults and healthcare providers, basic messaging and phone calls are still the most common communication methods, which suffer from limited availability, information loss, and process inefficiencies. One promising solution to facilitate patient-provider communication is to leverage large language models (LLMs) with their powerful natural conversation and summarization capability. However, there is a limited understanding of LLMs' role during the communication. We first conducted two interview studies with both older adults (N=10) and healthcare providers (N=9) to understand their needs and opportunities for LLMs in patient-provider asynchronous communication. Based on the insights, we built an LLM-powered communication system, Talk2Care, and designed interactive components for both groups: (1) For older adults, we leveraged the convenience and accessibility of voice assistants (VAs) and built an LLM-powered conversational interface for effective information collection. (2) For health providers, we built an LLM-based dashboard to summarize and present important health information based on older adults' conversations with the VA. We further conducted two user studies with older adults and providers to evaluate the usability of the system. The results showed that Talk2Care could facilitate the communication process, enrich the health information collected from older adults, and considerably save providers' efforts and time. We envision our work as an initial exploration of LLMs' capability in the intersection of healthcare and interpersonal communication.

Integrating NLP Chatbot into Career Guidance Web Application

Artificial Intelligence (AI) is the development of computer systems that can perform tasks that typically require human intelligence. The development of an advanced web-based chatbot system involves the integration of various technologies and methodologies to create a seamless conversational interface. Leveraging HTML, CSS, and JavaScript for frontend development, alongside Python Flask framework for backend functionality, the project aims to deliver a robust and intuitive user experience. Key to the system's operation is the incorporation of PyTorch for machine learning, allowing for the implementation of sophisticated natural language processing (NLP) techniques. Through tokenization and stemming using NLTK (Natural Language Toolkit), the system enhances its understanding of user queries, enabling it to provide relevant and contextually appropriate responses. At the core of the system lies a supervised learning model trained on a custom dataset compiled from user interactions. This model utilizes bag-of-words representations and neural network architectures to predict responses based on input text. By continuously refining its predictions through feedback mechanisms, the system improves its accuracy and responsiveness over time, ensuring a more tailored and effective user experience. Voice input functionality, facilitated by speech recognition technology, further enhances user interaction by allowing users to communicate with the chatbot using spoken commands. This feature expands the accessibility and convenience of the system, catering to a broader range of users with varying preferences and abilities. In addition to its conversational capabilities, the system prioritizes security and privacy, implementing robust user authentication mechanisms and secure data storage practices. By adhering to industry best practices and standards, the project aims to instill trust and confidence in users regarding the confidentiality and integrity of their data.User interface design and usability are also key considerations in the development process, with careful attention given to creating an intuitive and visually appealing interface. Through thoughtful design choices and user feedback, the system seeks to optimize the user experience and streamline the interaction flow, ensuring that users can easily navigate and utilize its features. Overall, the project endeavors to create an intelligent and user-friendly chatbot system that enhances communication and interaction between users and technology. By leveraging advanced technologies and methodologies, the system aims to provide personalized assistance and support to users, ultimately improving productivity, efficiency, and satisfaction in various domains and applications

Real Time Inventory Management System powered by Generative User Interface

This research explores the developing a real time inventory management system powered by a generative user interface. We are leveraging large language models like GPT4, Claude 3, and Google Gemini that support tool calling or function calling, and integrating it with the modern frontend frameworks like Next js that support streaming React Server Component (RSC), the proposed system enables interaction with the inventory through natural language prompts. We are using PostgreSQL as a choice of database and server actions are used to interact with the database in real time. The system composes and renders appropriate react components based on user prompt, providing a personalized user experience. The research discusses the system's architecture, implementation, and potential impact on inventory management systems. It showcases the potential of Large Language Models (LLMs) and conversational interfaces in enhancing enterprise software user experiences. Key Words: Inventory Management System, Generative User Interface, Generative AI, Large Language Models, Conversational Interface, Natural Language Processing

Artificial intelligence and medical education: application in classroom instruction and student assessment using a pharmacology & therapeutics case study

BackgroundArtificial intelligence (AI) tools are designed to create or generate content from their trained parameters using an online conversational interface. AI has opened new avenues in redefining the role boundaries of teachers and learners and has the potential to impact the teaching-learning process.MethodsIn this descriptive proof-of- concept cross-sectional study we have explored the application of three generative AI tools on drug treatment of hypertension theme to generate: (1) specific learning outcomes (SLOs); (2) test items (MCQs- A type and case cluster; SAQs; OSPE); (3) test standard-setting parameters for medical students.ResultsAnalysis of AI-generated output showed profound homology but divergence in quality and responsiveness to refining search queries. The SLOs identified key domains of antihypertensive pharmacology and therapeutics relevant to stages of the medical program, stated with appropriate action verbs as per Bloom’s taxonomy. Test items often had clinical vignettes aligned with the key domain stated in search queries. Some test items related to A-type MCQs had construction defects, multiple correct answers, and dubious appropriateness to the learner’s stage. ChatGPT generated explanations for test items, this enhancing usefulness to support self-study by learners. Integrated case-cluster items had focused clinical case description vignettes, integration across disciplines, and targeted higher levels of competencies. The response of AI tools on standard-setting varied. Individual questions for each SAQ clinical scenario were mostly open-ended. The AI-generated OSPE test items were appropriate for the learner’s stage and identified relevant pharmacotherapeutic issues. The model answers supplied for both SAQs and OSPEs can aid course instructors in planning classroom lessons, identifying suitable instructional methods, establishing rubrics for grading, and for learners as a study guide. Key lessons learnt for improving AI-generated test item quality are outlined.ConclusionsAI tools are useful adjuncts to plan instructional methods, identify themes for test blueprinting, generate test items, and guide test standard-setting appropriate to learners’ stage in the medical program. However, experts need to review the content validity of AI-generated output. We expect AIs to influence the medical education landscape to empower learners, and to align competencies with curriculum implementation. AI literacy is an essential competency for health professionals.

Optimizing Generative AI Chatbots for Net-Zero Emissions Energy Internet-of-Things Infrastructure

Internet-of-Things (IoT) technologies have been steadily adopted and embedded into energy infrastructure following the rapid transformation of energy grids through distributed consumption, renewables generation, and battery storage. The data streams produced by such energy IoT infrastructure can be extracted, processed, analyzed, and synthesized for informed decision-making that delivers optimized grid operations, reduced costs, and net-zero carbon emissions. However, the voluminous nature of such data streams leads to an equally large number of analysis outcomes that have proven ineffective in decision-making by energy grid operators. This gap can be addressed by introducing artificial intelligence (AI) chatbots, or more formally conversational agents, to proactively assist human operators in analyzing and identifying decision opportunities in energy grids. In this research, we draw upon the recent success of generative AI for optimized AI chatbots with natural language understanding and generation capabilities for the complex information needs of energy IoT infrastructure and net-zero emissions. The proposed approach for optimized generative AI chatbots is composed of six core modules: Intent Classifier, Knowledge Extractor, Database Retriever, Cached Hierarchical Vector Storage, Secure Prompting, and Conversational Interface with Language Generator. We empirically evaluate the proposed approach and the optimized generative AI chatbot in the real-world setting of an energy IoT infrastructure deployed at a large, multi-campus tertiary education institution. The results of these experiments confirm the contribution of generative AI chatbots in simplifying the complexity of energy IoT infrastructure for optimized grid operations and net-zero carbon emissions.

Understanding is a Two-Way Street: User-Initiated Repair on Agent Responses and Hearing in Conversational Interfaces

Although methods for repairing prior turns in natural conversation are critical for enabling mutual understanding, or successful communication, these methods are seldom built into conversational user interfaces systematically. Chatbots and voice assistants tend to ask users to paraphrase what they said if it was not understood, but users cannot do the same if they encounter trouble in understanding what the agent said. Understanding is a one-way street in most (intent-based) conversation-like interfaces. An exception to this is Moore and Arar (2019), who demonstrate nine types of user-initiated repair on agent responses that are common in natural conversation and who have shown that users will employ these repair features correctly in text-based interfaces if taught. In this small-scale study, we test these user-initiated repairs (in second position) in a voice-based interface. With understanding-oriented repairs, we found that participants employed them much the same way in text and voice. In addition, we examine some hearing- and speaking-oriented repairs that emerged from the use of our novel multi-modal interface. We found that participants used them to manage troubles specific to the voice modality. Analysis of user logs and transcripts suggests that user-initiated repair features are valuable components of conversational interfaces.

Conversational AI: An Explication of Few-Shot Learning Problem in Transformers-Based Chatbot Systems

With the recent advancements in conversational artificial intelligence (AI), the practical applications of chatbots have risen significantly in diverse domains such as healthcare, education, e-government, customer support systems, social platforms, and entertainment. The chatbot converses with humans in natural language and responds to their queries with precise and relevant answers. The relevant literature presents several methods for intent classification and slot mapping for chatbot question answering. However, the existing chatbot architectures still suffer from few-shot learning problem (imbalance ratio of class labels over samples) and ineffective dialog management to retain the context and slots mapping. This study aims to introduce the architecture of chatbot by focusing few-shot learning problem and context management in dialog-based conversations. First, to mitigate the few-shot learning problem with chatbots, we propose a novel hybrid intent and slots transformers (HIST) model. The HIST chatbot architecture utilizes transformers and self-attention mechanisms along with bigated recurrent unit and combines conditional random field algorithms for intent classification and slot extraction. Second, to address dialog management, we introduce a hybrid interaction strategy for slots mapping and effective conversational context management. To validate the proposed model’s effectiveness, comprehensive empirical analysis is carried out using three benchmark datasets including airline travel information system (ATIS), banking77, and conversational language interface for natural conversation 150 (CLINC150). The results show that HIST outperforms against the state-of-the-art existing methods with a clear margin and obtained an accuracy of 94.89% and 96.17% for intent classification and slots extraction, respectively. The empirical results confirm the effectiveness of the HIST chatbot for resolving the few-shot learning problem with effective dialog management in chatbot systems.

Multi-Stage Prompting for Next Best Agent Recommendations in Adaptive Workflows

Traditional business processes such as loan processing, order processing, or procurement have a series of steps that are pre-defined at design and executed by enterprise systems. Recent advancements in new-age businesses, however, focus on having adaptive and ad-hoc processes by stitching together a set of functions or steps enabled through autonomous agents. Further, to enable business users to execute a flexible set of steps, there have been works on providing a conversational interface to interact and execute automation. Often, it is necessary to guide the user through the set of possible steps in the process (or workflow). Existing work on recommending the next agent to run relies on historical data. However, with changing workflows and new automation constantly getting added, it is important to provide recommendations without historical data. Additionally, hand-crafted recommendation rules do not scale. The adaptive workflow being a combination of structured and unstructured information, makes it harder to mine. Hence, in this work, we leverage Large Language Models (LLMs) to combine process knowledge with the meta-data of agents to discover NBAs specifically at cold-start. We propose a multi-stage approach that uses existing process knowledge and agent meta-data information to prompt LLM and recommend meaningful next best agent (NBA) based on user utterances.

College Enquiry For Student using AI ChatBot

A chat bot is a computer program that may initiate conversations between users and other computers. A larger audience can use chatbot technology, which is text-based and safe to use.. Chatbots for university research are developed using AI algorithms that interpret user messages and assess user demands. The aims of the chatbot's responses is to match the user's input while avoiding making oneself physically available to the institution in response to queries. The program responds to the students' inquiries by applying its intelligence. For using this type applications, natural processing language, command line, graphical user interface (GUI), menu driven, form-based, etc. that used in user interfaces TGUI and web-based user interfaces are the most typical types, however sometimes another type of user interface is required. This is where a conversational user interface based on chatbots fits in. One type of bot that has been present on chat systems is the chatbot. The user can interact with them via graphical interfaces, and the trend is in this direction. They often offer a stateful service, meaning that each session's data is saved by the application.

Conversation-based hybrid UI for the repertory grid technique: A lab experiment into automation of qualitative surveys

A frequent use of conversational user interfaces (CUIs) today is improving the users’ experience with online quantitative surveys. In this paper, we explore the use of CUIs in qualitative surveys. As a concrete use case, we adopt a specific, well-structured, qualitative research method called the repertory grid technique (RGT). We developed a hybrid user interface (HUI) that combines a graphical user interface (GUI) with a CUI to automate the distinct stages in a RGT survey. A pilot study was used to verify the feasibility of the approach and to fine-tune interface aspects of an initial prototype. In this paper, we report the results of a within-subject lab experiment with 24 participants that aimed to establish the performance and UX in a realistic context of a more advanced prototype. We observed a small decrease in UX in some hedonistic aspects, but also confirmed that the HUI performs similarly to a human agent in most pragmatic aspects. These results provide support for our hypothesis that automating qualitative surveys is possible with proper interface design. We hope that our work can inspire other researchers to design additional tools for qualitative survey automation, especially now that generative AI systems, such as ChatGPT, open up interesting new ways for computer systems to interact with users in natural language.