Conversational practice, while crucial for all language learners, can be challenging to get enough of and very expensive. Chatbots are computer programs developed to engage in conversations with humans. They are designed as software avatars with limited, but growing conversational capability. The most natural and potentially powerful application of chatbots is in line with their fundamental nature - language practice. However, their role and outcomes within (in)formal language learning are currently tangential at best. Existing research in the area has generally focused on chatbots' comprehensibility and the motivation they inspire in their users. In this paper, we provide an overview of the chatbots for learning languages, critically analyze existing approaches, and discuss the major challenges for future work.
University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；Juji. Inc.（Juji公司）；IBM Research AI（IBM研究AI部门）；University of California, Irvine（加利福尼亚大学欧文分校）
The rise of increasingly more powerful chatbots offers a new way to collect information through conversational surveys, where a chatbot asks open-ended questions, interprets a user's free-text responses, and probes answers whenever needed. To investigate the effectiveness and limitations of such a chatbot in conducting surveys, we conducted a field study involving about 600 participants. In this study with mostly open-ended questions, half of the participants took a typical online survey on Qualtrics and the other half interacted with an AI-powered chatbot to complete a conversational survey. …
Conversational interfaces are currently on the rise: more and more applications rely on a chat-like interaction pattern to increase their acceptability and to improve user experience. Also in the area of questionnaire design and administration, interaction design is increasingly looked at as an important ingredient of a digital solution. For those reasons, we designed and developed a conversational survey tool to administer questionnaires with a colloquial form through a chat-like Web interface. In this paper, we present the evaluation results of our approach, taking into account both the user…
Neurodevelopmental Disorders (NDD) are a group of conditions with onset in the developmental period characterized by deficits in the cognitive and social areas. Conversational agents have been increasingly explored to support therapeutic interventions for people with NDD. This survey provides a structured view of the crucial design features of these systems, the types of therapeutic goals they address, and the empirical methods adopted for their evaluation. From this analysis, we elaborate a set of recommendations and highlight the gaps left unsolved in the state of the art, upon which we grou…
University of Klagenfurt（克拉根福大学）；Hong Kong Baptist University（香港浸会大学）
Recommender systems are software applications that help users to find items of interest in situations of information overload. Current research often assumes a one-shot interaction paradigm, where the users' preferences are estimated based on past observed behavior and where the presentation of a ranked list of suggestions is the main, one-directional form of user interaction. Conversational recommender systems (CRS) take a different approach and support a richer set of interactions. These interactions can, for example, help to improve the preference elicitation process or allow the user to as…
Intelligent conversational agents and virtual assistants, such as chatbots and voice assistants, have the potential of augmenting health service capacity to screen symptoms and deliver healthcare interventions. In this paper, we developed voice-based conversational agents (VCAs) in the Google Actions Console to deliver periodic self-assessment health surveys. The focus of this paper is to accommodate self-monitoring for patients with specific fluid consumption requirements or sleep disorders. Our VCAs, named FluidMonitor and Sleepy, have been tested to integrate naturally into a patient's dail…
A Survey on LLM-based Conversational User Simulation
Vanderbilt University（范德比大学）；Adobe Research（Adobe研究）；Yale University（耶鲁大学）；University of Oregon（俄勒冈大学）；University of California San Diego（加州大学圣地亚哥分校）；Dolby Laboratories（Dolby实验室）；University of California, Berkeley（加州大学伯克利分校）；Cisco AI Research（思科人工智能研究）；University of Southern California（南加州大学）；Texas A&M University（德克萨斯阿姆斯特朗大学）；UC Davis（加州大学戴维斯分校）
We present the first systematic analysis of personality dimensions developed specifically to describe the personality of speech-based conversational agents. Following the psycholexical approach from psychology, we first report on a new multi-method approach to collect potentially descriptive adjectives from 1) a free description task in an online survey (228 unique descriptors), 2) an interaction task in the lab (176 unique descriptors), and 3) a text analysis of 30,000 online reviews of conversational agents (Alexa, Google Assistant, Cortana) (383 unique descriptors). We aggregate the results…
The use of tangible interfaces in teaching has been proved more effective, user -friendly and helpful in collaborative learning departments, when compared to traditional teaching approaches. In particular, the tangible interface "Makey Makey"is a modern tool that enhances collaboration between pupils, with positive results in education, despite the limited research done on this interface so far. "Makey Makey" succeeds in motivating and engaging young learners in the learning process, showing better performance and scoring results. In addition, its use in teaching has been shown to benefit the …
Assessing the Feasibility of a Video-Based Conversational Chatbot Survey for Measuring Perceived Cycling Safety: A Pilot Study in New York City
Center for Urban Science + Progress, Tandon School of Engineering, New York University（纽约大学坦登工程学院城市科学与工程中心）；School of Geography, University of Leeds（利兹大学地理学院）；Department of Technology of Management and Innovation, Tandon School of Engineering, New York University（纽约大学坦登工程学院技术、管理与创新系）；Department of Urban and Regional Planning, College of Design, Construction and Planning, University of Florida（佛罗里达大学设计、建造与规划学院城市规划与区域规划系）
The conversational nature of chatbots poses challenges to designers since their development is different from other software and requires investigating new practices in the context of human-AI interaction and their impact on user experience. Therefore, this work aims to unveil chatbot conversational practices alongside their impacts on users to build a web guide to support designers while conceiving conversations for chatbots. We have carried out a Systematic Literature Review (SLR) to identify linguist, visual, and interactive elements used in chatbot conversational design. The SLR resulted i…
Factors That Influence the Adoption of AI-enabled Conversational Agents (AICAs) as an Augmenting Therapeutic Tool by Frontline Healthcare Workers: From Technology Acceptance Model 3 (TAM3) Lens -- A Systematic Mapping Review
Building conversational agents have many technical, design and linguistic challenges. Other more complex elements include using emotionally intelligent conversational agent to build trust with the individuals. In this chapter, we introduce the nature of conversational user interfaces (CUIs) for health and describe UX design principles informed by a systematic literature review of relevant research works. We analyze scientific literature in conversational interfaces and chatterbots, providing a survey of major studies and describing UX design principles and interaction patterns.
The increasingly collaborative decision-making process between humans and agents demands a comprehensive, continuous, and unobtrusive measure of trust in agents. The gold standard format for measuring trust, a Likert-style survey, suffers from major limitations in dynamic human-agent interactions. We proposed a new approach to evaluate trust in a nondirective and relational conversation. The term nondirective refers to abstract word selections in open-ended prompts, which can probe respondents to freely describe their attitudes. The term relational refers to interactive conversations where res…
Visual appearance is an important aspect influencing the perception and consequent acceptance of Embodied Conversational Agents (ECA). To this end, the Uncanny Valley theory contradicts the common assumption that increased humanization of characters leads to better acceptance. Rather, it shows that anthropomorphic behavior may trigger feelings of eeriness and rejection in people. The work presented in this paper explores whether four different autonomous ECAs, specifically build for a European research project, are affected by this effect, and how they compare to two slightly more realisticall…
The human papillomavirus (HPV) vaccine is the most effective way to prevent HPV-related cancers. Integrating provider vaccine counseling is crucial to improving HPV vaccine completion rates. Automating the counseling experience through a conversational agent could help improve HPV vaccine coverage and reduce the burden of vaccine counseling for providers. In a previous study, we tested a simulated conversational agent that provided HPV vaccine counseling for parents using the Wizard of OZ protocol. In the current study, we assessed the conversational agent among young college adults (n=24), a …
Seeking Late Night Life Lines: Experiences of Conversational AI Use in Mental Health Crisis
University of Minnesota（明尼苏达大学）；Northwestern University（西北大学）；Dartmouth College（达特茅斯学院）；Microsoft（微软）；Mental Health America（心理健康美国）；Microsoft Research（微软研究院）
From Lived Experience to Insight: Unpacking the Psychological Risks of Using AI Conversational Agents
School of Interactive Computing, Georgia Institute of Technology（交互计算学院，佐治亚理工学院）；Purdue University（普渡大学）；Microsoft Research（微软研究院）；Microsoft（微软）；Microsoft AI（微软人工智能）；University of Toronto（多伦多大学）
The article proposes a system for knowledge-based conversation designed for Social Robots and other conversational agents. The proposed system relies on an Ontology for the description of all concepts that may be relevant conversation topics, as well as their mutual relationships. The article focuses on the algorithm for Dialogue Management that selects the most appropriate conversation topic depending on the user's input. Moreover, it discusses strategies to ensure a conversation flow that captures, as more coherently as possible, the user's intention to drive the conversation in specific dir…
UNED（西班牙国立远程教育大学）；Université Paris-Saclay（巴黎萨克雷大学）；CNRS（法国国家科学研究中心）；LIMSI（法国计算机科学与自动化研究所）；Zurich University of Applied Sciences (ZHAW)（苏黎世应用科技大学）
In this paper we survey the methods and concepts developed for the evaluation of dialogue systems. Evaluation is a crucial part during the development process. Often, dialogue systems are evaluated by means of human evaluations and questionnaires. However, this tends to be very cost and time intensive. Thus, much work has been put into finding methods, which allow to reduce the involvement of human labour. In this survey, we present the main concepts and methods. For this, we differentiate between the various classes of dialogue systems (task-oriented dialogue systems, conversational dialogue …
With the emergence of conversational artificial intelligence (AI) agents, it is important to understand the mechanisms that influence users' experiences of these agents. We study a common tool in the designer's toolkit: conceptual metaphors. Metaphors can present an agent as akin to a wry teenager, a toddler, or an experienced butler. How might a choice of metaphor influence our experience of the AI agent? Sampling metaphors along the dimensions of warmth and competence---defined by psychological theories as the primary axes of variation for human social perception---we perform a study (N=260)…
Institut Polytechnique de Paris（巴黎理工学院）；Carnegie Mellon University（卡内基梅隆大学）；Inria Paris（法国国家信息与自动化研究所巴黎分部）
Some exciting new approaches to neural architectures for the analysis of conversation have been introduced over the past couple of years. These include neural architectures for detecting emotion, dialogue acts, and sentiment polarity. They take advantage of some of the key attributes of contemporary machine learning, such as recurrent neural networks with attention mechanisms and transformer-based approaches. However, while the architectures themselves are extremely promising, the phenomena they have been applied to to date are but a small part of what makes conversation engaging. In this pape…
History of generative Artificial Intelligence (AI) chatbots: past, present, and future development
University of Massachusetts Lowell（马萨诸塞大学洛厄尔分校）；Asian University of Bangladesh（亚洲孟加拉大学）；Sonargaon University（索纳尔冈大学）；Babes-Bolyai University（巴比什-博雅依大学）；Islamic University（伊斯兰大学）；University of Chittagong（吉大港大学）
