Showing papers on "Chatbot published in 2020"

Recipes for building an open-domain chatbot

Abstract: Building open-domain chatbots is a challenging area for machine learning research. While prior work has shown that scaling neural models in the number of parameters and the size of the data they are trained on gives improved results, we show that other ingredients are important for a high-performing chatbot. Good conversation requires a number of skills that an expert conversationalist blends in a seamless way: providing engaging talking points and listening to their partners, and displaying knowledge, empathy and personality appropriately, while maintaining a consistent persona. We show that large scale models can learn these skills when given appropriate training data and choice of generation strategy. We build variants of these recipes with 90M, 2.7B and 9.4B parameter models, and make our models and code publicly available. Human evaluations show our best models are superior to existing approaches in multi-turn dialogue in terms of engagingness and humanness measurements. We then discuss the limitations of this work by analyzing failure cases of our models.

The Design and Implementation of XiaoIce, an Empathetic Social Chatbot

Abstract: This article describes the development of Microsoft XiaoIce, the most popular social chatbot in the world. XiaoIce is uniquely designed as an artifical intelligence companion with an emotional conn...

AI-based chatbots in customer service and their effects on user compliance

Abstract: Communicating with customers through live chat interfaces has become an increasingly popular means to provide real-time customer service in many e-commerce settings. Today, human chat service agents are frequently replaced by conversational software agents or chatbots, which are systems designed to communicate with human users by means of natural language often based on artificial intelligence (AI). Though cost- and time-saving opportunities triggered a widespread implementation of AI-based chatbots, they still frequently fail to meet customer expectations, potentially resulting in users being less inclined to comply with requests made by the chatbot. Drawing on social response and commitment-consistency theory, we empirically examine through a randomized online experiment how verbal anthropomorphic design cues and the foot-in-the-door technique affect user request compliance. Our results demonstrate that both anthropomorphism as well as the need to stay consistent significantly increase the likelihood that users comply with a chatbot’s request for service feedback. Moreover, the results show that social presence mediates the effect of anthropomorphic design cues on user compliance.

Chatbots for learning: A review of educational chatbots for the Facebook Messenger

Abstract: With the exponential growth in the mobile device market over the last decade, chatbots are becoming an increasingly popular option to interact with users, and their popularity and adoption are rapidly spreading. These mobile devices change the way we communicate and allow ever-present learning in various environments. This study examined educational chatbots for Facebook Messenger to support learning. The independent web directory was screened to assess chatbots for this study resulting in the identification of 89 unique chatbots. Each chatbot was classified by language, subject matter and developer's platform. Finally, we evaluated 47 educational chatbots using the Facebook Messenger platform based on the analytic hierarchy process against the quality attributes of teaching, humanity, affect, and accessibility. We found that educational chatbots on the Facebook Messenger platform vary from the basic level of sending personalized messages to recommending learning content. Results show that chatbots which are part of the instant messaging application are still in its early stages to become artificial intelligence teaching assistants. The findings provide tips for teachers to integrate chatbots into classroom practice and advice what types of chatbots they can try out.

Challenges in Building Intelligent Open-domain Dialog Systems

Abstract: There is a resurgent interest in developing intelligent open-domain dialog systems due to the availability of large amounts of conversational data and the recent progress on neural approaches to conversational AI [33]. Unlike traditional task-oriented bots, an open-domain dialog system aims to establish long-term connections with users by satisfying the human need for communication, affection, and social belonging. This article reviews the recent work on neural approaches that are devoted to addressing three challenges in developing such systems: semantics, consistency, and interactiveness. Semantics requires a dialog system to not only understand the content of the dialog but also identify users’ emotional and social needs during the conversation. Consistency requires the system to demonstrate a consistent personality to win users’ trust and gain their long-term confidence. Interactiveness refers to the system’s ability to generate interpersonal responses to achieve particular social goals such as entertainment and conforming. The studies we select to present in this survey are based on our unique views and are by no means complete. Nevertheless, we hope that the discussion will inspire new research in developing more intelligent open-domain dialog systems.

A Survey on Conversational Recommender Systems

Abstract: 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 ask questions about the recommendations and to give feedback. The interest in CRS has significantly increased in the past few years. This development is mainly due to the significant progress in the area of natural language processing, the emergence of new voice-controlled home assistants, and the increased use of chatbot technology. With this paper, we provide a detailed survey of existing approaches to conversational recommendation. We categorize these approaches in various dimensions, e.g., in terms of the supported user intents or the knowledge they use in the background. Moreover, we discuss technological approaches, review how CRS are evaluated, and finally identify a number of gaps that deserve more research in the future.

Adoption of AI-based chatbots for hospitality and tourism.

Abstract: This study aims to investigate the customers’ behavioral intention and actual usage (AUE) of artificial intelligence (AI)-powered chatbots for hospitality and tourism in India by extending the technology adoption model (TAM) with context-specific variables.,To understand the customers’ behavioral intention and AUE of AI-powered chatbots for tourism, the mixed-method design was used whereby qualitative and quantitative techniques were combined. A total of 36 senior managers and executives from the travel agencies were interviewed and the analysis of interview data was done using NVivo 8.0 software. A total of 1,480 customers were surveyed and the partial least squares structural equation modeling technique was used for data analysis.,As per the results, the predictors of chatbot adoption intention (AIN) are perceived ease of use, perceived usefulness, perceived trust (PTR), perceived intelligence (PNT) and anthropomorphism (ANM). Technological anxiety (TXN) does not influence the chatbot AIN. Stickiness to traditional human travel agents negatively moderates the relation of AIN and AUE of chatbots in tourism and provides deeper insights into manager’s commitment to providing travel planning services using AI-based chatbots.,This research presents unique practical insights to the practitioners, managers and executives in the tourism industry, system designers and developers of AI-based chatbot technologies to understand the antecedents of chatbot adoption by travelers. TXN is a vital concern for the customers; so, designers and developers should ensure that chatbots are easily accessible, have a user-friendly interface, be more human-like and communicate in various native languages with the customers.,This study contributes theoretically by extending the TAM to provide better explanatory power with human–robot interaction context-specific constructs – PTR, PNT, ANM and TXN – to examine the customers’ chatbot AIN. This is the first step in the direction to empirically test and validate a theoretical model for chatbots’ adoption and usage, which is a disruptive technology in the hospitality and tourism sector in an emerging economy such as India.

"I Hear You, I Feel You": Encouraging Deep Self-disclosure through a Chatbot

Abstract: Chatbots have great potential to serve as a low-cost, effective tool to support people's self-disclosure. Prior work has shown that reciprocity occurs in human-machine dialog; however, whether reciprocity can be leveraged to promote and sustain deep self-disclosure over time has not been systematically studied. In this work, we design, implement and evaluate a chatbot that has self-disclosure features when it performs small talk with people. We ran a study with 47 participants and divided them into three groups to use different chatting styles of the chatbot for three weeks. We found that chatbot self-disclosure had a reciprocal effect on promoting deeper participant self-disclosure that lasted over the study period, in which the other chat styles without self-disclosure features failed to deliver. Chatbot self-disclosure also had a positive effect on improving participants' perceived intimacy and enjoyment over the study period. Finally, we reflect on the design implications of chatbots where deep self-disclosure is needed over time.

Artificial Intelligence Chatbot Behavior Change Model for Designing Artificial Intelligence Chatbots to Promote Physical Activity and a Healthy Diet: Viewpoint

Abstract: Background: Chatbots empowered by artificial intelligence (AI) can increasingly engage in natural conversations and build relationships with users. Applying AI chatbots to lifestyle modification programs is one of the promising areas to develop cost-effective and feasible behavior interventions to promote physical activity and a healthy diet. Objective: The purposes of this perspective paper are to present a brief literature review of chatbot use in promoting physical activity and a healthy diet, describe the AI chatbot behavior change model our research team developed based on extensive interdisciplinary research, and discuss ethical principles and considerations. Methods: We conducted a preliminary search of studies reporting chatbots for improving physical activity and/or diet in four databases in July 2020. We summarized the characteristics of the chatbot studies and reviewed recent developments in human-AI communication research and innovations in natural language processing. Based on the identified gaps and opportunities, as well as our own clinical and research experience and findings, we propose an AI chatbot behavior change model. Results: Our review found a lack of understanding around theoretical guidance and practical recommendations on designing AI chatbots for lifestyle modification programs. The proposed AI chatbot behavior change model consists of the following four components to provide such guidance: (1) designing chatbot characteristics and understanding user background; (2) building relational capacity; (3) building persuasive conversational capacity; and (4) evaluating mechanisms and outcomes. The rationale and evidence supporting the design and evaluation choices for this model are presented in this paper. Conclusions: As AI chatbots become increasingly integrated into various digital communications, our proposed theoretical framework is the first step to conceptualize the scope of utilization in health behavior change domains and to synthesize all possible dimensions of chatbot features to inform intervention design and evaluation. There is a need for more interdisciplinary work to continue developing AI techniques to improve a chatbot’s relational and persuasive capacities to change physical activity and diet behaviors with strong ethical principles.

PLATO-2: Towards Building an Open-Domain Chatbot via Curriculum Learning

Abstract: To build a high-quality open-domain chatbot, we introduce the effective training process of PLATO-2 via curriculum learning. There are two stages involved in the learning process. In the first stage, a coarse-grained generation model is trained to learn response generation under the simplified framework of one-to-one mapping. In the second stage, a fine-grained generative model augmented with latent variables and an evaluation model are further trained to generate diverse responses and to select the best response, respectively. PLATO-2 was trained on both Chinese and English data, whose effectiveness and superiority are verified through comprehensive evaluations, achieving new state-of-the-art results.

Bio-Inspiring Learning Style Chatbot Inventory Using Brain Computing Interface to Increase the Efficiency of E-Learning

Abstract: In recent times Electronic Learning (E-Learning) and Massive Open Online Courses (MOOC) are more popular among the current generation of learners. Coursera, Edx, Simplilearn, Byjus and many other E-Learning service providers are available to deliver various courses. A recent study, in online courses, it has been found by Massachusetts Institute of Technology (MIT) that an astronomical dropout rate of about 96 per cent was found for the last five years. Educational researchers are attempting to decrease the dropout rate of E-Learning courses using various methods. Human Computer Interface (HCI) researchers are attempting to use Brain Computer Interface (BCI) to increase the efficiency of the E-Learning. Beta waves (14-30 Hz) are generated when the learners are more alert. Neil Fleming's VARK (Visual, Auditory, Read and Write and Kinesthetic) questionnaires are used by many researchers to classify the learners. Carl Jung explored that Introverts and Extraverts are the personality traits among the humans. Soomin Kim's study shows that for gathering of quantitative data, Chatbot may be a promising method. The proposed research work in this paper is to find out a correlation between Introvert and Extravert personality types and their learning styles. Initially, modified VARK questionnaires are implemented as a Chatbot to classify individuals as Introverts or Extraverts. After the classifications by the Chatbot, two minutes of visual and auditory contents are given to Introverts and Extraverts and learners' Beta brain waves are recorded and a dataset is created at an interval of one second. The dataset is validated using Machine Learning (ML) algorithms, like Naive Bayes, N48 and Canopy. The proposed method is found to improve the accuracy of classification of learners. Bio-Inspired learning style Brain Computing Interface (BIL-BCI) framework proposed in this paper is a recommendation system to increase the accuracy of the classification among the E-Learners.

Challenges in Chatbot Development: A Study of Stack Overflow Posts

Abstract: Chatbots are becoming increasingly popular due to their benefits in saving costs, time, and effort. This is due to the fact that they allow users to communicate and control different services easily through natural language. Chatbot development requires special expertise (e.g., machine learning and conversation design) that differ from the development of traditional software systems. At the same time, the challenges that chatbot developers face remain mostly unknown since most of the existing studies focus on proposing chatbots to perform particular tasks rather than their development. Therefore, in this paper, we examine the Q&A website, Stack Overflow, to provide insights on the topics that chatbot developers are interested and the challenges they face. In particular, we leverage topic modeling to understand the topics that are being discussed by chatbot developers on Stack Overflow. Then, we examine the popularity and difficulty of those topics. Our results show that most of the chatbot developers are using Stack Overflow to ask about implementation guidelines. We determine 12 topics that developers discuss (e.g., Model Training) that fall into five main categories. Most of the posts belong to chatbot development, integration, and the natural language understanding (NLU) model categories. On the other hand, we find that developers consider the posts of building and integrating chatbots topics more helpful compared to other topics. Specifically, developers face challenges in the training of the chatbot's model. We believe that our study guides future research to propose techniques and tools to help the community at its early stages to overcome the most popular and difficult topics that practitioners face when developing chatbots.

How Do AI-driven Chatbots Impact User Experience? Examining Gratifications, Perceived Privacy Risk, Satisfaction, Loyalty, and Continued Use

Abstract: This study examined how artificial intelligence (AI)-driven chatbots impact user experience. It collected survey data from 1,064 consumers who used any chatbot service from the top 30 brands in the...

Users' experiences with chatbots: findings from a questionnaire study

Abstract: For chatbots to be broadly adopted by users, it is critical that they are experienced as useful and pleasurable. While there is an emerging body of research concerning user uptake and use of chatbots, there is a lack of theoretically grounded studies detailing what constitutes good or poor chatbot user experiences. In this paper, we present findings from a questionnaire study involving more than 200 chatbot users who reported on episodes of chatbot use that they found particularly satisfactory or frustrating. The user reports were analysed with basis in theory on user experience, with particular concern for pragmatic and hedonic attributes. We found that pragmatic attributes such as efficient assistance (positive) and problems with interpretation (negative) were important elements in user reports of satisfactory and frustrating episodes. Hedonic attributes such as entertainment value (positive) and strange and rude responses (negative) were also frequently mentioned. Older participants tended to report on pragmatic attributes more often, whereas younger participants tended to report on hedonic attributes more often. Drawing on the findings, we propose four high-level lessons learnt that may benefit chatbot service providers, and we suggest relevant future research.

Xatkit: A Multimodal Low-Code Chatbot Development Framework

Abstract: Chatbot (and voicebot) applications are increasingly adopted in various domains such as e-commerce or customer services as a direct communication channel between companies and end-users. Multiple frameworks have been developed to ease their definition and deployment. While these frameworks are efficient to design simple chatbot applications, they still require advanced technical knowledge to define complex interactions and are difficult to evolve along with the company needs (e.g. it is typically impossible to change the NL engine provider). In addition, the deployment of a chatbot application usually requires a deep understanding of the targeted platforms, especially back-end connections, increasing the development and maintenance costs. In this paper, we introduce the Xatkit framework. Xatkit tackles these issues by providing a set of Domain Specific Languages to define chatbots (and voicebots and bots in general) in a platform-independent way. Xatkit also comes with a runtime engine that automatically deploys the chatbot application and manages the defined conversation logic over the platforms of choice. Xatkit's modular architecture facilitates the separate evolution of any of its components. Xatkit is open source and fully available online.

Advantages and Constraints of a Hybrid Model K-12 E-Learning Assistant Chatbot

Abstract: E-Learning has become more and more popular in recent years with the advance of new technologies. Using their mobile devices, people can expand their knowledge anytime and anywhere. E-Learning also makes it possible for people to manage their learning progression freely and follow their own learning style. However, studies show that E-Learning can cause the user to experience feelings of isolation and detachment due to the lack of human-like interactions in most E-Learning platforms. These feelings could reduce the user’s motivation to learn. In this paper, we explore and evaluate how well current chatbot technologies assist users’ learning on E-Learning platforms and how these technologies could possibly reduce problems such as feelings of isolation and detachment. For evaluation, we specifically designed a chatbot to be an E-Learning assistant. The NLP core of our chatbot is based on two different models: a retrieval-based model and a QANet model. We designed this two-model hybrid chatbot to be used alongside an E-Learning platform. The core response context of our chatbot is not only designed with course materials in mind but also everyday conversation and chitchat, which make it feel more like a human companion. Experiment and questionnaire evaluation results show that chatbots could be helpful in learning and could potentially reduce E-Learning users’ feelings of isolation and detachment. Our chatbot also performed better than the teacher counselling service in the E-Learning platform on which the chatbot is based.

The impact of chatbot conversational skill on engagement and perceived humanness

Abstract: Conversational agents (CAs)—frequently operationalized as chatbots—are computer systems that leverage natural language processing to engage in conversations with human users. CAs are often operatio...

Conversational Ai: Dialogue Systems, Conversational Agents, and Chatbots

Abstract: This book provides a comprehensive introduction to Conversational AI. While the idea of interacting with a computer using voice or text goes back a long way, it is only in recent years that this idea has become a reality with the emergence of digital personal assistants, smart speakers, and chatbots. Advances in AI, particularly in deep learning, along with the availability of massive computing power and vast amounts of data, have led to a new generation of dialogue systems and conversational interfaces. Current research in Conversational AI focuses mainly on the application of machine learning and statistical data-driven approaches to the development of dialogue systems. However, it is important to be aware of previous achievements in dialogue technology and to consider to what extent they might be relevant to current research and development. Three main approaches to the development of dialogue systems are reviewed: rule-based systems that are handcrafted using best practice guidelines; statistical data-driven systems based on machine learning; and neural dialogue systems based on end-to-end learning. Evaluating the performance and usability of dialogue systems has become an important topic in its own right, and a variety of evaluation metrics and frameworks are described. Finally, a number of challenges for future research are considered, including: multimodality in dialogue systems, visual dialogue; data efficient dialogue model learning; using knowledge graphs; discourse and dialogue phenomena; hybrid approaches to dialogue systems development; dialogue with social robots and in the Internet of Things; and social and ethical issues.

KBot : a Knowledge graph based chatBot for natural language understanding over linked data

Abstract: With the rapid progress of the semantic web, a huge amount of structured data has become available on the web in the form of knowledge bases (KBs). Making these data accessible and useful for end-users is one of the main objectives of chatbots over linked data. Building a chatbot over linked data raises different challenges, including user queries understanding, multiple knowledge base support, and multilingual aspect. To address these challenges, we first design and develop an architecture to provide an interactive user interface. Secondly, we propose a machine learning approach based on intent classification and natural language understanding to understand user intents and generate SPARQL queries. We especially process a new social network dataset (i.e., myPersonality) and add it to the existing knowledge bases to extend the chatbot capabilities by understanding analytical queries. The system can be extended with a new domain on-demand, flexible, multiple knowledge base, multilingual, and allows intuitive creation and execution of different tasks for an extensive range of topics. Furthermore, evaluation and application cases in the chatbot are provided to show how it facilitates interactive semantic data towards different real application scenarios and showcase the proposed approach for a knowledge graph and data-driven chatbot.

Perceiving a Mind in a Chatbot: Effect of Mind Perception and Social Cues on Co-presence, Closeness, and Intention to Use

Abstract: A chatbot equipped with a conversational user interface often allows its users to feel as if they are conversing with a human being. The current study examined whether users’ perception of a mind w...

Designing a Chatbot as a Mediator for Promoting Deep Self-Disclosure to a Real Mental Health Professional

Abstract: Chatbots are becoming increasingly popular. One promising application for chatbots is to elicit people's self-disclosure of their personal experiences, thoughts, and feelings. As receiving one's deep self-disclosure is critical for mental health professionals to understand people's mental status, chatbots show great potential in the mental health domain. However, there is a lack of research addressing if and how people self-disclose sensitive topics to a real mental health professional (MHP) through a chatbot. In this work, we designed, implemented and evaluated a chatbot that offered three chatting styles; we also conducted a study with 47 participants who were randomly assigned into three groups where each group experienced the chatbot's self-disclosure at varying levels respectively. After using the chatbot for a few weeks, participants were introduced to a MHP and were asked if they would like to share their self-disclosed content with the MHP. If they chose to share, the participants had the option of changing (adding, deleting, and editing) the content they self-disclosed to the chatbot. Comparing participants' self-disclosure data the week before and the week after sharing with the MHP, our results showed that, within each group, the depth of participants' self-disclosure to the chatbot remained after sharing with the MHP; participants exhibited deeper self-disclosure to the MHP through a more self-disclosing chatbot; further, through conversation log analysis, we found that some participants made different edits on their self-disclosed content before sharing it with the MHP. Participants' interview and survey feedback suggested an interaction between participants' trust in the chatbot and their trust in the MHP, which further explained participants' self-disclosure behavior.

Managing the human–chatbot divide: how service scripts influence service experience

Abstract: Brands are increasingly considering the use of chatbots to supplement, or even replace, humans in service interactions. Like humans, chatbots can follow certain service scripts in their encounters, which can subsequently determine the customer experience. Service scripts are verbal prescriptions that seek to standardize customer service interactions. However, while the role of service scripts is well documented, despite the increasing use of chatbots as a service mechanism, less is known about the effect, on consumers, of different service scripts presented during chatbot service encounters.,An experimental scenario was developed to test the research hypotheses. Respondents were randomly allocated to scenarios representing a 2 (service interaction: human, chatbot) × 2 (service script: education, entertainment) design. A total of 262 US consumers constituted the final sample for the study.,The findings indicate that when employing an education script, a significant positive effect occurs for human service agents (compared to chatbots) in terms of both satisfaction and purchase intention. These effects are fully mediated by emotion and rapport, showing that the bonds developed through the close proximity to a human service agent elicit emotion and develop rapport, which in turn influence service outcomes. However, this result is present only when an educational script is used.,This paper contributes to the emerging service marketing literature on the use of digital services, in particular chatbots, in service interactions. We show that differences occur in key outcomes dependent on the type of service script employed (education or entertainment). For managers, this study indicates that chatbot interactions can be tailored (in script delivered) in order to maximize emotion and rapport and subsequently consumer purchase intention and satisfaction.

Bot in the Bunch: Facilitating Group Chat Discussion by Improving Efficiency and Participation with a Chatbot

Abstract: Although group chat discussions are prevalent in daily life, they have a number of limitations. When discussing in a group chat, reaching a consensus often takes time, members contribute unevenly to the discussion, and messages are unorganized. Hence, we aimed to explore the feasibility of a facilitator chatbot agent to improve group chat discussions. We conducted a needfinding survey to identify key features for a facilitator chatbot. We then implemented GroupfeedBot, a chatbot agent that could facilitate group discussions by managing the discussion time, encouraging members to participate evenly, and organizing members' opinions. To evaluate GroupfeedBot, we performed preliminary user studies that varied for diverse tasks and different group sizes. We found that the group with GroupfeedBot appeared to exhibit more diversity in opinions even though there were no differences in output quality and message quantity. On the other hand, GroupfeedBot promoted members' even participation and effective communication for the medium-sized group.

Tell Me About Yourself: Using an AI-Powered Chatbot to Conduct Conversational Surveys with Open-ended Questions

Abstract: 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. Our detailed analysis of over 5,200 free-text responses revealed that the chatbot drove a significantly higher level of participant engagement and elicited significantly better quality responses measured by Gricean Maxims in terms of their informativeness, relevance, specificity, and clarity. Based on our results, we discuss design implications for creating AI-powered chatbots to conduct effective surveys and beyond.

Conversation to Automation in Banking Through Chatbot Using Artificial Machine Intelligence Language

Abstract: Artificial Machine Intelligence is a very complicated topic. It involves creating machines that are capable of simulating knowledge. This paper examines some of the latest AI patterns and activities and then provides alternative theory of change in some of the popular and widely accepted postulates of today. Based on basic A.I. (Artificial Intelligence) structuring and working for this, System-Chatbots are made (or chatter bots). The paper shows that A.I is ever improving. As of now there isn't enough information on A.I. however this paper provides a new concept which addresses machine intelligence and sheds light on the potential of intelligent systems. The rise of chatbots in the finance sector is the latest disruptive force that has changed the way customers interact. In the banking industry, the introduction of Artificial Intelligence has driven chatbots and changed the face of the interaction between bank and customers. The banking sector plays an important role in development into any country. It also explores the existing usability of chatbot to assess whether it can fulfill customers ever-changing needs.

Technical aspects of developing chatbots for medical applications: scoping review

Abstract: Background: Chatbots are applications that can conduct natural language conversations with users. In the medical field, chatbots have been developed and used to serve different purposes. They provide patients with timely information that can be critical in some scenarios, such as access to mental health resources. Since the development of the first chatbot, ELIZA, in the late 1960s, much effort has followed to produce chatbots for various health purposes developed in different ways. Objective: This study aimed to explore the technical aspects and development methodologies associated with chatbots used in the medical field to explain the best methods of development and support chatbot development researchers on their future work. Methods: We searched for relevant articles in 8 literature databases (IEEE, ACM, Springer, ScienceDirect, Embase, MEDLINE, PsycINFO, and Google Scholar). We also performed forward and backward reference checking of the selected articles. Study selection was performed by one reviewer, and 50% of the selected studies were randomly checked by a second reviewer. A narrative approach was used for result synthesis. Chatbots were classified based on the different technical aspects of their development. The main chatbot components were identified in addition to the different techniques for implementing each module. Results: The original search returned 2481 publications, of which we identified 45 studies that matched our inclusion and exclusion criteria. The most common language of communication between users and chatbots was English (n=23). We identified 4 main modules: text understanding module, dialog management module, database layer, and text generation module. The most common technique for developing text understanding and dialogue management is the pattern matching method (n=18 and n=25, respectively). The most common text generation is fixed output (n=36). Very few studies relied on generating original output. Most studies kept a medical knowledge base to be used by the chatbot for different purposes throughout the conversations. A few studies kept conversation scripts and collected user data and previous conversations. Conclusions: Many chatbots have been developed for medical use, at an increasing rate. There is a recent, apparent shift in adopting machine learning–based approaches for developing chatbot systems. Further research can be conducted to link clinical outcomes to different chatbot development techniques and technical characteristics.