Interacting with educational chatbots: A systematic review

Education and Information Technologies, Год журнала: 2022, Номер 28(1), С. 973 - 1018

Опубликована: Июль 9, 2022

Abstract Chatbots hold the promise of revolutionizing education by engaging learners, personalizing learning activities, supporting educators, and developing deep insight into learners’ behavior. However, there is a lack studies that analyze recent evidence-based chatbot-learner interaction design techniques applied in education. This study presents systematic review 36 papers to understand, compare, reflect on attempts utilize chatbots using seven dimensions: educational field, platform, principles, role chatbots, styles, evidence, limitations. The results show were mainly designed web platform teach computer science, language, general education, few other fields such as engineering mathematics. Further, more than half used teaching agents, while third peer agents. Most predetermined conversational path, quarter utilized personalized approach catered students’ needs, experiential collaborative besides principles. Moreover, evaluated with experiments, primarily point improved subjective satisfaction. Challenges limitations include inadequate or insufficient dataset training reliance usability heuristics. Future should explore effect chatbot personality localization satisfaction effectiveness.

Язык: Английский

---

Privacy-preserving artificial intelligence in healthcare: Techniques and applications

Computers in Biology and Medicine, Год журнала: 2023, Номер 158, С. 106848 - 106848

Опубликована: Апрель 6, 2023

There has been an increasing interest in translating artificial intelligence (AI) research into clinically-validated applications to improve the performance, capacity, and efficacy of healthcare services. Despite substantial worldwide, very few AI-based have successfully made it clinics. Key barriers widespread adoption clinically validated AI include non-standardized medical records, limited availability curated datasets, stringent legal/ethical requirements preserve patients' privacy. Therefore, there is a pressing need improvise new data-sharing methods age that patient privacy while developing applications. In literature, significant attention devoted privacy-preserving techniques overcoming issues hampering actual clinical environment. To this end, study summarizes state-of-the-art approaches for preserving Prominent such as Federated Learning Hybrid Techniques are elaborated along with potential attacks, security challenges, future directions.

Язык: Английский

---

Artificial intelligence empowered conversational agents: A systematic literature review and research agenda

Journal of Business Research, Год журнала: 2023, Номер 161, С. 113838 - 113838

Опубликована: Март 21, 2023

Consumer research on conversational agents (CAs) has been growing. To illustrate and map out in this field, we conducted a systematic literature review (SLR) of published work indexed the Clarivate Web Science Elsevier Scopus databases. Four dominant topical areas were identified through bibliographic coupling. They are 1) consumers’ trust CAs; 2) Natural Language Processing (NLP) developing designing 3) communication with 4) impact CAs value creation for business. We leverage these findings to provide an updated synopsis extant scientific work. Moreover, draw framework whereby identify the: drivers motivators adoption engagement outcomes CA both users organizations. Finally, develop agenda future research.

Язык: Английский

---

Chatbot use cases in the Covid-19 public health response

Journal of the American Medical Informatics Association, Год журнала: 2022, Номер 29(5), С. 1000 - 1010

Опубликована: Янв. 27, 2022

To identify chatbot use cases deployed for public health response activities during the Covid-19 pandemic.We searched PubMed/MEDLINE, Web of Knowledge, and Google Scholar in October 2020 performed a follow-up search July 2021. We screened articles based on their abstracts keywords text, reviewed potentially relevant articles, references to (a) assess whether article met inclusion criteria (b) additional articles. Chatbots, cases, design characteristics were extracted from information other sources by accessing those chatbots that publicly accessible.Our returned 3334 61 our criteria, 30 countries identified. categorized case(s) design. Six categories emerged comprising 15 distinct cases: risk assessment, dissemination, surveillance, post-Covid eligibility screening, distributed coordination, vaccine scheduler. Design-wise, relatively simple, implemented using decision-tree structures predetermined options, focused narrow set simple tasks, presumably due need quick deployment.Chatbots' scalability, wide accessibility, ease use, fast dissemination provide complementary functionality augments workers activities, addressing capacity constraints, social distancing requirements, misinformation. Additional more sophisticated designs, opportunities synergies development should be explored.

Язык: Английский

---

The Use of Artificial Intelligence–Based Conversational Agents (Chatbots) for Weight Loss: Scoping Review and Practical Recommendations

JMIR Medical Informatics, Год журнала: 2022, Номер 10(4), С. e32578 - e32578

Опубликована: Апрель 13, 2022

Background Overweight and obesity have now reached a state of pandemic despite the clinical commercial programs available. Artificial intelligence (AI) chatbots strong potential in optimizing such for weight loss. Objective This study aimed to review AI chatbot use cases loss identify essential components prolonging user engagement. Methods A scoping was conducted using 5-stage framework by Arksey O’Malley. Articles were searched across nine electronic databases (ACM Digital Library, CINAHL, Cochrane Central, Embase, IEEE Xplore, PsycINFO, PubMed, Scopus, Web Science) until July 9, 2021. Gray literature, reference lists, Google Scholar also searched. Results total 23 studies with 2231 participants included evaluated this review. Most (8/23, 35%) focused on promote both healthy diet exercise, 13% (3/23) used solely lifestyle data collection risk assessment whereas only 4% (1/23) promoting combination diet, stress management. In total, 48% (11/23) text-based chatbots, 52% (12/23) operationalized through smartphones, 39% (9/23) integrated collected fitness wearables or Internet Things appliances. The core functions provide personalized recommendations (20/23, 87%), motivational messages (18/23, 78%), gamification (6/23, 26%), emotional support 26%). Study who experienced speech- augmented reality–based interactions addition reported higher engagement because convenience hands-free interactions. Enabling conversations multiple platforms (eg, SMS text messaging, Slack, Telegram, Signal, WhatsApp, Facebook Messenger) devices laptops, Home, Amazon Alexa) increase human semblance verbal nonverbal cues improved interactivity empathy. Other techniques personally culturally appropriate colloquial tones content; emojis that emulate expressions; positively framed words; citations credible information sources; personification; validation; provision real-time, fast, reliable recommendations. Prevailing issues privacy; accountability; burden; interoperability other databases, third-party applications, social media platforms, devices, Conclusions should be designed human-like, personalized, contextualized, immersive, enjoyable enhance experience, engagement, behavior change, These require integration health metrics based self-reports wearable trackers), personality preferences goal achievements), circumstantial behaviors trigger-based overconsumption), states detectors) deliver effective

Язык: Английский

---

Health-focused conversational agents in person-centered care: a review of apps

npj Digital Medicine, Год журнала: 2022, Номер 5(1)

Опубликована: Фев. 17, 2022

Abstract Health-focused apps with chatbots (“healthbots”) have a critical role in addressing gaps quality healthcare. There is limited evidence on how such healthbots are developed and applied practice. Our review of aims to classify types healthbots, contexts use, their natural language processing capabilities. Eligible were those that health-related, had an embedded text-based conversational agent, available English, for free download through the Google Play or Apple iOS store. Apps identified using 42Matters software, mobile app search engine. assessed evaluation framework chatbot characteristics features. The suggests uptake across 33 low- high-income countries. Most patient-facing, interface provide range functions including health education counselling support, assessment symptoms, assistance tasks as scheduling. 78 reviewed focus primary care mental health, only 6 (7.59%) theoretical underpinning, 10 (12.35%) complied information privacy regulations. indicated few use machine learning approaches, despite marketing claims. allowed finite-state input, where dialogue led by system follows predetermined algorithm. Healthbots potentially transformative centering around user; however, they nascent state development require further research development, automation adoption population-level impact.

Язык: Английский

---

Conversational Agent Interventions for Mental Health Problems: Systematic Review and Meta-analysis of Randomized Controlled Trials

Journal of Medical Internet Research, Год журнала: 2023, Номер 25, С. e43862 - e43862

Опубликована: Март 10, 2023

Mental health problems are a crucial global public concern. Owing to their cost-effectiveness and accessibility, conversational agent interventions (CAIs) promising in the field of mental care.

Язык: Английский

---

An Artificial Intelligence Chatbot for Young People’s Sexual and Reproductive Health in India (SnehAI): Instrumental Case Study

Journal of Medical Internet Research, Год журнала: 2022, Номер 24(1), С. e29969 - e29969

Опубликована: Янв. 3, 2022

Leveraging artificial intelligence (AI)-driven apps for health education and promotion can help in the accomplishment of several United Nations sustainable development goals. SnehAI, developed by Population Foundation India, is first Hinglish (Hindi + English) AI chatbot, deliberately designed social behavioral changes India. It provides a private, nonjudgmental, safe space to spur conversations about taboo topics (such as sex family planning) offers accurate, relatable, trustworthy information resources.This study aims use Gibson theory affordances examine SnehAI offer scholarly guidance on how chatbots be used educate adolescents young adults, promote sexual reproductive health, advocate entitlements women girls India.We adopted an instrumental case approach that allowed us explore from perspectives technology design, program implementation, user engagement. We also mix qualitative insights quantitative analytics data triangulate our findings.SnehAI demonstrated strong evidence across fifteen functional affordances: accessibility, multimodality, nonlinearity, compellability, queriosity, editability, visibility, interactivity, customizability, trackability, scalability, glocalizability, inclusivity, connectivity, actionability. effectively engaged its users, especially men, with 8.2 million messages exchanged 5-month period. Almost half incoming were texts deeply personal questions concerns well allied topics. Overall, successfully presented itself trusted friend mentor; curated content was both entertaining educational, natural language processing system worked personalize chatbot response optimize experience.SnehAI represents innovative, engaging, educational intervention enables vulnerable hard-to-reach population groups talk learn sensitive important issues. powerful testimonial vital potential lies technologies good.

Язык: Английский

---

Roles, Users, Benefits, and Limitations of Chatbots in Health Care: Rapid Review

Journal of Medical Internet Research, Год журнала: 2024, Номер 26, С. e56930 - e56930

Опубликована: Апрель 12, 2024

Background Chatbots, or conversational agents, have emerged as significant tools in health care, driven by advancements artificial intelligence and digital technology. These programs are designed to simulate human conversations, addressing various care needs. However, no comprehensive synthesis of chatbots’ roles, users, benefits, limitations is available inform future research application the field. Objective This review aims describe characteristics, focusing on their diverse roles pathway, user groups, limitations. Methods A rapid published literature from 2017 2023 was performed with a search strategy developed collaboration sciences librarian implemented MEDLINE Embase databases. Primary studies reporting chatbot benefits were included. Two reviewers dual-screened results. Extracted data subjected content analysis. Results The categorized into 2 themes: delivery remote services, including patient support, management, education, skills building, behavior promotion, provision administrative assistance providers. User groups spanned across patients chronic conditions well cancer; individuals focused lifestyle improvements; demographic such women, families, older adults. Professionals students also alongside seeking mental behavioral change, educational enhancement. chatbots classified improvement quality efficiency cost-effectiveness delivery. identified encompassed ethical challenges, medicolegal safety concerns, technical difficulties, experience issues, societal economic impacts. Conclusions Health offer wide spectrum applications, potentially impacting aspects care. While they promising for improving quality, integration system must be approached consideration ensure optimal, safe, equitable use.

Язык: Английский

---

Closing the accessibility gap to mental health treatment with a personalized self-referral chatbot

Nature Medicine, Год журнала: 2024, Номер 30(2), С. 595 - 602

Опубликована: Фев. 1, 2024

Язык: Английский

---