Human-computer interaction series, Journal Year: 2025, Volume and Issue: unknown, P. 399 - 438
Published: Jan. 1, 2025
Language: Английский
Applied Sciences, Journal Year: 2022, Volume and Issue: 12(17), P. 8427 - 8427
Published: Aug. 24, 2022
Recent advances in Artificial Intelligence (AI) and machine learning have paved the way for increasing adoption of chatbots language learning. Research published to date has mostly focused on chatbot accuracy chatbot–human communication from students’ or in-service teachers’ perspectives. This study aims examine knowledge, level satisfaction perceptions concerning integration conversational AI among future educators. In this mixed method research based convenience sampling, 176 undergraduates two educational settings, Spain (n = 115) Poland 61), interacted autonomously with three agents (Replika, Kuki, Wysa) over a four-week period. A module about was specifically designed research, including an ad hoc model named Chatbot–Human Interaction Satisfaction Model (CHISM), which used by teacher candidates evaluate different linguistic technological features agents. Quantitative qualitative data were gathered through pre-post-survey CHISM TAM2 (technology acceptance) models template analysis (TA), analyzed IBM SPSS 22 QDA Miner software. The yielded positive results regarding learning, particularly relation perceived ease use (PeU) attitudes (AT), but scores behavioral intention (BI) more moderate. findings also unveiled some gender-related differences participants’ design topics interaction.
Language: Английский
Citations
152
Published: Dec. 27, 2022
Large language models have been shown useful in multiple domains including conversational agents, education, and explainable AI.ChatGPT is a large model developed by OpenAI as agent. Being model, ChatGPT trained on massive amounts of data. Clearly, the characteristics data influence ChatGPT's responses. In this paper, we stress surprising bias related to use digits numbers. Namely, show very high correlation between frequency generated humans' favorite numbers, with most frequent digit ChatGPT, matching favorable number, $7$. We also some advantages being agent, discuss its limitations.
Language: Английский
Citations
84
Information Systems Frontiers, Journal Year: 2023, Volume and Issue: 26(2), P. 729 - 754
Published: April 20, 2023
Abstract Conversational agents (CAs) have come a long way from their first appearance in the 1960s to today’s generative models. Continuous technological advancements such as statistical computing and large language models allow for an increasingly natural effortless interaction, well domain-agnostic deployment opportunities. Ultimately, this evolution begs multiple questions: How technical capabilities developed? is nature of work changed through humans’ interaction with conversational agents? has research framed dominant perceptions depictions And what path forward? To address these questions, we conducted bibliometric study including over 5000 articles on CAs. Based systematic analysis keywords, topics, author networks, derive “five waves CA research” that describe past, present, potential future Our results highlight fundamental evolutions theoretical paradigms research. Therefore, discuss moderating role big technologies, novel like OpenAI GPT or BLOOM NLU mark next frontier We contribute theory by laying out central streams research, offer practical implications highlighting design opportunities
Language: Английский
Citations
56
Frontiers in Psychology, Journal Year: 2023, Volume and Issue: 14
Published: March 22, 2023
This mini-review aims to identify major research trends, models, and theories provide specific pedagogical implications for teaching when using chatbots in EFL classes. study follows the guidelines of PRISMA methodology searches open-access empirical studies two reputable databases, Web Science Scopus. The results this confirm findings other studies, which show that present on use university settings focuses their effectiveness, motivation, satisfaction, exposure, assessment. key contribution lies its evaluation chatbot's potential applying integrating existing concepts used learning, such as CEFR, mind mapping, or self-regulatory learning theory. will address gap literature because no previous review has conducted an analysis. Overall, contribute with methods effective environment, be it formal informal.
Language: Английский
Citations
48
Annals of Medicine, Journal Year: 2024, Volume and Issue: 56(1)
Published: March 11, 2024
Background Utilizing artificial intelligence (AI) in chatbots, especially for chronic diseases, has become increasingly prevalent. These AI-powered chatbots serve as crucial tools enhancing patient communication, addressing the rising prevalence of conditions, and meeting growing demand supportive healthcare applications. However, there is a notable gap comprehensive reviews evaluating impact chatbot interventions within academic literature. This study aimed to assess user satisfaction, intervention efficacy, specific characteristics AI architectures systems designed diseases.
Language: Английский
Citations
40
Journal of Medical Internet Research, Journal Year: 2024, Volume and Issue: 26, P. e56930 - e56930
Published: April 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.
Language: Английский
Citations
36
Educational Technology Research and Development, Journal Year: 2025, Volume and Issue: unknown
Published: Jan. 15, 2025
Language: Английский
Citations
2
IEEE Access, Journal Year: 2022, Volume and Issue: 10, P. 92337 - 92356
Published: Jan. 1, 2022
Artificial intelligence is changing the world, especially interaction between machines and humans. Learning interpreting natural languages responding have paved way for many technologies applications. The amalgam of machine learning, deep language processing helped Conversational Intelligence (AI) to change face Human-Computer Interaction (HCI). A conversational agent an excellent example AI, which imitates language. This article presents a sweeping overview agents that includes different techniques such as pattern-based, learning used implement agents. It also discusses panorama tasks in study focuses on how can simulate human behavior by adding emotions, sentiments, affect context. With advancements recent trends rise models, authors review various publicly available datasets unearths research gaps gives insights into future directions.
Language: Английский
Citations
71
Human Behavior and Emerging Technologies, Journal Year: 2022, Volume and Issue: 2022, P. 1 - 23
Published: Sept. 26, 2022
Conversational technologies are transforming the landscape of human-machine interaction. Chatbots increasingly being used in several domains to substitute human agents performing tasks, answering questions, giving advice, and providing social emotional support. Therefore, improving user satisfaction with these is imperative for their successful integration. Researchers leveraging Artificial Intelligence (AI) Natural Language Processing (NLP) techniques impart intelligence capabilities chatbots. This study provides a systematic review research on developing emotionally intelligent We employ approach gather analyze 42 articles published last decade. The aimed at comprehensive analysis past discover problems addressed, used, evaluation measures employed by studies embedding emotion chatbot conversations. study’s findings reveal that most based an open-domain generative architecture. mainly address issue accurately detecting user’s generating relevant responses. Nearly 57% use enhanced Seq2Seq encoding decoding input conversational model. Almost all both automatic manual evaluate chatbots, BLEU measure popular method objective evaluation.
Language: Английский
Citations
62
Data Intelligence, Journal Year: 2023, Volume and Issue: 6(1), P. 240 - 296
Published: Nov. 7, 2023
ABSTRACT This paper investigates the capabilities of ChatGPT as an automated assistant in diverse domains, including scientific writing, mathematics, education, programming, and healthcare. We explore potential to enhance productivity, streamline problem-solving processes, improve writing style. Furthermore, we highlight risks associated with excessive reliance on these fields. These limitations encompass factors like incorrect fictitious responses, inaccuracies code, limited logical reasoning abilities, overconfidence, critical ethical concerns copyright privacy violation. outline areas objectives where proves beneficial, applications it should be used judiciously, scenarios its reliability may limited. In light observed limitations, given that tool's fundamental errors pose a special challenge for non-experts, strategic methodology. By drawing from comprehensive experimental studies, offer methods flowcharts effectively using ChatGPT. Our recommendations emphasize iterative interaction independent verification outputs. Considering importance utilizing judiciously expertise, recommend usage experts who are well-versed respective domains.
Language: Английский
Citations
41