Pergantis Pantelis, Bamicha Victoria, Skianis Charalampos, Drigas Athanasios
Net Media Lab & Mind & Brain R&D, Institute of Informatics & Telecommunications, National Centre of Scientific Research 'Demokritos', 153 41 Agia Paraskevi, Greece.
Department of Information & Communication Systems Engineering, University of the Aegean, 832 00 Karlovasi, Greece.
Brain Sci. 2025 Jan 6;15(1):47. doi: 10.3390/brainsci15010047.
: The evolution of digital technology enhances the broadening of a person's intellectual growth. Research points out that implementing innovative applications of the digital world improves human social, cognitive, and metacognitive behavior. Artificial intelligence chatbots are yet another innovative human-made construct. These are forms of software that simulate human conversation, understand and process user input, and provide personalized responses. Executive function includes a set of higher mental processes necessary for formulating, planning, and achieving a goal. The present study aims to investigate executive function reinforcement through artificial intelligence chatbots, outlining potentials, limitations, and future research suggestions. Specifically, the study examined three research questions: the use of conversational chatbots in executive functioning training, their impact on executive-cognitive skills, and the duration of any improvements. : The assessment of the existing literature was implemented using the systematic review method, according to the PRISMA 2020 Principles. The avalanche search method was employed to conduct a source search in the following databases: Scopus, Web of Science, PubMed, and complementary Google Scholar. This systematic review included studies from 2021 to the present using experimental, observational, or mixed methods. It included studies using AI-based chatbots or conversationalists to support executive functions, such as anxiety, stress, depression, memory, attention, cognitive load, and behavioral changes. In addition, this study included general populations with specific neurological conditions, all peer-reviewed, written in English, and with full-text access. However, the study excluded studies before 2021, the literature reviews, systematic reviews, non-AI-based chatbots or conversationalists, studies not targeting the range of executive skills and abilities, studies not written in English, and studies without open access. The criteria aligned with the study objectives, ensuring a focus on AI chatbots and the impact of conversational agents on executive function. The initial collection totaled = 115 articles; however, the eligibility requirements led to the final selection of = 10 studies. : The findings of the studies suggested positive effects of using AI chatbots to enhance and improve executive skills. Although, several limitations were identified, making it still difficult to generalize and reproduce their effects. : AI chatbots are an innovative artificial intelligence tool that can function as a digital assistant for learning and expanding executive skills, contributing to the cognitive, metacognitive, and social development of the individual. However, its use in executive skills training is at a primary stage. The findings highlighted the need for a unified framework for reference and future studies, better study designs, diverse populations, larger sample sizes of participants, and longitudinal studies that observe the long-term effects of their use.
数字技术的发展促进了个人智力成长的拓展。研究指出,实施数字世界的创新应用可改善人类的社交、认知和元认知行为。人工智能聊天机器人是另一种创新的人造工具。它们是模拟人类对话、理解和处理用户输入并提供个性化回复的软件形式。执行功能包括一系列制定、规划和实现目标所需的高级心理过程。本研究旨在探讨通过人工智能聊天机器人强化执行功能,概述其潜力、局限性及未来研究建议。具体而言,该研究考察了三个研究问题:对话式聊天机器人在执行功能训练中的应用、它们对执行认知技能的影响以及任何改善的持续时间。
根据PRISMA 2020原则,采用系统评价方法对现有文献进行评估。采用雪崩搜索法在以下数据库中进行文献检索:Scopus、科学网、PubMed以及补充性的谷歌学术。该系统评价纳入了2021年至今采用实验、观察或混合方法的研究。它包括使用基于人工智能的聊天机器人或对话者来支持执行功能的研究,如焦虑、压力、抑郁、记忆、注意力、认知负荷和行为变化。此外,本研究纳入了有特定神经状况的普通人群,所有研究均经过同行评审、用英文撰写且可获取全文。然而,该研究排除了2021年之前的研究、文献综述、系统评价、非基于人工智能的聊天机器人或对话者、未针对执行技能和能力范围的研究、非英文撰写的研究以及无开放获取的研究。这些标准与研究目标一致,确保专注于人工智能聊天机器人以及对话代理对执行功能的影响。初步收集到115篇文章;然而,根据纳入标准最终选定了10项研究。
研究结果表明,使用人工智能聊天机器人增强和改善执行技能具有积极效果。尽管如此,也发现了一些局限性,这使得仍然难以对其效果进行推广和复制。
人工智能聊天机器人是一种创新的人工智能工具,可作为学习和扩展执行技能的数字助手,有助于个体的认知、元认知和社会发展。然而,其在执行技能训练中的应用尚处于初级阶段。研究结果强调需要一个统一的框架以供参考和未来研究,需要更好的研究设计、多样化的人群、更大规模的参与者样本以及观察其使用长期效果的纵向研究。