Effects of Artificial Intelligence-Powered Virtual Agents on Learning Outcomes in Computer-Based Simulations: A Meta-Analysis

Dai, Chih-Pu; Ke, Fengfeng; Pan, Yanjun; Moon, Jewoong; Liu, Zhichun

doi:10.1007/s10648-024-09855-4

Cited by 7 publications

(4 citation statements)

References 106 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Current LLMs like GPT-4 can understand and respond in more than 50 languages, and automatic speech recognition of user input and text-to-speech for synthetic voice output are also available for many languages. Other key applications include teaching science and engineering (Chan et al, 2023;Dai et al, 2024) and tutoring for individual learning difficulties (Johnson & Lester, 2016). In the contexts mentioned, AI-based avatars could generate suitable tasks for learners and adapt to their difficulty level.…”

Section: Individualized Instructionmentioning

confidence: 99%

“…Immersive learning refers to the use of virtual, augmented, and mixed reality to create a deeply engaging and authentic learning experience. A recent meta-analysis reported that only 19 AI-BASED AVATARS: BENEFITS AND CHALLENGES 9 studies using AI-based avatars in the context of immersive learning are available (Dai et al, 2024). Most of these studies were conducted before the recent advances in generative AI.…”

Section: Immersive Learningmentioning

confidence: 99%

“…To date, few empirical findings are available on adaptive scaffolding with modern AI-based avatars. Most of the available studies either used static pedagogical agents without authentic animations and voice output or did not employ current generative AI models (Chien et al, 2024;Dai et al, 2024;Wu & Yu, 2024). Therefore, we now describe the results known for scaffolding in various forms of e-learning.…”

Section: Scaffoldingmentioning

confidence: 99%

See 2 more Smart Citations

AI-Based Avatars Are Changing the Way We Learn and Teach: Benefits and Challenges

Fink,

Robinson,

Ertl

2024

Preprint

View full text Add to dashboard Cite

Advancements in the generative AI field have enabled the development of powerful educational avatars. These avatars can, for instance, listen to users’ spoken input, generate an answer utilizing a large-language model, and reply by speaking with a synthetic voice. A theoretical introduction summarizes essential steps in developing AI-based educational avatars and explains how they differ from previously available educational technologies. Moreover, we introduce GPTAvatar, an open-source, state-of-the-art AI-based avatar. We then discuss the benefits of using educational AI-based avatars, which include, among other things, individualized and contextualized instruction. Afterward, we highlight the challenges of using AI-based educational avatars. Major problems concern incorrect and inaccurate information provided, as well as insufficient data protection. In the discussion, we provide an outlook by addressing advances in educational content and educational technology and identifying three crucial open questions for research and practice.

show abstract

Section: Individualized Instructionmentioning

confidence: 99%

Section: Immersive Learningmentioning

confidence: 99%

Section: Scaffoldingmentioning

confidence: 99%

See 1 more Smart Citation

AI-Based Avatars Are Changing the Way We Learn and Teach: Benefits and Challenges

Fink,

Robinson,

Ertl

2024

Preprint

View full text Add to dashboard Cite

show abstract

“…However, if the audio quality is poor or the narration lacks coherence, it can become a distraction rather than a help to learning . The inconsistent effects of these factors highlight the importance of individualized learning approaches that take into account the unique needs and preferences of learners (Dai et al, 2024). Educators and instructional designers should consider how ethnicity, prior knowledge, images, audios, visuals, and narration intersect to influence learning outcomes (Zhao et al, 2023).…”

Section: Ethnicity Prior Knowledge Image Audios Visuals and Narrationmentioning

confidence: 99%

Examining and Visualizing the Effects of Pedagogical Agents on Learning Outcomes

Lou,

Yang

2024

International Journal of E-Collaboration

View full text Add to dashboard Cite

While there has been a growing interest in the use of animated, interactive, and embodied agents in education, there is a lack of comprehensive understanding of their impact on learning outcomes. To comprehensively examine their impact on learning outcomes, this study utilized VOSviewer and CitNetExplorer for a bibliometric analysis, examining the research trends in the field of pedagogical agents for learning. The top 10 cited authors, sources, organizations, and countries in this field were identified. The findings indicate that animated, interactive, and embodied pedagogical agents may enhance learning outcomes. Furthermore, ethnicity and prior knowledge are significant factors in influencing learning outcomes. The integration of image, audio, visuals, and narration within these agents can positively impact learning outcomes, creating a more immersive and engaging learning experience. The ethical and social implications of pedagogical agents cannot be overlooked in the future research.

show abstract

Beyond inquiry or direct instruction: Pressing issues for designing impactful science learning opportunities

de Jong,

Lazonder,

Chinn

et al. 2024

Educational Research Review

View full text Add to dashboard Cite

Effects of Artificial Intelligence-Powered Virtual Agents on Learning Outcomes in Computer-Based Simulations: A Meta-Analysis

Cited by 7 publications

References 106 publications

AI-Based Avatars Are Changing the Way We Learn and Teach: Benefits and Challenges

AI-Based Avatars Are Changing the Way We Learn and Teach: Benefits and Challenges

Examining and Visualizing the Effects of Pedagogical Agents on Learning Outcomes

Beyond inquiry or direct instruction: Pressing issues for designing impactful science learning opportunities

Contact Info

Product

Resources

About