The implementation of the cognitive theory of multimedia learning in the design and evaluation of an AI educational video assistant utilizing large language models
The integration of Artificial Intelligence (AI) holds immense potential for revolutionizing education; especially, in contexts where multimodal learning experiences are designed. This paper investigated the potential benefits of Generative Artificial Intelligence (AI) in education, concentrating on...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2024-02-01
|
| Series: | Heliyon |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2405844024013926 |
| _version_ | 1797304456617918464 |
|---|---|
| author | Rana AlShaikh Norah Al-Malki Maida Almasre |
| author_facet | Rana AlShaikh Norah Al-Malki Maida Almasre |
| author_sort | Rana AlShaikh |
| collection | DOAJ |
| description | The integration of Artificial Intelligence (AI) holds immense potential for revolutionizing education; especially, in contexts where multimodal learning experiences are designed. This paper investigated the potential benefits of Generative Artificial Intelligence (AI) in education, concentrating on the design and evaluation of an AI Educational Video Assistant tailored for multimodal learning experiences. The tool, utilizing the principles of the Cognitive Theory of Multimedia Learning (CTML), comprises three modules: Transcription, Engagement, and Reinforcement, each focusing on distinct aspects of the learning process. It Integraties Automatic Speech Recognition (ASR) using OpenAI's Whisper and Google's Large Language Model (LLM) Bard. Our twofold objective includes both the development of this AI assistant tool and the assessment of its effect on improving the learning experiences. For the evaluation, a mixed methods approach was adopted, combining human evaluation by nine educational experts with automatic metrics. Participants provided their perceptions on the tool's effectiveness in terms of engagement, content organization, clarity, and usability. Additionally, automatic metrics including Content Distinctiveness and Readability scores were computed. The results from the human evaluation suggest positive impacts across all assessed domains. The automatic metrics further proved the tool's ability in content generation and readability. Collectively, these preliminary results highlight the tool's potential to revolutionize educational design and provide personalized and engaging learning experiences. |
| first_indexed | 2024-03-08T00:09:47Z |
| format | Article |
| id | doaj.art-073571e8432845608081d6e77bb27ee0 |
| institution | Directory Open Access Journal |
| issn | 2405-8440 |
| language | English |
| last_indexed | 2024-03-08T00:09:47Z |
| publishDate | 2024-02-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Heliyon |
| spelling | doaj.art-073571e8432845608081d6e77bb27ee02024-02-17T06:40:50ZengElsevierHeliyon2405-84402024-02-01103e25361The implementation of the cognitive theory of multimedia learning in the design and evaluation of an AI educational video assistant utilizing large language modelsRana AlShaikh0Norah Al-Malki1Maida Almasre2Faculty of Computing and Information Technology, Department of Information Systems, King Abdulaziz University, Rabigh, 21911, Saudi Arabia; Corresponding author.Faculty of Arts and Humanities, Modern Languages and Literatures Department, King Abdulaziz University, Jeddah, Saudi ArabiaFaculty of Computing and Information Technology, Department of Information Technology, King Abdulaziz University, Jeddah, 21589, Saudi ArabiaThe integration of Artificial Intelligence (AI) holds immense potential for revolutionizing education; especially, in contexts where multimodal learning experiences are designed. This paper investigated the potential benefits of Generative Artificial Intelligence (AI) in education, concentrating on the design and evaluation of an AI Educational Video Assistant tailored for multimodal learning experiences. The tool, utilizing the principles of the Cognitive Theory of Multimedia Learning (CTML), comprises three modules: Transcription, Engagement, and Reinforcement, each focusing on distinct aspects of the learning process. It Integraties Automatic Speech Recognition (ASR) using OpenAI's Whisper and Google's Large Language Model (LLM) Bard. Our twofold objective includes both the development of this AI assistant tool and the assessment of its effect on improving the learning experiences. For the evaluation, a mixed methods approach was adopted, combining human evaluation by nine educational experts with automatic metrics. Participants provided their perceptions on the tool's effectiveness in terms of engagement, content organization, clarity, and usability. Additionally, automatic metrics including Content Distinctiveness and Readability scores were computed. The results from the human evaluation suggest positive impacts across all assessed domains. The automatic metrics further proved the tool's ability in content generation and readability. Collectively, these preliminary results highlight the tool's potential to revolutionize educational design and provide personalized and engaging learning experiences.http://www.sciencedirect.com/science/article/pii/S2405844024013926Large language modelsCognitive theory of multimedia learningEducational videoASRGoogle's bard |
| spellingShingle | Rana AlShaikh Norah Al-Malki Maida Almasre The implementation of the cognitive theory of multimedia learning in the design and evaluation of an AI educational video assistant utilizing large language models Heliyon Large language models Cognitive theory of multimedia learning Educational video ASR Google's bard |
| title | The implementation of the cognitive theory of multimedia learning in the design and evaluation of an AI educational video assistant utilizing large language models |
| title_full | The implementation of the cognitive theory of multimedia learning in the design and evaluation of an AI educational video assistant utilizing large language models |
| title_fullStr | The implementation of the cognitive theory of multimedia learning in the design and evaluation of an AI educational video assistant utilizing large language models |
| title_full_unstemmed | The implementation of the cognitive theory of multimedia learning in the design and evaluation of an AI educational video assistant utilizing large language models |
| title_short | The implementation of the cognitive theory of multimedia learning in the design and evaluation of an AI educational video assistant utilizing large language models |
| title_sort | implementation of the cognitive theory of multimedia learning in the design and evaluation of an ai educational video assistant utilizing large language models |
| topic | Large language models Cognitive theory of multimedia learning Educational video ASR Google's bard |
| url | http://www.sciencedirect.com/science/article/pii/S2405844024013926 |
| work_keys_str_mv | AT ranaalshaikh theimplementationofthecognitivetheoryofmultimedialearninginthedesignandevaluationofanaieducationalvideoassistantutilizinglargelanguagemodels AT norahalmalki theimplementationofthecognitivetheoryofmultimedialearninginthedesignandevaluationofanaieducationalvideoassistantutilizinglargelanguagemodels AT maidaalmasre theimplementationofthecognitivetheoryofmultimedialearninginthedesignandevaluationofanaieducationalvideoassistantutilizinglargelanguagemodels AT ranaalshaikh implementationofthecognitivetheoryofmultimedialearninginthedesignandevaluationofanaieducationalvideoassistantutilizinglargelanguagemodels AT norahalmalki implementationofthecognitivetheoryofmultimedialearninginthedesignandevaluationofanaieducationalvideoassistantutilizinglargelanguagemodels AT maidaalmasre implementationofthecognitivetheoryofmultimedialearninginthedesignandevaluationofanaieducationalvideoassistantutilizinglargelanguagemodels |