Can Artificial Intelligence Automate the Microteaching Evaluation?
Saved in:
| Title: | Can Artificial Intelligence Automate the Microteaching Evaluation? |
|---|---|
| Language: | English |
| Authors: | Nani Hartini, Eka Prihatin, Yayah Rahyasih, Endang Herawan, Nurdin, Destisari Nurbani, Sarah Dzakirah, Song Jiayin |
| Source: | Educational Process: International Journal. Article e2025607 2025 19. |
| Availability: | UNIVERSITEPARK Limited. iTOWER Plaza (No61, 9th floor) Merkez Mh Akar Cd No3, Sisli, Istanbul, Turkey 34382. e-mail: editor@edupij.com; Web site: http://www.edupij.com/ |
| Peer Reviewed: | Y |
| Page Count: | 28 |
| Publication Date: | 2025 |
| Document Type: | Journal Articles Reports - Research |
| Education Level: | Higher Education Postsecondary Education |
| Descriptors: | Artificial Intelligence, Microteaching, Automation, Teacher Evaluation, Video Technology, Evaluation Methods, Technology Uses in Education, College Faculty, Universities, Foreign Countries, Teacher Educators, Teacher Attitudes, Models |
| Geographic Terms: | Indonesia (Jakarta), Indonesia |
| ISSN: | 2147-0901 2564-8020 |
| Abstract: | Purpose: This study aims to describe how automation works in microteaching evaluation by an Artificial Intelligence (AI)-based application through video analysis. Background: The rapid integration of Artificial Intelligence (AI) into education has transformed assessment and teacher training practices. However, most existing AI applications in microteaching focus on providing feedback or assisting instruction, rather than functioning as autonomous evaluators. This gap underscores the need to understand how automation can systematically operate in evaluating microteaching performance through video analysis, bridging technological capability with pedagogical interpretation. Method: A qualitative approach was used to elaborate on the explanations of 9 participants selected purposively -- including learning experts and AI technology practitioners. In-depth semi-structured interviews were adopted -- using instruments curated by education research experts. Thematic analysis techniques, formulated into 6 steps with Nvivo support, were utilized. Results: The research findings indicate that the process consists of 8 steps. A dataset of human facial expressions and voice intonations embedded into the AI-based application enables the application to identify and categorize students' reactions to learning. This categorization is projected by the adoption and integration of convolutional neural network (CNN) and recurrent neural network (RNN) systems, which can analyze students' verbal and non-verbal aspects in microteaching videos based on the dataset. Conclusions: The study revealed that automation in microteaching evaluation operates through an eight-stage workflow integrating CNN and RNN systems. This model enables consistent and objective assessment of multimodal cues and offers a replicable foundation for AI-driven teacher evaluation. Further validation through quasi-experimental research is recommended. |
| Abstractor: | As Provided |
| Entry Date: | 2026 |
| Accession Number: | EJ1493869 |
| Database: | ERIC |
| Abstract: | Purpose: This study aims to describe how automation works in microteaching evaluation by an Artificial Intelligence (AI)-based application through video analysis. Background: The rapid integration of Artificial Intelligence (AI) into education has transformed assessment and teacher training practices. However, most existing AI applications in microteaching focus on providing feedback or assisting instruction, rather than functioning as autonomous evaluators. This gap underscores the need to understand how automation can systematically operate in evaluating microteaching performance through video analysis, bridging technological capability with pedagogical interpretation. Method: A qualitative approach was used to elaborate on the explanations of 9 participants selected purposively -- including learning experts and AI technology practitioners. In-depth semi-structured interviews were adopted -- using instruments curated by education research experts. Thematic analysis techniques, formulated into 6 steps with Nvivo support, were utilized. Results: The research findings indicate that the process consists of 8 steps. A dataset of human facial expressions and voice intonations embedded into the AI-based application enables the application to identify and categorize students' reactions to learning. This categorization is projected by the adoption and integration of convolutional neural network (CNN) and recurrent neural network (RNN) systems, which can analyze students' verbal and non-verbal aspects in microteaching videos based on the dataset. Conclusions: The study revealed that automation in microteaching evaluation operates through an eight-stage workflow integrating CNN and RNN systems. This model enables consistent and objective assessment of multimodal cues and offers a replicable foundation for AI-driven teacher evaluation. Further validation through quasi-experimental research is recommended. |
|---|---|
| ISSN: | 2147-0901 2564-8020 |
