EUVIMEDEUVIMED entdecken
ValidierungsstudieOpen Access · CC BY-NC 4.0

Development and initial validation of a video-mediated listening test based on multimodal generative AI

Ting Yin, Jiexin Chen, Tong Yao, Zhiqing Lin

Acta Psychologica · 2026

DOI: 10.1016/j.actpsy.2026.106521 ↗

Kurz gefasst

Validierungsstudie in der Zeitschrift Acta Psychologica, 2026. Verfasst von Ting Yin und 3 weiteren Autor:innen. Beteiligte Einrichtung: School of Foreign Languages, Guangdong Polytechnic Normal University, 293 Zhongshan Avenue West, Guangzhou, 510665, China. Electronic address: yintin…. Hauptthemen laut MEDLINE: Psychometrics, Video Recording. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 121 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: Guangdong Polytechnic Normal University, National Social Science Fund of China, University of Macau.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Video-mediated listening has been recognized for its potential to facilitate learners' comprehension, engagement, and motivation by providing richer contextual cues and audiovisual input. However, the development of authentic listening assessments typically requires substantial time and financial resources, which hinders their practical implementation. This study aims to address these challenges by applying generative AI to develop a video-mediated listening assessment. Multimodal generative AI (InVideo) was employed to create four videos, while GPT-4 was used to automatically generate 20 test items targeting five listening subskills. A total of 542 university students completed the AI-based video-mediated listening assessment within 30 min, followed by a questionnaire. Additionally, five students and five teachers were selected for semi-structured interviews. Results from psychometric models showed that 19 out of 20 items effectively measured five targeted listening subskills, with appropriate item difficulty and discrimination, confirming construct validity. The questionnaire suggested that the AI-generated videos were adequate in terms of audio, visual, and audio-visual consistency, providing support for the relevance and utility of the test. Questionnaires and semi-structured interviews indicated that video-mediated listening seemed to improve students' listening ability and enhance their interest, motivation, and engagement compared to audio-based methods, while teachers reported that multimodal AI reduced the emotional labor of preparing audiovisual materials in language teaching, supporting the assessment's positive consequences. The fundamental validity considerations of AI-based video-mediated listening assessment and implications for language learning and teaching were discussed.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

PsychometricsVideo RecordingHumansFemaleGenerative Artificial IntelligenceMaleYoung AdultAdultSurveys and QuestionnairesStudentsComprehension

Stichwörter der Autor:innen

AI-enhanced listening assessmentGenerative AIPsychometric validationValidityVideo-mediated listening assessment

Autor:innen und Institutionen

  • School of Foreign Languages, Guangdong Polytechnic Normal University, 293 Zhongshan Avenue West, Guangzhou, 510665, China. Electronic address: yinting@gpnu.edu.cn.
  • School of Foreign Languages, Neusoft Institute of Guangdong, Foshan, 528000, China. Electronic address: chenjiexin@nuit.edu.cn.
  • Center for Linguistics and Applied Linguistics, Guangdong University of Foreign Studies, Guangzhou, 510080, China. Electronic address: yaot2182@gmail.com.
  • School of Foreign Languages, Guangdong Polytechnic Normal University, 293 Zhongshan Avenue West, Guangzhou, 510665, China. Electronic address: linzq@gpnu.edu.cn.

Förderung

  • Guangdong Polytechnic Normal University
  • National Social Science Fund of China
  • University of Macau

Zitieren

APA

Yin, T., Chen, J., Yao, T., & Lin, Z. (2026). Development and initial validation of a video-mediated listening test based on multimodal generative AI. Acta Psychologica. https://doi.org/10.1016/j.actpsy.2026.106521

Vancouver

Yin T, Chen J, Yao T, Lin Z. Development and initial validation of a video-mediated listening test based on multimodal generative AI. Acta Psychologica. 2026. doi:10.1016/j.actpsy.2026.106521

BibTeX
@article{Yin2026,
  author = {Yin, Ting and Chen, Jiexin and Yao, Tong and Lin, Zhiqing},
  title = {Development and initial validation of a video-mediated listening test based on multimodal generative AI},
  journal = {Acta Psychologica},
  year = {2026},
  doi = {10.1016/j.actpsy.2026.106521}
}
Kostenlos starten →