AI‐Based Adaptive Feedback in Simulations for Teacher Education: An Experimental Replication in the Field DOI Creative Commons
Elisabeth Bauer, Michael Sailer, Frank Niklas

и другие.

Journal of Computer Assisted Learning, Год журнала: 2025, Номер 41(1)

Опубликована: Янв. 15, 2025

ABSTRACT Background Artificial intelligence, particularly natural language processing (NLP), enables automating the formative assessment of written task solutions to provide adaptive feedback automatically. A laboratory study found that, compared with static (an expert solution), automated through artificial neural networks enhanced preservice teachers' diagnostic reasoning in a digital case‐based simulation. However, effectiveness simulation different types and generalizability field settings remained unclear. Objectives We tested previous findings single session either type an experimental study. Methods In regular online courses, 332 teachers at five German universities participated one three randomly assigned groups: (1) group NLP‐based feedback, (2) (3) no‐simulation control group. analysed effect two on participants' judgement accuracy justification quality. Results Conclusions Compared significantly quality but not accuracy. Only benefited learners' over group, while no significant differences were found. Our experiment replicated unlike seems enhance Under conditions, learners require support simulations can benefit from using networks.

Язык: Английский

AI‐Based Adaptive Feedback in Simulations for Teacher Education: An Experimental Replication in the Field DOI Creative Commons
Elisabeth Bauer, Michael Sailer, Frank Niklas

и другие.

Journal of Computer Assisted Learning, Год журнала: 2025, Номер 41(1)

Опубликована: Янв. 15, 2025

ABSTRACT Background Artificial intelligence, particularly natural language processing (NLP), enables automating the formative assessment of written task solutions to provide adaptive feedback automatically. A laboratory study found that, compared with static (an expert solution), automated through artificial neural networks enhanced preservice teachers' diagnostic reasoning in a digital case‐based simulation. However, effectiveness simulation different types and generalizability field settings remained unclear. Objectives We tested previous findings single session either type an experimental study. Methods In regular online courses, 332 teachers at five German universities participated one three randomly assigned groups: (1) group NLP‐based feedback, (2) (3) no‐simulation control group. analysed effect two on participants' judgement accuracy justification quality. Results Conclusions Compared significantly quality but not accuracy. Only benefited learners' over group, while no significant differences were found. Our experiment replicated unlike seems enhance Under conditions, learners require support simulations can benefit from using networks.

Язык: Английский

Процитировано

2