Feedback plays a pivotal role in online testing. This study employed a randomized experimental design to investigate how feedback types (confirmatory vs. informative) and modalities (text, audio, multimodal) affect university students’ online test performance. Utilizing fNIRS and questionnaires, the research measured learning achievement, cognitive load, emotions, motivation, and attention. Results revealed that feedback modalities significantly influenced learning achievement. Informative feedback can enhance learning outcomes and promote more positive emotions. Furthermore, distinct activation patterns in various brain regions were elicited by different feedback types and modalities during testing. This study enriches the application of cognitive load theory in online testing feedback and offers insights for optimizing feedback design to reduce cognitive overload. It also supports the assessment of feedback effectiveness using neural indicators and the development of real-time brain-computer interface systems.

Sibo Ma, Julian Nyarko. Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2025.