Distance learning and assessment through online platforms have emerged as a complementary approach to traditional classroom-based activities in the contemporary educational landscape. These platforms add significant value to conventional learning and evaluation methods by offering flexibility and accessibility. The increasing demand for intelligent online platforms has led to the integration of innovative techniques such as artificial intelligence (AI), computer vision, and deep neural networks for different classifications. However, online assessments pose several challenges, including the absence of physical invigilator presence, limited face-to-face instructions about the examinations, and issues related to student engagement and motivation. AI tools have enabled the creation of sophisticated models that can track student’s emotions throughout the assessment period, particularly using computer vision and natural language processing.
AI provides viable options to automate the emotion recognition process more effectively and accurately. This chapter examines the different AI tools such as Affectiva, Cognimates, Empatica, QuantaEd, HUME AI, iMotions, EmoVu, Sensum, and Emotion AI by Beyond Verbal to track student’s emotional states in online assessment. It examines the advantages of incorporating deep learning techniques, including enhanced accuracy, scalability, and the ability to capture subtle emotional nuances in real time. Additionally, the exploration highlights noteworthy developments and applications in the field, showcasing how advanced models in computer vision and natural language processing are being utilized to revolutionize the way student emotions are monitored and understood in educational assessment settings.
