BEGIN:VCALENDAR VERSION:2.0 PRODID:researchseminars.org CALSCALE:GREGORIAN X-WR-CALNAME:researchseminars.org BEGIN:VEVENT SUMMARY:Dr. John Lin (National Taiwan Normal University) DTSTART:20240410T060000Z DTEND:20240410T070000Z DTSTAMP:20260423T021432Z UID:MAC8028/25 DESCRIPTION:Title: Automated prediction of problem solving performance using eye movement: C an AI help?\nby Dr. John Lin (National Taiwan Normal University) as pa rt of Trends in Mathematical Research\n\nLecture held in NTNU Gongguan S10 1.\n\nAbstract\nWith the ability to predict learning behaviors in complex scenarios\, artificial intelligence (AI) shows its potential in assessing the problem-solving performance. Given that AI\, data-driven algorithms\, could be helpful to address random signals (e.g.\, random fixations)\, usi ng AI to predict learning performance based on eye movements seems promisi ng. The aims to explorer the potential of an AI\, designed based on the lo ng-short-term memory neural structure\, to predict whether mathematics pro blems could be solved in a digital problem-solving scenario using eye move ments. Sixty-one students participated in this study. We examined whether types of eye movement features (AOI-based vs. fixation-based features) and information (Separated vs. integrated steps) during solving problems coul d impact the performance of AI models. In additional\, the effects of two hyper-parameters\, activations in hidden layers and number of neuros\, wer e examined. The results suggested that fixation-based features outperform AOI-based features. Furthermore\, information in separated steps could pro vide higher accuracy than that in the integrated steps. Regarding the impa ct of hyper-parameters on AI performance\, the activation function ‘tanh ’ and thirty neurons in each layer could be used to train AI models with higher accuracy. The inconsistent between human and AI-based assessment w ere discussed and visualized.\n LOCATION:https://researchseminars.org/talk/MAC8028/25/ END:VEVENT END:VCALENDAR