Με τη χρηματοδότηση της Ευρωπαϊκής Ένωσης. Οι απόψεις και οι γνώμες που διατυπώνονται εκφράζουν αποκλειστικά τις απόψεις των συντακτών και δεν αντιπροσωπεύουν κατ'ανάγκη τις απόψεις της Ευρωπαϊκής Ένωσης ή του Ευρωπαϊκού Εκτελεστικού Οργανισμού Εκπαίδευσης και Πολιτισμού (EACEA). Η Ευρωπαϊκή Ένωση και ο EACEA δεν μπορούν να θεωρηθούν υπεύθυνοι για τις εκφραζόμενες απόψεις. Ενότητα 6: Μελέτες περίπτωσης Αυτή η ενότητα περιέχει τριάντα έξι (36) εθνικές/ευρωπαϊκές μελέτες περίπτωσης με τεκμηριωμένα παραδείγματα ενσωμάτωσης εργαλείων ΤΝ στα Ανώτατα Εκπαιδευτικά Ιδρύματα, καθώς και τις δυνατότητες και τις προκλήσεις τους για την επαγγελματική και παιδαγωγική πρακτική. Μελέτη περίπτωσης 1: Ένα ολοκληρωμένο πλαίσιο για την ανάπτυξη και την αξιολόγηση ενός αυτοματοποιημένου συστήματος αξιολόγησης του ύφους μιας διάλεξης General information Dimitriadou, E., & Lanitis, A. (2023). An integrated framework for developing and evaluating an automated lecture style assessment system. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2312.00201 The study aims to develop and evaluate an integrated system that provides an automated evaluation of an instructor's lecture style. This system aims to help teachers by giving instant feedback on their lecturing style, to improve quality and enhance student learning experiences. Description of case The proposed application analysed and extracted measurable biometric characteristics from video cameras and audio sensors using machine learning. These characteristics included facial expressions, body activity, speech rate and tone, hand movements, and facial pose. These features, in combination, provided a score reflecting the quality of the lecture style. The system’s performance was evaluated by comparing its assessments with human evaluations and through feedback from education officers, teachers, and students. Lessons learned The results indicated that the system effectively provided automated feedback that participants received well. It performed comparably to humans and, in some cases, even outperformed them. Participants appreciated the application's utility in enhancing lecture delivery through immediate feedback. Implications for practice With similar or even fewer differences between AI-driven and human evaluation of lecture quality, the system can be used in natural settings (e.g., a university classroom) to support teachers in improving their lecturing and increasing student engagement. The researchers aim to further improve the system by refining the biometric metrics used in the automated lecture-style evaluation system, expanding its capabilities to include additional and wearable cameras and conducting real-time testing in classroom settings.
RkJQdWJsaXNoZXIy NzYwNDE=