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. that may be related to cheating. This integrated system ensures that the same student remains throughout the test and supports examiners by offering real-time alerts and a secure, user-friendly interface for data security. Lessons learned The TRUSTID system, evaluated by stakeholders, showed resilience against impersonation attacks and received positive feedback in terms of usability and user experience. The system was robust in monitoring student behaviours and identifying anomalies, receiving positive feedback from students and instructors for its usability and ease of use. Privacy concerns were addressed with a privacy-preserving biometric wallet, allowing secure control and sharing of biometric data. Overall, the TRUSTID system was well-received across various stakeholder groups, showing its potential applicability and effectiveness in maintaining academic integrity in online educational settings. Implications for practice The system has the potential to enhance the integrity of online examinations by using advanced biometric verification methods to prevent common threats such as impersonation and cheating. Μελέτη περίπτωσης 4: Αυτοματοποιημένη ανατροφοδότηση φοιτητών/τριών σε εργασίες Επιστήμης των Δεδομένων: Βελτιωμένη εφαρμογή και αποτελέσματα. General information Alessandra Galassi & Pierpaolo Vittorini, CHItaly 2021: 14th Biannual Conference of the Italian SIGCHI Chapter, July 11–13, 2021, Bolzano, Italy, Association for Computing Machinery (ACM), New York, NY, USA, 8 pages. The research discusses the development and implementation of an automated feedback system for assignments in data science. This system focuses on grading assignments that involve language commands, their outputs, and natural language comments. The primary objective is to change students' learning experiences by providing fast and detailed feedback that can identify mistakes and offer improvement suggestions. The study evaluated the effectiveness of this system using student feedback collected through standardised and custom questionnaires. Description of case The research presents a case study on the development, implementation, and evaluation of an automated feedback system for data science assignments at the University of L’Aquila, Italy. The system was specifically designed to grade assignments involving R language commands, their outputs, and accompanying natural language comments. It used static code analysis and machine learning techniques to evaluate the correctness and quality of the R code and the associated comments. The system provided feedback with explanations for grading decisions, identification of errors, and suggestions for improvements. This feedback was intended to be detailed and instructive to help students learn from their mistakes. Lessons learned The study observed an increased engagement of students in the process. The automated feedback system led to higher levels of student engagement, as students could receive immediate feedback and make corrections quickly. Perceived Usefulness: Students found the feedback to be useful in understanding their mistakes and learning how to correct them. Clear Error Identification: The system was effective in clearly identifying errors and providing impactful suggestions for improvement. Impact: The results show that the automatic feedback provided by the system was useful to students to understand their mistakes, to understand the correct statistical method to solve the problem, and to verify the preparation for the final exam. Furthermore, most of the students used the tool iteratively to improve their solutions.
RkJQdWJsaXNoZXIy NzYwNDE=