Mirroring Teachers' Assessment of Novice Students' Presentations through an Intelligent Tutor System

Abstract

This study proposes an Intelligent Tutor System for assessing slide presentations from novice undergraduate students. To develop such system, two learner models (rule based model and clustering model) were built using 80 presentations graded by three human experts. An experiment to determine the best learner model and students' perception was carried out using 51 presentations uploaded by students. The findings show that the clustering model classified in a similar way as a human evaluator only when a holistic evaluation criterion was used. Whereas, the rule-base model was more precise when the evaluation rules were easier to be followed by a human evaluator. Furthermore, students agreed with the usefulness of the system as well as the level of agreement with the grading model, although the latter in a lesser extent. Results from this study encourage to explore this area and adapt the proposed Intelligent Tutor System to other existing automated grading systems.

Utilization of Artificial Intelligence in Education: A Perspective on Learning Strategies

“…However, the use of intelligent tutoring systems includes the integrated form of AI, so the spread of ITS in time will further disseminate these systems that are being used in education. These systems are used for adaptive feedback [23][24][25][26][27][28], presenting and recommending content [24,27,29,30].…”

Fundamental Structue of Matter and Interactions

“…While previous works often employ diverse techniques jointly, including learner style classification (Grawemeyer et al 2016;Nihad, Seghroucheni et al 2017), data mining (Echeverria, Guamán, and Chiluiza 2015), Bayesian learning (Grawemeyer et al 2016), etc, the recent emergence of large language models (LLMs) (Devlin et al 2019;Raffel et al 2019;Brown et al 2020;Bommasani et al 2021;Han et al 2021), like ChatGPT (OpenAI 2022), has broadened our imagination on new designs of intelligent tutoring systems. LLMs impressed people firstly with the ability to generate and transform information following human instructions, then with the potential in task planning and tool usage.…”

“…In addition to AutoTutor's application to various fields, enhancement of specific aspects of education are also investigated, including adaptive feedback(Dzikovska et al 2014;Roscoe and McNamara 2013), learning material recommendation (S. 2014;Mohammed and Mohan 2015), and classifying learners(Grawemeyer et al 2016;Nihad, Seghroucheni et al 2017;. Commonly adopted techniques include data mining(Echeverria, Guamán, and Chiluiza 2015), condition-action rule based (J. 2014; S.…”