*1.1. Research Background and Motivation*

Due to vigorous development of information technology, digital learning development and applied education are very common. Emotions are an important part of everyone and can affect behavior, thinking skills, decision-making, resilience, well-being, and the way human beings communicate with each other [1]. Based on the discussions, emotion not only is the driving factor that promotes learning but also is the primary factor that hinders the learning process as well. Hence, it is crucial to have reliable methods of emotion recognition in academic contexts [2]. The term "affective computing" was proposed by Professor Rosalind Picard in 1997 [3], and it has been guiding computers to identify and express emotions and respond intelligently to human emotions [4]. Owing to this, a trend has developed that applies emotional lenses to emerging academic research and positions emotion at the core of learning [5,6]. Kort and other scholars have proposed an emotion conceptualization module (2001) to combine affective computing with intelligent tutoring system for the purpose of identifying learners' emotions, responding to affections of current learners and promoting learning effectiveness [7]. Moreover, it can also identify the user's emotions and corresponding system responses as well as guide how to keep positive emotions via "mood proxy" and promote the achievement of learning objectives [8,9]. As Chen Huang Cheng mentioned in this book (2006), the best way to relieve negative emotions is to shift your thinking direction and appropriately reduce the expansion of negative emotions. Impacted with positive emotions, determination to solve problems will

**Citation:** Lin, H.-C.K.; Liao, Y.-C.; Wang, H.-T. Eye Movement Analysis and Usability Assessment on Affective Computing Combined with Intelligent Tutoring System. *Sustainability* **2022**, *14*, 16680. https://doi.org/10.3390/ su142416680

Academic Editor: Aras Bozkurt

Received: 11 October 2022 Accepted: 9 December 2022 Published: 13 December 2022

**Publisher's Note:** MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations.

**Copyright:** © 2022 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https:// creativecommons.org/licenses/by/ 4.0/).

be generated when encountering difficulties [10]. In many studies on the affective tutoring system, the experimental results mainly discuss the usability and interactivity of the system. In this study, we use Scan Path to understand the subject's eye movement trajectory and observe his/her eye movement fixation duration in each ROI block to understand if the subject is more willing to stay in the digital course after combining the tutoring system with the affective computing module.
