Figure - available from: Education and Information Technologies
This content is subject to copyright. Terms and conditions apply.
Source publication
In many rural Indian schools, English is a second language for teachers and students. Intelligent tutoring systems have good potential because they enable students to learn at their own pace, in an exploratory manner. This paper describes a 3-year longitudinal study of 2123 Indian students who used the intelligent tutoring system, AmritaITS. The ai...
Citations
... The early warning systems for at-risk students [60,61] proposed aimed to identify the at-risk students at the earliest so that intervention programs can be planned by the teachers. The interactive logs of an intelligent system are used to predict at-risk students and also to identify their reading difficulties [62]. The at-risk students are also predicted at different percentages of course length [63]. ...
... Prediction of at-risk students [31,32,34,65,38,40,41,42,52,67,63,66,62,60,90,91,61,58,59,64] 20 Features affecting the academic performance [76,36,39,43,44,79,70,77,51,81,80,69,83,74,82,78,84,92,68,85,75,71,93,72] 24 Suitable Course selection [87,86,55,88,89,48] 6 Prediction of marks / grades [29,30,37,45,46,47,94,49,50,53,95,96,62,90,97,98,58,99,100,16,72,9 8,18,15,75,101,102,64] 28 ...
Review paper analyzing the role of Machine learning in academic performance of college hearing students and deaf students.
... The students are represented as the affected users, the advisors or teachers are represented as the end-users who trust the model, the regulatory bodies who obtain insights from the model, and the AI system builders who train and evaluate the model and ensure its performance. Some of the major applications in the education domain using ML techniques are the classification of students according to their academic performance [16]- [18], identification of at-risk students [19]- [21] prediction of marks [22]- [24] and identification of factors affecting academic performance [25], [26]. ...
Deaf and Hard of Hearing (DHH) students encounter obstacles in higher education due to language and communication challenges. Although research aims to improve their academic performance, the potential of Machine Learning (ML) remains underutilized in DHH education. The opacity of ML models further complicates their adoption. This study aims to fill this gap by developing a novel ML-based system with eXplainable AI (XAI), specifically utilizing Local Interpretable Model-Agnostic Explainer (LIME) and Shapley Additive Explainer (SHAP). The objective is twofold: predicting at-risk DHH students and explaining risk factors. Merging ML and XAI, this approach could positively impact DHH students’ educational outcomes. A dataset of 454 records detailing DHH students is collected. To address dataset limitations, synthetic data and SMOTE are used. Students are categorized into three performance levels. The data is modeled with different ML models, transfer models, ensemble models, and combination models. Among the models, the stacked model with XGBoost, ExtraTrees, and Random Forest exhibited better performance with an accuracy of 92.99%. Results highlight the model’s significance, providing insights through XAI into crucial factors affecting academic performance, including communication mode, early intervention, schooling type, and family deafness history. LIME and SHAP values were found to be effective in deriving insights into DHH student performance prediction framework. Communication mode, notably, strongly influences at-risk students. The major contribution of this study is the development of a novel ML-based system and the XAI interpretations whose value lies in its social relevance, guiding stakeholders to enhance DHH scholars’ academic achievements.
... The use of eye gaze tracking data has been applied in many areas in the education field [8] and intelligent tutoring [9] such as stress detection [3] , fatigue detection [4,5], cross talk elimination [6], misbehaviour/ cheating detection [2]. [11] analyses the reading strategies applied by university students who are English language speakers at C1 level. ...
Advancement in technology brings about the advent of E-learning which replaces the traditional way of conducting examination using paper and pen. Determining student academic growth merely based on assessment scores is inadequate to help them learn and grow from their mistakes. Non-verbal inkling such as eye gaze can provide insights on the motive and contemplation of the participants that may have affected their performance. The addition of this knowledge can help in obtaining a more realistic system for determining participant performance. This research focuses on 3 different reading patterns of participants and to label them into various categories. It was observed that most of the participants belonged to the novice category, while there was an equal distribution among the participants exhibiting organized and unorganized reading pattern classes, and participants that employed the scanning method tend to answer questions correctly.KeywordsEye gazeReading patternsMachine LearningMCQ
... The use of eye gaze tracking data has been applied in many areas in the education field [8] and intelligent tutoring [9] such as stress detection [3] , fatigue detection [4,5], cross talk elimination [6], misbehaviour/ cheating detection [2]. [11] analyses the reading strategies applied by university students who are English language speakers at C1 level. ...
Advancement in technology brings about the advent of E-learning which replaces the traditional way of conducting examination using paper and pen. Determining student academic growth merely based on assessment scores is inadequate to help them learn and grow from their mistakes. Non-verbal inkling such as eye gaze can provide insights on the motive and contemplation of the participants that may have affected their performance. The addition of this knowledge can help in obtaining a more realistic system for determining participant performance. This research focuses on 3 different reading patterns of participants and to label them into various categories. It was observed that most of the participants belonged to the novice category, while there was an equal distribution among the participants exhibiting organized and unorganized reading pattern classes, and participants that employed the scanning method tend to answer questions correctly.
... In deploying cognitive (e.g., taking notes, summarizing, planning) and metacognitive (e.g., content evaluations, feelings of knowing) SRL strategies, learners moderate the difficulty and amount of instructional information presented throughout an ITS Li et al., 2020;Taub & Azevedo, 2019;Trevors et al., 2014). The deployment of these strategies can be supported using prompts via pedagogical agents (Castro-Alonso et al., 2021;Schroeder et al., 2017) that are programmed to scaffold learners' interaction with ITS instructional materials through externally regulating learners' deployment of cognitive and metacognitive SRL strategies (Haridas et al., 2020;Johnson & Lester, 2016;McCarthy et al., 2018;Sharma & Harkishan, 2022;Taub et al., 2015). This is especially critical during learning about a complex topic, which requires the learner to achieve deeper understanding through deploying different strategies throughout the learning process (e.g., conceptual comparisons; Graesser & D'Mello, 2012). ...
Self-regulated learning (SRL), learners’ monitoring and control of cognitive, affective, metacognitive, and motivational processes, is essential for learning. However, cognitive and metacognitive SRL strategies are not typically used accurately leading to poor learning outcomes. Intelligent tutoring systems (ITSs) attempt to address this issue by prompting and scaffolding learners to engage in SRL via using pedagogical agents. However, current literature does not examine the extent to which learners’ deployed strategies are functional or dysfunctional in relation to pedagogical agent scaffolding. The current study collected 117 undergraduate students’ data as they learned with MetaTutor, an ITS about the human circulatory system. Participants were randomly assigned to either the (1) Prompt and Feedback Condition where pedagogical agents scaffolded cognitive and metacognitive SRL strategies or (2) Control Condition where no prompts or feedback were provided. Results demonstrated that learners who received prompts by the pedagogical agents to engage in SRL had higher learning gains as well as greater frequencies across most strategies compared to those in the Control Condition who relied on self-initiated strategy use. While sequential transitions across all strategies were not significant between conditions, further analysis grounded in Complex Systems Theory found that learners who were prompted to engage in strategies demonstrated a significantly lower degree of repetition and balance between repetitive and novel patterns of strategy use. The findings suggest that pedagogical agents within MetaTutor successfully scaffolded the functional deployment of cognitive and metacognitive SRL strategies and are indicative of higher learning after interacting with ITSs.
... These types of errors like, letters omission, addition of letters and letters substitution are recognized and in copying tasks analyzed the spelling errors [12]. More details on the spelling test are given by Haridas [11,9,10]. ...
The triple word form (TWF) theory provides a formal framework for understanding the cognitive processes involved in reading and spelling. On the basis of this theory, spelling errors can be classified into different types, and by understanding the relationships between these error types, one can draw inferences about the difficulties students face while spelling. This paper examines data from 210 second-grade, bilingual students in Kerala, South India. These students participated in a spelling test, and their spelling errors on the test were classified according to the TWF theory. Bayesian networks were used to understand the relationships between the error types. This paper compares three algorithms that were used to study the structure of the Bayesian networks: a score-based algorithm, a constraint-based algorithm, and a hybrid algorithm. Using tenfold cross-validation, it was found that among these three algorithms, the score-based algorithm performed best in terms of expected loss.KeywordsTriple word form theoryCognitive spelling modelBayesian networkNetwork structure learningCross-validation
... Previous studies have used self-efficacy (Yu et al., 2020a), demographics (El Aissaoui et al., 2020;Yağci & Çevik, 2019), and students' online behaviors (Conijn et al., 2017;Lemay & Doleck, 2020) to predict students' performance. Furthermore, given the potential value of finding hidden patterns between features, studies that predict students' performance using various machine learning algorithms have been actively conducted, and the results of these studies exhibited high prediction rates (Cen et al., 2016;Chaturvedi & Ezeife, 2017;Grivokostopoulou et al., 2015;Haridas et al., 2020). ...
... ForumPosts (Arbaugh, 2014;Conijn et al., 2017;Dietz-Uhler & Hurn, 2013;Lauría et al., 2012;Macfadyen & Dawson, 2010;Muñoz-Organero et al., 2010;Nandi et al., 2011;Zacharis, 2015) GradeClick (Dietz-Uhler & Hurn, 2013;Yu et al., 2020a) WikiClick, WikiEdits (Zacharis, 2015) (Conijn et al., 2017) LargestPeriodOfInactivity, TimeUntilFirstActivity, IrregularityOfStudyInterval (Conijn et al., 2017) AverageTimePerSession (Conijn et al., 2017;Dawson et al., 2008;Hu et al., 2014;Macfadyen & Dawson, 2010) IrregularityOfStudyTime (Conijn et al., 2017;Dollinger et al., 2008;Muñoz-Organero et al., 2010;Yu & Jo, 2014) QuizStarted (Lauría et al., 2012) (Conijn et al., 2017;Kovanović et al., 2015;Macfadyen & Dawson, 2010;Zacharis, 2015) EmailsToInstructor (Dietz-Uhler & Hurn, 2013) Other learning-related features EffortRegulation, TimeManagement, EnvironmentManagement, SelfEfficacy (Yu et al., 2020a) VisualPerceptualSkill, BigFivePersonality (Helle et al., 2010) StudyHabits (Dvorak & Jia, 2016) CellphoneUsageBehavior (Felisoni & Godoi, 2018) LearningStyle (Gowda et al., 2013) Assessments AssessmentScore (Aydoğdu, 2020;Conijn et al., 2017;Haridas et al., 2020;Jayaprakash et al., 2014;Rafaeli et al., n.d.;Riestra-González et al., 2021;Schell et al., 2014;Tempelaar et al., 2015;Umer, 2019) Table 8 ...
Predicting students’ performance in advance could help assist the learning process; if “at-risk” students can be identified early on, educators can provide them with the necessary educational support. Despite this potential advantage, the technology for predicting students’ performance has not been widely used in education due to practical limitations. We propose a practical method to predict students’ performance in the educational environment using machine learning and explainable artificial intelligence (XAI) techniques. We conducted qualitative research to ascertain the perspectives of educational stakeholders. Twelve people, including educators, parents of K-12 students, and policymakers, participated in a focus group interview. The initial practical features were chosen based on the participants’ responses. Then, a final version of the practical features was selected through correlation analysis. In addition, to verify whether at-risk students could be distinguished using the selected features, we experimented with various machine learning algorithms: Logistic Regression, Decision Tree, Random Forest, Multi-Layer Perceptron, Support Vector Machine, XGBoost, LightGBM, VTC, and STC. As a result of the experiment, Logistic Regression showed the best overall performance. Finally, information intended to help each student was visually provided using the XAI technique.
... Risk analysis on student models is well-known mainly in web-based education systems like MOOCs, LMS, and Intelligent Tutoring Systems (ITS). The risk analysis on MOOCs and LMS consider predicting dropout risks as a vital topic, while studies based on ITS focus on building skills (Srilekshmi et al., 2016;Olivé et al., 2020;Haridas et al., 2020). Recently, most studies in risk predictions are based on web-based education systems, using learning activities and demographic data (Chen et al., 2020). ...
... We analyze the scores on each cognitive skill bound to the respective course for their impact on the success or failure of students in the course and attempt to understand their feasibility in visualizing the student achievements coherent to the predictions. The student's accomplishments in the third year of study are the most explanatory variable among the predictors Haridas et al. (2020) Predict the student performance, school students at risk, students with reading difficulty in an intelligent tutoring system Past performance ...
In recent times, Educational Data Mining and Learning Analytics have been abundantly used to model decision-making to improve teaching/learning ecosystems. However, the adaptation of student models in different domains/courses needs a balance between the generalization and context specificity to reduce the redundancy in creating domain-specific models. This paper explores the predictive power and generalization of a feature - context-bound cognitive skill score- in estimating the likelihood of success or failure of a student in a traditional higher education course so that the appropriate intervention is provided to help the students. To identify the students at risk in different courses, we applied classification algorithms on context-bound cognitive skill scores of a student to estimate the chances of success or failure, especially failure. The context-bound cognitive skill scores were aggregated based on the learning objective of a course to generate meaningful visual feedback to teachers and students so that they can understand why some students are predicted to be at risk. Evaluation of the generated model shows that this feature is applicable in a range of courses, and it mitigates the effort in engineering features/models for each domain. We submit that overall, context-bound cognitive skill scores prove to be effective in flagging the student performance when the accurate metrics related to learning activities and social behaviors of the students are unavailable.
... Well written multiple-choice-based assessment can also evaluate higher-order thinking such as application, creativity and analytics skills. Intelligent tutoring systems by [7] predicts learner performance via summative and formative assessments and also predict learners at risk of failure in the final evaluation. However, these do not provide deeper insights into how the learner's answered the questions, what was perceived, was it a mere guess, was there a state of confusion, what factors lead to answering the correct option or incorrect option etc. ...
In the current education environment, learning takes place outside the physical classroom, and tutors need to determine whether learners are absorbing the content delivered to them. Online assessment has become a viable option for tutors to establish the achievement of course learning outcomes by learners. It provides real-time progress and immediate results; however, it has challenges in quantifying learner aspects like wavering behavior, confidence level, knowledge acquired, quickness in completing the task, task engagement, inattentional blindness to critical information, etc. An intelligent eye gaze-based assessment system called IEyeGASE is developed to measure insights into these behavioral aspects of learners. The system can be integrated into the existing online assessment system and help tutors re-calibrate learning goals and provide necessary corrective actions.
In many STEM domains, instruction on foundational concepts heavily relies on visuals. Instructors often assume that students can mentally visualize concepts, but students often struggle with internal visualization skills—the ability to mentally visualize information. In order to address this issue, we developed a formal as well as an informal assessment of students’ internal visualization skills in the context of engineering instruction. To validate the assessments, we used data triangulation methods. We drew on data from two separate studies conducted in a small-scale lab experiment and in a larger-scale classroom context. Our studies demonstrate that an intelligent tutoring system with interactive visual representations can serve as an informal assessment of students’ internal visualization skills, predicting their performance on a formal assessment of these skills. Our study enriches methodological and theoretical underpinnings in educational research and practices in multiple ways: it contributes to (1) research methodologies by illustrating how multimodal triangulation can be used for test development, (2) theories of learning by offering pathways to assessing internal visualization skills that are not directly observable, and (3) instructional practices in STEM education by enabling instructors to determine when and where they should provide additional scaffoldings.
