Exploring the Connections Between the Use of an Automated Feedback System and Learning Behavior in a MOOC for Programming

Gabbay, Hagit; Cohen, Anat

doi:10.1007/978-3-031-16290-9_9

Cited by 3 publications

(5 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…While some research studied this area, it mainly focuses on bioinformatics (Rider et al, 2010), leaving the educational sector without standardized XAI techniques for clustering. This is despite the extensive use of cluster analysis in various educational research scenarios (Gabbay and Cohen, 2022;Klingler et al, 2016;Mojarad et al, 2018). With this in mind, the study first addressed the following research question, RQ1: If and how ML and XAI methods can be employed to create meaningful explanations for automatically detected profiles of student knowledge?…”

Section: Discussionmentioning

confidence: 99%

“…Cluster analysis has been applied in numerous educational studies to forecast the probability of students succeeding, failing, or dropping out of a course based on their academic performance and online behavior (Gabbay and Cohen, 2022;Käser et al, 2013;Klingler et al, 2016;Mojarad et al, 2018), predicting the specific skills and competencies that students have acquired or are yet to develop, and classifying students into groups based on their knowledge profile (Asif et al, 2017;Nazaretsky et al, 2022a;Klingler et al, 2016). However, many clustering algorithms lead to cluster assignments that are difficult to explain.…”

Section: Xai For Cluster Analysis In Educationmentioning

confidence: 99%

“…Rationale. A common goal of cluster analysis in education is classifying the learners into groups with similar knowledge profiles (Gabbay and Cohen, 2022;Klingler et al, 2016) based on their responses to collections of educational items. The results of such clustering analysis are inherently difficult to interpret, thus requiring explicit user-focused explanations.…”

Section: The Xai Schemementioning

confidence: 99%

See 2 more Smart Citations

Explainable AI for unsupervised machine learning: A proposed scheme applied to a case study with science teachers

Feldman-Maggor,

Nazaretsky,

Alexandron

2024

Preprint

View full text Add to dashboard Cite

Explainable Artificial Intelligence (XAI) seeks to render Artificial Intelligence (AI) models transparent and comprehensible, potentially increasing trust and confidence in AI recommendations. This research explores the realm of XAI within unsupervised educational machine learning, a relatively under-explored topic within Learning Analytics (LA). It introduces an XAI framework designed to elucidate clustering-based personalized recommendations for educators. Our approach involves a two-step validation: computational verification followed by domain-specific evaluation concerning its impact on teachers' AI acceptance. Through interviews with K-12 educators, we identified key themes in teachers' attitudes toward the explanations. The main contribution of this paper is a new XAI scheme for unsupervised educational machine-learning decision-support systems. The second is shedding light on the subjective nature of educators' interpretation of XAI schemes and visualizations.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Xai For Cluster Analysis In Educationmentioning

confidence: 99%

Section: The Xai Schemementioning

confidence: 99%

See 1 more Smart Citation

Explainable AI for unsupervised machine learning: A proposed scheme applied to a case study with science teachers

Feldman-Maggor,

Nazaretsky,

Alexandron

2024

Preprint

View full text Add to dashboard Cite

show abstract

“…The provision of personalized feedback in MOOCs is hindered by a substantial logistical and resource-intensive obstacle in the form of scalability challenges. Generative AI possesses the capability to mitigate this divide through the automation of the feedback procedure while preserving a substantial level of customization [23,24]. It possesses the capability to assess student submissions, pinpoint areas that require enhancement, and provide constructive criticism in an engaging and enlightening fashion.…”

Section: Generative Ai For Feedbackmentioning

confidence: 99%

Personalized Feedback in Massive Open Online Courses: Harnessing the Power of LangChain and OpenAI API

Morales-Chan,

Amado-Salvatierra,

Medina

et al. 2024

Electronics

View full text Add to dashboard Cite

Studies show that feedback greatly improves student learning outcomes, but achieving this level of personalization at scale is a complex task, especially in the diverse and open environment of Massive Open Online Courses (MOOCs). This research provides a novel method for using cutting-edge artificial intelligence technology to enhance the feedback mechanism in MOOCs. The main goal of this research is to leverage AI’s capabilities to automate and refine the MOOC feedback process, with special emphasis on courses that allow students to learn at their own pace. The combination of LangChain—a cutting-edge framework specifically designed for applications that use language models—with the OpenAI API forms the basis of this work. This integration creates dynamic, scalable, and intelligent environments that can provide students with individualized, insightful feedback. A well-organized assessment rubric directs the feedback system, ensuring that the responses are both tailored to each learner’s unique path and aligned with academic standards and objectives. This initiative uses Generative AI to enhance MOOCs, making them more engaging, responsive, and successful for a diverse, international student body. Beyond mere automation, this technology has the potential to transform fundamentally how learning is supported in digital environments and how feedback is delivered. The initial results demonstrate increased learner satisfaction and progress, thereby validating the effectiveness of personalized feedback powered by AI.

show abstract

“…This is an instance of a fundamental problem -deciding on the number of clusters in a dataset. This is relevant for many applications in education [44,46], such as discovering knowledge profiles, adaptive learning and student modelling [12,13,21,22,25,29,33,34,40,50]. Despite this vast use, the issue of investigating ways to decide on the number of clusters in student response data was not studied in a systematic manner.…”

Section: Introductionmentioning

confidence: 99%

Automated Identification and Validation of the Optimal Number of Knowledge Profiles in Student Response Data

Din¹,

Nazaretsky²,

Feldman-Maggor³

et al. 2023

Preprint

View full text Add to dashboard Cite

It is well--known that the provision of personalized instruction can enhance student learning. AI--based education tools can be used to incorporate blended learning in the science classroom, and have been shown to enhance teachers' ability to prescribe this personalisation. In order to reveal student knowledge profiles from their response data, we must utilise classical educational data mining techniques, with cluster analysis being one of the key methods for doing so. However, while clustering algorithms typically require the number of clusters as a hyperparameter, there is no clear method for choosing the optimal number.Motivated by a practical instance of this foundational problem -- deciding on the number of student clusters for a group-based personalization tool -- this paper discusses several variations of the gap statistic to identify the optimal number of clusters in student response data. We start with a simulation study where the ground truth is known to evaluate the quality of the identified methods, and then assess their behaviour on real student data. Based on the results, we suggest a stability--based approach to validate our predictions, and identify an empirical threshold for the number of observations for a prediction to be stable.We find that if a dataset has some cluster structure, very small subsamples also showed cluster structure -- large datasets were not required to identify if any cluster structure exists, but only to discern the number of clusters accurately. Finally, we discuss how the flexibility of the method enables teachers to choose between a different number of clusters according to their class environment or teaching goals.

show abstract

Exploring the Connections Between the Use of an Automated Feedback System and Learning Behavior in a MOOC for Programming

Cited by 3 publications

References 33 publications

Explainable AI for unsupervised machine learning: A proposed scheme applied to a case study with science teachers

Explainable AI for unsupervised machine learning: A proposed scheme applied to a case study with science teachers

Personalized Feedback in Massive Open Online Courses: Harnessing the Power of LangChain and OpenAI API

Automated Identification and Validation of the Optimal Number of Knowledge Profiles in Student Response Data

Contact Info

Product

Resources

About