Learning Feedback in Intelligent Tutoring Systems

Groß, Sebastian; Mokbel, Bassam; Hammer, Barbara; Pinkwart, Niels

doi:10.1007/s13218-015-0367-y

Cited by 21 publications

(4 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Knowledge about concepts is typically represented either as an explanation of the subject matter or as an example illustrating a concept. The former can be found in Ask-Elle [14], an educational tool that suggests relevant web pages when a particular programming language construct is encountered; the latter can be found in FIT Java Tutor [16], which suggests an example of a correct solution in response to an erroneous one written by the student.…”

Section: Formative Feedback Generators In Programmingmentioning

confidence: 99%

Educating Students about Programming Plagiarism and Collusion via Formative Feedback

Karnalim

Simón²,

Chivers

et al. 2022

ACM Trans. Comput. Educ.

View full text Add to dashboard Cite

To help address programming plagiarism and collusion, students should be informed about acceptable practices and about program similarity, both coincidental and non-coincidental. However, current approaches are usually manual, brief, and delivered well before students are in a situation where they might commit academic misconduct. This paper presents an assessment submission system with automated, personalized, and timely formative feedback that can be used in institutions that apply some leniency in early instances of plagiarism and collusion. If a student’s submission shares coincidental or non-coincidental similarity with other submissions, personalized similarity reports are generated for the involved submissions and the students are expected to explain the similarity and resubmit the work. Otherwise, a report simulating similarities is sent just to the author of the submitted program to enhance their knowledge. Results from two quasi-experiments involving two academic semesters suggest that students with our approach are more aware of programming plagiarism and collusion, including the futility of some program disguises. Further, their submitted programs have lower similarity even at the level of program flow, suggesting that they are less likely to have engaged in programming plagiarism and collusion. Student behavior while using the system is also analyzed based on the statistics of the generated reports and student justifications for the reported similarities.

show abstract

Section: Formative Feedback Generators In Programmingmentioning

confidence: 99%

Educating Students about Programming Plagiarism and Collusion via Formative Feedback

Karnalim

Simón²,

Chivers

et al. 2022

ACM Trans. Comput. Educ.

View full text Add to dashboard Cite

show abstract

“…ITS are very specialized learning systems that are restricted to narrow domains [17]. Due to limited scope, separate ITS is required for different subjects which is not feasible due to the high development cost and the diverse training needs [18]. On the other hand AH provides an alternate solution against the issues of ITS [19].…”

Section: Literature Reviewmentioning

confidence: 99%

A Model of Adaptive E-Learning in an ODL Environment

Ahmed

Sangi

Mahmood

2018

Mehran Univ. res. j. eng. technol.

View full text Add to dashboard Cite

In recent years, technology enabled learning also called e-learning is penetrating in the educational sector and its use is increasing especially in ODL (Open and Distance Learning). But a majority of the e-learning systems merely focuses on instruction delivery with little focus on learning activities and thus creating opportunities to develop e-learning more interactive and engaging by adding adaptive features. However, it is also a challenging task to develop and implement an adaptive e-learning model for an ODL environment. There are various issues like non-availability of the specialized contents, the learning sequence story board and the preferences of learners under the available infrastructure. This paper proposes a model of adaptive e-learning for an ODL environment. The proposed model has three important components: content model, learner model and adaptive model. The content model defines and stores the organization of chapters and topics in a logical sequence. The learner model stores information about survey and quizzes data and keep the track of the learning performance. The survey is designed to investigate the personal profiles and the preference of students about their favorite content types. The adaptive model manages content presentation and its navigation derived by the learning algorithm. The learning algorithm takes information from the learner model, analyzes it and adjusts the display of the contents by retrieving it from the content model. The implementation was conducted on two courses of computer science and in each course the experimental and control groups were formed to investigate the change in their learning level. The results show that the proposed adaptive e-learning model has improved the knowledge level of the students. The percentage of highest grade holders has increased and the failure rate has dropped in both courses. The feedback of the students enrolled in adaptive e-learning course is also conducted. The results of the survey highlight the positive opinion about this new paradigm of technology based learning.

show abstract

“…However, this approach typically reveals several reproduciblity issues within the same notebook, making it difficult for the students to debug. In this paper, we propose to alleviate this problem with a simple Jupyter plug-in (NoRM) that gives immediate visual feedback [6,7,8,9] to students regarding reproducibility while they are writing their notebooks. Our plug-in continuously attempts to reproduce the notebook in the background and highlights which cells are reproducible or not using colors.…”

Section: Introductionmentioning

confidence: 99%