A review of automated feedback systems for learners: Classification framework, challenges and opportunities

Deeva, Galina; Bogdanova, Daria; Serral, Estefanía; Snoeck, Monique; Weerdt, Jochen De

doi:10.1016/j.compedu.2020.104094

Cited by 135 publications

(44 citation statements)

References 103 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…A third consideration is that it is very common to base feedback on expert information. In a very recent overview, Deeva et al [26] analyzed 109 automated feedback systems, distinguishing data-driven and expert-driven feedback generation models, and found that almost half of the existing systems were expert based, 32% were data driven and 19% combined both approaches. According to these authors, mixed approaches offer better opportunities than pure expert models.…”

Section: Discussionmentioning

confidence: 99%

“…By providing students with suggestions instead of directions we encourage students to create their own concept maps while considering the expert suggestions given to them. The use of a single reference map for generating assessments and feedback, as is predominantly done in this research field [26], makes the tool easy to adapt to different domains and easier to deploy in educational practice. A reference map can easily be generated by teachers.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Automated Assessment of and Feedback on Concept Maps During Inquiry Learning

Kroeze

Berg

Veldkamp

et al. 2021

IEEE Trans. Learning Technol.

View full text Add to dashboard Cite

A tool is presented that can automatically assess the quality of students' concept maps and provide feedback based on a reference concept map. It is shown that this tool can effectively assess the quality of concept maps, and that it can provide accurate and helpful feedback on a number of specific shortcomings often evident in students' concept maps. However, it was also found that students who had access to feedback often did not request it, or did not take full advantage of the feedback given.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Automated Assessment of and Feedback on Concept Maps During Inquiry Learning

Kroeze

Berg

Veldkamp

et al. 2021

IEEE Trans. Learning Technol.

View full text Add to dashboard Cite

show abstract

“…However, students might have a concern about the data breach of their learning behaviours (e.g., learning materials download frequency and login duration) in the learning management systems controlled by the institutions [14] and this concern can further cause a negative effect to the students' trust [28,27]. When scrutinising the feedback generation process, the systems need to collect and process learning behaviours from students, use AI algorithms to analyse the behaviour patterns (e.g., students' engagement level with the course materials), and generate personalised feedback to the students [10,8]. Therefore, there might be a conflict between the feedback generation process and the students' privacy concerns regarding their learning behaviour data.…”

Section: Privacymentioning

confidence: 99%

Establishing Trustworthy Artificial Intelligence in Automated Feedback

Lin¹,

Sha²,

Gašević³

et al. 2022

Preprint

View full text Add to dashboard Cite

Providing educational feedback has been widely acknowledged as an effective method to assist student learning. To offer feedback for a large student cohort, educational researchers started developing artificial intelligence (AI) systems. Though the existing AI-driven feedback achieved certain success, many concerns still exist during the deployment of AI (e.g., privacy, AI explainability and accountability) and further shape the untrustworthy barriers between the educational stakeholders' needs and AI efforts. To reduce the barriers, it is necessary to identify the concerns based on the principles of trustworthy AI before the development of automated feedback. Therefore, in this paper, we aimed to tease out the concerns raised in the existing literature. In particular, we mainly discuss trustworthy AI trough five dimensions -- i.e., acceptance, explainability, accountability, fairness, and privacy -- to shed light on the future design of automated feedback.

show abstract

“…In a recent review, Deeva et al [10] classified automated feedback systems by their applied educational settings, the properties of their delivered automated feedback, and their design and evaluation approaches. They concluded that applied learning theories or educational frameworks had not been reported in most cases.…”

Section: Introductionmentioning

confidence: 99%

Explainable Student Agency Analytics

Saarela¹,

Heilala²,

Jääskelä³

et al. 2021

IEEE Access

View full text Add to dashboard Cite

Several studies have shown that complex nonlinear learning analytics (LA) techniques outperform the traditional ones. However, the actual integration of these techniques in automatic LA systems remains rare because they are generally presumed to be opaque. At the same time, the current reviews on LA in higher education point out that LA should be more grounded to the learning science with actual linkage to teachers and pedagogical planning. In this study, we aim to address these two challenges. First, we discuss different techniques that open up the decision-making process of complex techniques and how they can be integrated in LA tools. More precisely, we present various global and local explainable techniques with an example of an automatic LA process that provides information about different resources that can support student agency in higher education institutes. Second, we exemplify these techniques and the LA process through recently collected student agency data in four courses of the same content taught by four different teachers. Altogether, we demonstrate how this process-which we call explainable student agency analytics-can contribute to teachers' pedagogical planning through the LA cycle.

show abstract

A review of automated feedback systems for learners: Classification framework, challenges and opportunities

Cited by 135 publications

References 103 publications

Automated Assessment of and Feedback on Concept Maps During Inquiry Learning

Automated Assessment of and Feedback on Concept Maps During Inquiry Learning

Establishing Trustworthy Artificial Intelligence in Automated Feedback

Explainable Student Agency Analytics

Contact Info

Product

Resources

About