Analysis of students' study paths using finite Markov chains

Ikonen, Enso; Tervaskanto, Manne; Najim, K.

doi:10.1109/icca.2009.5410623

Cited by 2 publications

(2 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This may yield some patterns that are not readily seen through the usual analyses that we undertake. We are finalising a sub-project that took a first step towards exploring whether the probability theory of Markov Chains, has any relevance to University study, after finding a paper that had attempted something similar (Ikonen, 2009). The theory is used in a number of fields, including voice recognition.…”

Section: Next Stepsmentioning

confidence: 99%

The Student Study Experience – Analysing Student Study Choices

Edwards

Gaved

2020

JECP

View full text Add to dashboard Cite

As higher education institutions increasingly teach online and offer greater levels of choice to students (over which modules to study, in which order to study, and how long to extend study before qualification) new challenges are introduced. One of these challenges is how to maintain an understanding of the student experience. This understanding is necessary to provide feedback to both students and faculty, and institutionally for the continued enhancement of quality. This paper is the first attempt at providing a narrative describing one approach to this challenge and the experience within a large distance learning University. It demonstrates a new approach to data is key to enabling the analysis of student study pathways. For many years, this University has offered great flexibility of study and as wide a study choice as it is possible to offer with conventional modules. By design, the Institution holds high levels of data for all student study. However, whilst it is possible to create bespoke queries, we found that this has been insufficient to readily enable analysis of the student experience. By moving from a traditional relational database structure to a multi-model database, many of the difficulties are resolved. In this paper, we report on this approach and describe next steps, including the potential to apply machine learning algorithms and test other data theories like that of Markov Chains.

show abstract

Section: Next Stepsmentioning

confidence: 99%

The Student Study Experience – Analysing Student Study Choices

Edwards

Gaved

2020

JECP

View full text Add to dashboard Cite

show abstract

“…Most education platforms attempt to plan reasonable learning paths for college student users, but they have generally ignored differences in their learning time distribution preferences, learning habits, and learning requirements, and haven't taken the dynamic development trends of their learning states into consideration. Moreover, the generated learning path often does not conform to the cognition sequence of college students, and is not easily accepted or recognized by them, sometimes it can even lead to problems such as cognitive overload, disorientation, and learning efficiency in them [16][17][18][19][20][21][22][23][24]. Therefore, rationally planning the learning path for the personalized and fragmented learning of college students is a very meaningful and practical work.…”

Section: Introductionmentioning

confidence: 99%

Path Planning for the Fragmented Learning of College Students Based on Artificial Intelligence

Li¹

2022

Int. J. Emerg. Technol. Learn.

View full text Add to dashboard Cite

Most education platforms attempt to plan reasonable learning paths for college student users, but they have generally ignored differences in their learning time distribution preferences, learning habits, and learning requirements, and haven’t taken the dynamic development trends of their learning states into consideration. To make up for these shortcomings, this paper aims to study the learning path planning for the fragmented learning of college students based on artificial intelligence. At first, this paper proposed a fragmented learning path planning model for college students, and introduced a fragmented knowledge concept map method to mine the recommended fragmented knowledge structure and the association between concepts, so as to fragment knowledge concept into small knowledge pieces and realize fragmented knowledge recommendation. Then, this paper introduced the regularization constraints, and adopted the sparse auto-encoder to predict the missing values in the interaction matrix, so as to solve the problem of data sparsity. After that, hybrid recommendation of fragmented knowledge was made based on the multi-layer perception network model, and the accuracy of the personalized recommendation of fragmented knowledge had been effectively improved. At last, experimental results verified the effectiveness of the proposed recommendation model.

show abstract

Analysis of students' study paths using finite Markov chains

Cited by 2 publications

References 5 publications

The Student Study Experience – Analysing Student Study Choices

The Student Study Experience – Analysing Student Study Choices

Path Planning for the Fragmented Learning of College Students Based on Artificial Intelligence

Contact Info

Product

Resources

About