2020
DOI: 10.18608/jla.2020.72.1
|View full text |Cite
|
Sign up to set email alerts
|

Utilizing Student Time Series Behaviour in Learning Management Systems for Early Prediction of Course Performance

Abstract: Predictive analytics in higher education has become increasingly popular in recent years with the growing availability of educational big data. Particularly, a wealth of student activity data is available from learning management systems (LMSs) in most academic institutions. However, previous investigations into predictive analytics in higher education using LMS activity data did not adequatelyaccommodate student behaviours in the form of time series. In this study, we have applied a deep learning approach -lo… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

2
52
0
1

Year Published

2021
2021
2024
2024

Publication Types

Select...
5
3
1

Relationship

0
9

Authors

Journals

citations
Cited by 60 publications
(55 citation statements)
references
References 37 publications
2
52
0
1
Order By: Relevance
“…They concluded that their intervention program resulted in a notable uptick of student retention and learning outcomes. While ML has been demonstrated as a particularly effective tool for developing predictive models, with the plethora of ML algorithms to choose there is ongoing work that remains to compare and assess their suitability (Chen & Cui, 2020).…”
Section: Literature Reviewmentioning
confidence: 99%
“…They concluded that their intervention program resulted in a notable uptick of student retention and learning outcomes. While ML has been demonstrated as a particularly effective tool for developing predictive models, with the plethora of ML algorithms to choose there is ongoing work that remains to compare and assess their suitability (Chen & Cui, 2020).…”
Section: Literature Reviewmentioning
confidence: 99%
“…They primarily highlighted students' positive reception of features such as immediate grading with the allowance of multiple submissions [55]. Together with this, several works focused on the ability to create custom learnings paths based on student performance [56,26,54,55,56,57,58,59], and the ability to flag students at high risk of not succeeding [51,60,61,62,63,64,62]. Table V summarizes the benefits found in the review.…”
Section: F Rq3 What Are the Positive Effects On The Student Experience Of Using Automatic Feedback And Automatic Scoring?mentioning
confidence: 99%
“…Only several papers published the results of the longitudinal analysis the students' behaviour from the VLE logs. Some of them used a combination of time series techniques [1], neural networks [27] or clustering [28].…”
Section: Related Workmentioning
confidence: 99%
“…This notion is in line with other researchers in the domain of learning analytics, who stated, that even though the importance of temporality in learning has been long established, it is only recently that serious attention has been paid to explore temporal concepts and data types, analyse methods for exploiting temporal data, techniques for visualizing temporal information, and practical considerations how to effectively use the outcomes of temporal analysis in particular educational contexts. Thus, temporal and sequential nature of the learning process is receiving increasing interest and suggestions for systematic research, in which the knowledge discovery tasks like time series analysis or data clustering based on different temporal characteristics are mostly applied [1], [2].…”
Section: Introductionmentioning
confidence: 99%