Dark Mode
Higher Education E-Learning Analytics
Education & Learning Analytics
Tags and Keywords
Trusted By
"No reviews yet"
Free
About
Introducing the anonymised Open University Learning Analytics Dataset (OULAD), designed to facilitate research into student behaviour and educational performance. This collection includes detailed information regarding courses, demographic details of students, and logs capturing their interactions within the Virtual Learning Environment (VLE) across seven distinct modules. The data allows analysts to explore factors influencing final results, submission patterns for different types of assessments, and engagement levels with online course materials. Course presentations are distinguished by their start month, either February or October.
Columns
The data is organised into multiple related CSV files, connected by unique identifiers. Key columns across these files include:
- code_module: The unique identifier for a specific course module.
- code_presentation: Identifies the specific presentation of the course, incorporating the year and the start month ('B' for February, 'J' for October).
- length: The duration of the module presentation, recorded in days.
- assessment_type: Categorises the type of student evaluation, such as Tutor Marked Assessment (TMA), Computer Marked Assessment (CMA), or Final Exam (Exam).
- weight: The percentage weight of an assessment towards the final grade.
- gender: The declared gender of the student.
- region: The geographic location where the student resided during the module presentation.
- highest_education: The highest level of education attained by the student prior to enrolling.
- age_band: Categorical description of the student's age.
- final_result: The student’s outcome for the module (e.g., Pass, Fail, Withdrawal).
- score: The student's assessment mark, ranging from 0 to 100.
- sum_click: The count of daily interactions a student had with specific VLE material.
Distribution
This dataset comprises several relational tables, including
courses, assessments, vle, studentInfo, studentRegistration, studentAssessment, and studentVle. All tables are provided in the standard CSV format. While specific total row counts across all files are not specified, the structure is established via unique identifiers linking students, courses, assessments, and VLE interactions. Individual files, such as assessments.csv, contain hundreds of records.Usage
This resource is ideal for developing predictive models of student success or failure, studying the impact of assessment type and weighting on outcomes, and analysing engagement patterns within online learning environments. Potential use cases involve researching student retention rates, investigating differences in performance between February and October presentations, and mapping how demographic factors relate to academic achievement.
Coverage
The scope covers learning analytics for seven selected modules presented by the Open University. Data presentations typically begin in February or October. Demographic coverage is robust, including details on student gender, age band, highest education level on entry, disability status, and geographic region. Time data is recorded relative to the start date of the module presentation (day 0) for registrations, submissions, and VLE interactions.
License
Attribution 4.0 International (CC BY 4.0)
Who Can Use It
- Academics and Researchers: To study pedagogy, learning analytics, and distance education efficacy.
- Educational Data Scientists: To build machine learning models predicting student outcomes (e.g., withdrawal risk or final grade).
- Policy Makers: To inform decisions regarding course structure, assessment design, and support for diverse student populations.
Dataset Name Suggestions
- Open University Learning Analytics (OULAD)
- OULAD Student Performance and VLE Interaction Data
- Higher Education E-Learning Analytics
- Student Retention and Assessment Results
Attributes
Original Data Source: Higher Education E-Learning Analytics
QUALITYLoading...