DeepSData
Dataset guide · 机器学习与语料

E-learning Recommender System Dataset

Mandarine Academy Recommender System (MARS) Dataset from Harvard Dataverse, containing explicit and implicit ratings for both French and English versions of a real-world MOOC platform.

← Back to dataset library · 中文版

机器学习与语料Free to access

Key facts

InstitutionHarvard Dataverse
CoverageMandarine Academy MOOC platform (French and English versions)
Time spanSee official page
Scale8 files
LicenseLicense pending verification
AccessHarvard Dataverse

Contents & fields

The dataset includes users, items, explicit ratings, and implicit ratings in CSV files for both French and English versions. User IDs and item IDs are consistent across files. Fields include:

  • user_id——Unique user identifier
  • job——User's job (if available)
  • item_id——Unique item identifier
  • language——Item language (French or English)
  • name——Item name
  • nb_views——Number of views of the item
  • description——Item description
  • created_at——Timestamp of rating or item creation
  • Difficulty——Item difficulty
  • Job——Job related to the item
  • Software——Software related to the item
  • Theme——Item theme
  • duration——Item duration
  • type——Item type
  • watch_percentage——Watch percentage (explicit ratings)
  • rating——Explicit rating value

Research uses

Suitable for recommender system research in education, especially algorithm evaluation based on explicit and implicit feedback, and comparison of recommendation effectiveness in multilingual environments.

This card was drafted from the source page; institution, coverage, time span, scale, fields and license are subject to the official page (pending human review).

Keywords

recommender systemeducational dataMOOCexplicit ratingimplicit feedbackmultilingual

Access & license

License: License pending verification | Free to access

Why this is hard to get on your own

Educational recommender system datasets are scarce, especially those with both explicit and implicit feedback in a multilingual context.

Related datasets

Same domain

Need this data retrieved and prepared?

Tell us your hard requirements. We first assess availability, then retrieve for real — and if it truly cannot be obtained, we say so plainly.