Data Mining and Learning Analytics

What is Data Mining?

• Definition: Process of transforming raw data into useful information.
• Usage: Analyzing large datasets (e.g., social media, healthcare, entertainment) to provide recommendations and targeted advertisements.
• Techniques:
  • Pattern mining
  • Process mining
  • Predictions
  • Correlations
  • Regressions
  • Algorithm development
• Applications:
  • Marketing/E-commerce: Product recommendations and targeted advertisements based on user behavior.
  • Credit Risk Management: Assessing credit ratings based on past behavior (loan history, repayment timeliness).
  • Educational Forums: Analyzing student interactions to provide meaningful feedback.

Educational Data Mining (EDM)

• Definition: Application of data mining algorithms to educational data to understand and enhance learning experiences.
• Objectives:
  • Analyze data from learning environments (classrooms, MOOCs) to understand students.
  • Provide adaptable content and better feedback for improved learning outcomes.
• Examples:
  • Developing learner models to predict test performance and course completion.
  • Identifying effective pedagogical strategies through data analysis (e.g., pretests, teaching methods).
  • Using data to inform institutional decisions (e.g., resource allocation, student engagement).

Academic Analytics

• Definition: Learning analytics applied at institutional, regional, or national levels to address student success and accountability.
• Purpose: Support operational and financial decision-making for stakeholders such as management and executives.
• Applications:
  • Analyzing LMS data to assess teacher and student interactions, course effectiveness.
  • Predicting school performance and resource needs based on historical data.

Differences Between Academic Analytics and Learning Analytics

• Academic Analytics:
  • Scope: High-level focus on institutional management and decision-making.
  • Stakeholders: Management executives, government officials.
  • Purpose: Improve education, develop districts, implement new educational methods.
• Learning Analytics:
  • Scope: Focus on individual student performance and specific learning goals.
  • Stakeholders: Students, instructors, researchers.
  • Purpose: Aid students in learning, achieve learning goals, and provide feedback to improve educational experiences.

Summary

• The course focuses on Learning Analytics (LA) and Educational Data Mining (EDM) interchangeably.
• Academic Analytics (business intelligence) is less emphasized in the course.