Knowledge Tracing

Mining Massive Student Data with Deep Learning

What is Knowledge Tracing?

In this project, we aim to mine a large amount of real educational data and develop knowledge tracing and adaptive assessment models. In particular, we are focused on

  • Developing better models to predict students’ answers to questions based on their previous actions and responses.
  • Given effective knowledge tracing algorithms, devising ways to build models upon them to sequence material in ways maximally useful for students.
  • Using the text of questions and answers to perform natural-language analysis and experiment with augmenting knowledge-tracing and other algorithms to be able to incorporate new questions (which were not included in training data) into the software.
  • Using official score reports to study to what degree it is possible to predict students’ real test scores based on their interactions with the software.