What and When do Students Learn? Fully Data-Driven Joint Estimation of Cognitive and Student Models
نویسندگان
چکیده
We present the Topical Hidden Markov Model method, which infers jointly a cognitive and student model from longitudinal observations of student performance. Its cognitive diagnostic component specifies which items use which skills. Its knowledge tracing component specifies how to infer students’ knowledge of these skills from their observed performance. Unlike prior work, it uses no expert engineered domain knowledge — yet predicts future student performance in an algebra tutor as accurately as a published expert model.
منابع مشابه
Peer-Assessment and Student-Driven Negotiation of Meaning: Two Ingredients for Creating Social Presence in Online EFL Social Contexts
With the current availability of state-of-the-art technology, particularly the Internet, people have expanded their channels of communication. This has similarly led to many people utilizing technology to learn second/foreign languages. Nevertheless, many current computer-assisted language learning (CALL) programs still appear to be lacking in interactivity and what is termed social presence, w...
متن کاملWhat and When Do Students Learn? Methods For Knowledge Tracing With Data-Driven Mapping of Items to Skills
Recent interest in online education, such as Massively Open Online Courses and intelligent tutoring systems, promises large amounts of data from students solving items at different levels of proficiency over time. Existing approaches for inferring students’ knowledge from data require a cognitive model – a mapping between the tutor problems and the set of skills they require. This is a very exp...
متن کاملVirtual Space as a Platform for Student Research Practices
Online learning is becoming an increasingly popular request. Many universities are moving fully or partially to this form of study. In the article, the authors considered what is virtual space, what are its criteria, as well as applicability for teaching students and passing research practices. Based on an analysis of existing virtual spaces (platforms), an experiment was conducted. The study s...
متن کاملWhat makes a good clinical student and teacher? An exploratory study
BACKGROUND What makes a good clinical student is an area that has received little coverage in the literature and much of the available literature is based on essays and surveys. It is particularly relevant as recent curricular innovations have resulted in greater student autonomy. We also wished to look in depth at what makes a good clinical teacher. METHODS A qualitative approach using indiv...
متن کاملModeling Students' Metacognitive Errors in Two Intelligent Tutoring Systems
Intelligent tutoring systems help students acquire cognitive skills by tracing students’ knowledge and providing relevant feedback. However, feedback that focuses only on the cognitive level might not be optimal errors are often the result of inappropriate metacognitive decisions. We have developed two models which detect aspects of student faulty metacognitive behavior: A prescriptive rational...
متن کامل