Methoden vergleichen
Prüfen Sie die ausgewählten Methoden nebeneinander; abweichende Zeilen sind hervorgehoben.
| Educational Data Mining× | Bayesian Knowledge Tracing× | |
|---|---|---|
| Fachgebiet | Education | Education |
| Familie | Machine learning | Machine learning |
| Entstehungsjahr≠ | 2009 | 1994 |
| Urheber≠ | Educational data mining community (Baker, Yacef, Romero, Ventura) | Albert Corbett & John Anderson |
| Typ≠ | Application of data-mining and machine-learning methods to educational data | Two-state hidden Markov model of latent skill mastery from response sequences |
| Wegweisende Quelle≠ | Baker, R. S. J. d., & Yacef, K. (2009). The state of educational data mining in 2009: A review and future visions. Journal of Educational Data Mining, 1(1), 3–17. link ↗ | Corbett, A. T., & Anderson, J. R. (1994). Knowledge tracing: Modeling the acquisition of procedural knowledge. User Modeling and User-Adapted Interaction, 4(4), 253–278. DOI ↗ |
| Aliasnamen | EDM, Mining Education Data, Data Mining in Education, Learner Data Mining | BKT, Knowledge Tracing (Corbett-Anderson), Hidden Markov Knowledge Tracing, Skill Mastery Tracing |
| Verwandt≠ | 4 | 3 |
| Zusammenfassung≠ | Educational data mining (EDM) is the field that develops and applies data-mining and machine-learning methods to data generated by educational settings — clickstreams from online courses, intelligent tutoring system logs, assessment records, and student information systems. Its goal is to discover patterns that explain and predict learning: who is at risk of failing, how students work through material, which content sequences help, and what hidden skill structures underlie performance. EDM treats fine-grained learner data as a source of actionable scientific and practical insight. | Bayesian knowledge tracing (BKT) is a model that estimates, after each problem a student attempts, the probability that the student has mastered the underlying skill. Introduced by Corbett and Anderson for intelligent tutoring systems, it is a two-state hidden Markov model: the latent variable is whether the skill is learned or not, and observed correct/incorrect responses update that latent state through Bayesian inference. With just four parameters — initial knowledge, learning, slip, and guess — BKT drives the mastery decisions that tell a tutor when a student can move on. |
| ScholarGateDatensatz ↗ |
|
|