Can an Intelligent Tutoring System Predict Math Proficiency as Well as a Standardized Test

作者: Kenneth R. Koedinger , Neil T. Heffernan , Mingyu Feng , Joseph E. Beck

DOI:

关键词:

摘要: It has been reported in previous work that students' online tutoring data collected from intelligent systems can be used to build models predict actual state test scores. In this paper, we replicated a study model math proficiency by taking into consideration response during the session and their help-seeking behavior. To extend our work, propose new method of using students scores multiple years (referred as cross-year data) for determining whether student is good standardized which it compared at estimating proficiency. We show do well test. what assess prediction ability two later. stress contribution paper methodology score evaluate against

参考文章(11)
June Sison, Joseph E. Beck, Using Knowledge Tracing in a Noisy Environment to Measure Student Reading Proficiencies artificial intelligence in education. ,vol. 16, pp. 129- 143 ,(2006) , 10.5555/1435344.1435347
Neil T. Heffernan, Mingyu Feng, Towards Live Informing and Automatic Analyzing of Student Learning: Reporting in ASSISTment System The Journal of Interactive Learning Research. ,vol. 18, pp. 207- 230 ,(2007)
Steven P. Reise, Susan E. Embretson, Item response theory for psychologists ,(2000)
Adrian E. Raftery, Bayesian Model Selection in Social Research Sociological Methodology. ,vol. 25, pp. 111- ,(1995) , 10.2307/271063
Mingyu Feng, Neil T. Heffernan, Kenneth R. Koedinger, Predicting State Test Scores Better with Intelligent Tutoring Systems: Developing Metrics to Measure Assistance Required Intelligent Tutoring Systems. pp. 31- 40 ,(2006) , 10.1007/11774303_4
Mingyu Feng, Neil T. Heffernan, Kenneth R. Koedinger, Addressing the testing challenge with a web-based e-assessment system that tutors as it assesses Proceedings of the 15th international conference on World Wide Web - WWW '06. pp. 307- 316 ,(2006) , 10.1145/1135777.1135825