dc.contributor.author | Saarela, Mirka | |
dc.contributor.author | Yener, Bülent | |
dc.contributor.author | Zaki, Mohammed J. | |
dc.contributor.author | Kärkkäinen, Tommi | |
dc.contributor.editor | Balcan, Maria Florina | |
dc.contributor.editor | Weinberger, Kilian Q. | |
dc.date.accessioned | 2017-01-02T07:22:16Z | |
dc.date.available | 2017-01-02T07:22:16Z | |
dc.date.issued | 2016 | |
dc.identifier.citation | Saarela, M., Yener, B., Zaki, M. J., & Kärkkäinen, T. (2016). Predicting Math Performance from Raw Large-Scale Educational Assessments Data : A Machine Learning Approach. In M. F. Balcan, & K. Q. Weinberger (Eds.), <i>MLDEAS workshop papers of the 33rd International Conference on Machine Learning (ICML 2016 Workshop)</i> (pp. 1-8). JMLR. JMLR Workshop and Conference Proceedings, 48. <a href="http://medianetlab.ee.ucla.edu/papers/ICMLWS3.pdf" target="_blank">http://medianetlab.ee.ucla.edu/papers/ICMLWS3.pdf</a> | |
dc.identifier.other | CONVID_26401335 | |
dc.identifier.other | TUTKAID_72195 | |
dc.identifier.uri | https://jyx.jyu.fi/handle/123456789/52562 | |
dc.description.abstract | Large-scale educational assessment studies
(LSAs) regularly collect massive amounts of
very rich cognitive and contextual data of whole
student populations. Currently, LSAs are limited
to reporting student proficiencies in the form of
plausible values (PVs). PVs are random draws
from the posterior distribution of a student’s
ability, which is based on the Bayesian approach
with the prior distribution modeling the student
background within the population and the
likelihood test item response using the Rasch
model. While PVs have shown to be a reliable
estimate for proficiencies of populations, a more
comprehensive study of these rich data sets by
deploying machine learning algorithms may
provide a better understanding of the underlying
factors affecting student performance and thus
yield to better and more interpretable predictive
models. This paper presents such a novel
approach to learn directly from LSA data by
deploying a combination of both unsupervised
and supervised learning feature selection algorithms
to predict student performance on math
scores. Our technique learns the difficulty level
of different math questions and predicts weather
or not a student with a particular background
profile will be successful in answering correctly. | |
dc.language.iso | eng | |
dc.publisher | JMLR | |
dc.relation.ispartof | MLDEAS workshop papers of the 33rd International Conference on Machine Learning (ICML 2016 Workshop) | |
dc.relation.ispartofseries | JMLR Workshop and Conference Proceedings | |
dc.relation.uri | http://medianetlab.ee.ucla.edu/papers/ICMLWS3.pdf | |
dc.subject.other | large-scale educational assessments | |
dc.title | Predicting Math Performance from Raw Large-Scale Educational Assessments Data : A Machine Learning Approach | |
dc.type | conferenceObject | |
dc.identifier.urn | URN:NBN:fi:jyu-201612205202 | |
dc.contributor.laitos | Tietotekniikan laitos | fi |
dc.contributor.laitos | Department of Mathematical Information Technology | en |
dc.contributor.oppiaine | Tietotekniikka | fi |
dc.contributor.oppiaine | Mathematical Information Technology | en |
dc.type.uri | http://purl.org/eprint/type/ConferencePaper | |
dc.date.updated | 2016-12-20T16:15:08Z | |
dc.type.coar | conference paper | |
dc.description.reviewstatus | peerReviewed | |
dc.format.pagerange | 1-8 | |
dc.relation.issn | 1938-7288 | |
dc.type.version | publishedVersion | |
dc.rights.copyright | © the Authors, 2016. | |
dc.rights.accesslevel | openAccess | fi |
dc.relation.conference | International Conference on Machine Learning | |