BAYER, Jaroslav, Hana BYDŽOVSKÁ, Jan GÉRYK, Tomáš OBŠÍVAČ and Lubomír POPELÍNSKÝ. Predicting drop-out from social behaviour of students. In Kalina Yacef, Osmar Zaïane, Arnon Hershkovitz, Michael Yudelson and John Stamper. Proceedings of the 5th International Conference on Educational Data Mining - EDM 2012. Greece: www.educationaldatamining.org. p. 103 - 109. ISBN 978-1-74210-276-4. 2012.
Other formats:   BibTeX LaTeX RIS
Basic information
Original name Predicting drop-out from social behaviour of students
Authors BAYER, Jaroslav (203 Czech Republic, belonging to the institution), Hana BYDŽOVSKÁ (203 Czech Republic, belonging to the institution), Jan GÉRYK (203 Czech Republic, belonging to the institution), Tomáš OBŠÍVAČ (203 Czech Republic, belonging to the institution) and Lubomír POPELÍNSKÝ (203 Czech Republic, guarantor, belonging to the institution).
Edition Greece, Proceedings of the 5th International Conference on Educational Data Mining - EDM 2012, p. 103 - 109, 7 pp. 2012.
Publisher www.educationaldatamining.org
Other information
Original language English
Type of outcome Proceedings paper
Field of Study 10201 Computer sciences, information science, bioinformatics
Country of publisher Greece
Confidentiality degree is not subject to a state or trade secret
Publication form electronic version available online
RIV identification code RIV/00216224:14330/12:00060271
Organization unit Faculty of Informatics
ISBN 978-1-74210-276-4
Keywords in English data mining; study-related data; social behaviour data; social network analysis
Tags best3
Tags International impact, Reviewed
Changed by Changed by: RNDr. Hana Bydžovská, Ph.D., učo 139544. Changed: 16/10/2014 08:50.
Abstract
This paper focuses on predicting drop-out and school failure when student data has been enriched with data derived from students social behaviour. These data describe social dependencies gathered from e-mail and discussion boards conversation, among other sources. We describe an extraction of new features from both student data and behaviour data (or more precisely from social graph which we construct). Then we introduce a novel method for learning classier for student failure prediction that employs cost-sensitive learning to lower the number of incorrectly classified unsuccessful students. We show that a use of social behaviour data results in significant prediction accuracy increase.
Links
LA09016, research and development projectName: Účast ČR v European Research Consortium for Informatics and Mathematics (ERCIM) (Acronym: ERCIM)
Investor: Ministry of Education, Youth and Sports of the CR, Czech Republic membership in the European Research Consortium for Informatics and Mathematics
PrintDisplayed: 28/3/2024 13:17