Predicting drop-out from social behaviour of students

D 2012

Predicting drop-out from social behaviour of students

BAYER, Jaroslav, Hana BYDŽOVSKÁ, Jan GÉRYK, Tomáš OBŠÍVAČ, Lubomír POPELÍNSKÝ et. al.

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

Language

English

Type of outcome

Stať ve sborníku

Field of Study

10201 Computer sciences, information science, bioinformatics

Country of publisher

Greece

Confidentiality degree

není předmětem státního či obchodního tajemství

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

Abstract

V originále

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 project

Name: 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

Citovat

BAYER, Jaroslav, Hana BYDŽOVSKÁ, Jan GÉRYK, Tomáš OBŠÍVAČ and Lubomír POPELÍNSKÝ. Predicting drop-out from social behaviour of students. Online. 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, 2012, p. 103 - 109. ISBN 978-1-74210-276-4.

@inproceedings{985903,
   author = {Bayer, Jaroslav and Bydžovská, Hana and Géryk, Jan and Obšívač, Tomáš and Popelínský, Lubomír},
   address = {Greece},
   booktitle = {Proceedings of the 5th International Conference on Educational Data Mining - EDM 2012},
   editor = {Kalina Yacef, Osmar Zaïane, Arnon Hershkovitz, Michael Yudelson and John Stamper},
   keywords = {data mining; study-related data; social behaviour data; social network analysis},
   howpublished = {elektronická verze "online"},
   language = {eng},
   location = {Greece},
   isbn = {978-1-74210-276-4},
   pages = {103 - 109},
   publisher = {www.educationaldatamining.org},
   title = {Predicting drop-out from social behaviour of students},
   year = {2012}
}

TY  - JOUR
ID  - 985903
AU  - Bayer, Jaroslav - Bydžovská, Hana - Géryk, Jan - Obšívač, Tomáš - Popelínský, Lubomír
PY  - 2012
TI  - Predicting drop-out from social behaviour of students
PB  - www.educationaldatamining.org
CY  - Greece
SN  - 9781742102764
KW  - data mining
KW  - study-related data
KW  - social behaviour data
KW  - social network analysis
N2  - 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.
ER  -

BAYER, Jaroslav, Hana BYDŽOVSKÁ, Jan GÉRYK, Tomáš OBŠÍVAČ and Lubomír POPELÍNSKÝ. Predicting drop-out from social behaviour of students. Online. In Kalina Yacef, Osmar Zaïane, Arnon Hershkovitz, Michael Yudelson and John Stamper. \textit{Proceedings of the 5th International Conference on Educational Data Mining - EDM 2012}. Greece: www.educationaldatamining.org, 2012, p.~103 - 109. ISBN~978-1-74210-276-4.

Detailed Information on Publication Record