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.

Základní údaje

Originální název

Predicting drop-out from social behaviour of students

Autoři

BAYER, Jaroslav (203 Česká republika, domácí), Hana BYDŽOVSKÁ (203 Česká republika, domácí), Jan GÉRYK (203 Česká republika, domácí), Tomáš OBŠÍVAČ (203 Česká republika, domácí) a Lubomír POPELÍNSKÝ (203 Česká republika, garant, domácí)

Vydání

Greece, Proceedings of the 5th International Conference on Educational Data Mining - EDM 2012, od s. 103 - 109, 7 s. 2012

Nakladatel

www.educationaldatamining.org

Další údaje

Jazyk

angličtina

Typ výsledku

Stať ve sborníku

Obor

10201 Computer sciences, information science, bioinformatics

Stát vydavatele

Řecko

Utajení

není předmětem státního či obchodního tajemství

Forma vydání

elektronická verze "online"

Kód RIV

RIV/00216224:14330/12:00060271

Organizační jednotka

Fakulta informatiky

ISBN

978-1-74210-276-4

Klíčová slova anglicky

data mining; study-related data; social behaviour data; social network analysis

Štítky

best3

Příznaky

Mezinárodní význam, Recenzováno

Změněno: 16. 10. 2014 08:50, RNDr. Hana Bydžovská, Ph.D.

Anotace

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.

Návaznosti

LA09016, projekt VaV

Název: Účast ČR v European Research Consortium for Informatics and Mathematics (ERCIM) (Akronym: ERCIM)

Investor: Ministerstvo školství, mládeže a tělovýchovy ČR, Účast ČR v European Research Consortium for Informatics and Mathematics

Citovat

BAYER, Jaroslav, Hana BYDŽOVSKÁ, Jan GÉRYK, Tomáš OBŠÍVAČ a 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, s. 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 a 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, s.~103 - 109. ISBN~978-1-74210-276-4.

Podrobný výpis o publikaci