Exploring students' learning attributes in consecutive lessons to improve prediction performance

Shaymaa E. Sorour, Tsunenori Mine

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Citations (Scopus)

Abstract

Building an understandable student prediction model has an essential role to play in the educational environment. Most current prediction models are difficult for teachers to interpret. This poses problems for model use (e.g., improve student performance, interventions and allow a feedback process). In this paper, we propose a new approach in building a practical model by identifying a number of attributes in comment data that reflect students' learning attitudes, tendencies and activities involved with the lesson. We check the capability of an attributes representation model compared to the Latent Dirichlet Allocation (LDA) model that represents student comments as a statistical latent class 'Topics.' In addition, we employ a Multi-Instance Learning (MIL) method to all available information for each student to improve the efficiency and effectiveness of classical representation for each lesson to predict final student performance. Computational experiments show that when the model is regarded as MIL, the prediction performance achieves better results than those based on single instance representation for each lesson.

Original languageEnglish
Title of host publicationProceedings of the Australasian Computer Science Week Multiconference, ACSW 2016
PublisherAssociation for Computing Machinery
ISBN (Electronic)9781450340427
DOIs
Publication statusPublished - Feb 1 2016
EventAustralasian Computer Science Week Multiconference, ACSW 2016 - Canberra, Australia
Duration: Feb 1 2016Feb 5 2016

Publication series

NameACM International Conference Proceeding Series
Volume01-05-February-2016

Other

OtherAustralasian Computer Science Week Multiconference, ACSW 2016
CountryAustralia
CityCanberra
Period2/1/162/5/16

Fingerprint

Students
Feedback
Experiments

All Science Journal Classification (ASJC) codes

  • Software
  • Human-Computer Interaction
  • Computer Vision and Pattern Recognition
  • Computer Networks and Communications

Cite this

Sorour, S. E., & Mine, T. (2016). Exploring students' learning attributes in consecutive lessons to improve prediction performance. In Proceedings of the Australasian Computer Science Week Multiconference, ACSW 2016 [a2] (ACM International Conference Proceeding Series; Vol. 01-05-February-2016). Association for Computing Machinery. https://doi.org/10.1145/2843043.2843066

Exploring students' learning attributes in consecutive lessons to improve prediction performance. / Sorour, Shaymaa E.; Mine, Tsunenori.

Proceedings of the Australasian Computer Science Week Multiconference, ACSW 2016. Association for Computing Machinery, 2016. a2 (ACM International Conference Proceeding Series; Vol. 01-05-February-2016).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Sorour, SE & Mine, T 2016, Exploring students' learning attributes in consecutive lessons to improve prediction performance. in Proceedings of the Australasian Computer Science Week Multiconference, ACSW 2016., a2, ACM International Conference Proceeding Series, vol. 01-05-February-2016, Association for Computing Machinery, Australasian Computer Science Week Multiconference, ACSW 2016, Canberra, Australia, 2/1/16. https://doi.org/10.1145/2843043.2843066
Sorour SE, Mine T. Exploring students' learning attributes in consecutive lessons to improve prediction performance. In Proceedings of the Australasian Computer Science Week Multiconference, ACSW 2016. Association for Computing Machinery. 2016. a2. (ACM International Conference Proceeding Series). https://doi.org/10.1145/2843043.2843066
Sorour, Shaymaa E. ; Mine, Tsunenori. / Exploring students' learning attributes in consecutive lessons to improve prediction performance. Proceedings of the Australasian Computer Science Week Multiconference, ACSW 2016. Association for Computing Machinery, 2016. (ACM International Conference Proceeding Series).
@inproceedings{03db4377ad804a71aa4e8adc55d60fa4,
title = "Exploring students' learning attributes in consecutive lessons to improve prediction performance",
abstract = "Building an understandable student prediction model has an essential role to play in the educational environment. Most current prediction models are difficult for teachers to interpret. This poses problems for model use (e.g., improve student performance, interventions and allow a feedback process). In this paper, we propose a new approach in building a practical model by identifying a number of attributes in comment data that reflect students' learning attitudes, tendencies and activities involved with the lesson. We check the capability of an attributes representation model compared to the Latent Dirichlet Allocation (LDA) model that represents student comments as a statistical latent class 'Topics.' In addition, we employ a Multi-Instance Learning (MIL) method to all available information for each student to improve the efficiency and effectiveness of classical representation for each lesson to predict final student performance. Computational experiments show that when the model is regarded as MIL, the prediction performance achieves better results than those based on single instance representation for each lesson.",
author = "Sorour, {Shaymaa E.} and Tsunenori Mine",
year = "2016",
month = "2",
day = "1",
doi = "10.1145/2843043.2843066",
language = "English",
series = "ACM International Conference Proceeding Series",
publisher = "Association for Computing Machinery",
booktitle = "Proceedings of the Australasian Computer Science Week Multiconference, ACSW 2016",

}

TY - GEN

T1 - Exploring students' learning attributes in consecutive lessons to improve prediction performance

AU - Sorour, Shaymaa E.

AU - Mine, Tsunenori

PY - 2016/2/1

Y1 - 2016/2/1

N2 - Building an understandable student prediction model has an essential role to play in the educational environment. Most current prediction models are difficult for teachers to interpret. This poses problems for model use (e.g., improve student performance, interventions and allow a feedback process). In this paper, we propose a new approach in building a practical model by identifying a number of attributes in comment data that reflect students' learning attitudes, tendencies and activities involved with the lesson. We check the capability of an attributes representation model compared to the Latent Dirichlet Allocation (LDA) model that represents student comments as a statistical latent class 'Topics.' In addition, we employ a Multi-Instance Learning (MIL) method to all available information for each student to improve the efficiency and effectiveness of classical representation for each lesson to predict final student performance. Computational experiments show that when the model is regarded as MIL, the prediction performance achieves better results than those based on single instance representation for each lesson.

AB - Building an understandable student prediction model has an essential role to play in the educational environment. Most current prediction models are difficult for teachers to interpret. This poses problems for model use (e.g., improve student performance, interventions and allow a feedback process). In this paper, we propose a new approach in building a practical model by identifying a number of attributes in comment data that reflect students' learning attitudes, tendencies and activities involved with the lesson. We check the capability of an attributes representation model compared to the Latent Dirichlet Allocation (LDA) model that represents student comments as a statistical latent class 'Topics.' In addition, we employ a Multi-Instance Learning (MIL) method to all available information for each student to improve the efficiency and effectiveness of classical representation for each lesson to predict final student performance. Computational experiments show that when the model is regarded as MIL, the prediction performance achieves better results than those based on single instance representation for each lesson.

UR - http://www.scopus.com/inward/record.url?scp=84962564473&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84962564473&partnerID=8YFLogxK

U2 - 10.1145/2843043.2843066

DO - 10.1145/2843043.2843066

M3 - Conference contribution

AN - SCOPUS:84962564473

T3 - ACM International Conference Proceeding Series

BT - Proceedings of the Australasian Computer Science Week Multiconference, ACSW 2016

PB - Association for Computing Machinery

ER -