Hierarchical text classification for supporting educational programs

Qi Ju, Chiara Ravagni, Alessandro Moschitti, Giampiero Vaschetto

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

Abstract

More than two decades have passed since the first design of the CONSTRUE system [2], a powerful rule-based model for the categorization of Reuters news. Nowadays, statistical approaches are well assessed and they allow for an easy design of text classification (TC) systems. Additionally, the Web has emphasized the need of approaches for digesting large amount of textual information and making it more easily accessible, e.g., thorough hierarchical taxonomies like Dmoz or Yahoo! categories. Surprisingly, automated approaches have not proved yet to be indispensable for such categorization processes. This suggests that the role of TC might be different from simply routing documents to different topical categories. In this paper, we provide evidence of the promising use of TC as a support for an interesting and high level human activity in the educational context. The latter refers to the selection and definition of educational programs tailored on specific needs of pupils, who sometime require particular attention and actions to solve their learning problems. TC in this context is exploited to automatically extract several aspects and properties from learning objects, i.e., didactic material, in terms of semantic labels. These can be used to organized the different pieces of material in specific didactic program, which can address specific deficiencies of pupils. The TC experiments, carried out with state-of-the-art algorithms and a small set of training data, show that automatic classifiers can easily derive labels like, didactic context, school matter, pupil difficulties and educative solution type.

Original languageEnglish
Title of host publicationCEUR Workshop Proceedings
Pages18-25
Number of pages8
Volume835
Publication statusPublished - 2012
Externally publishedYes
Event3rd Italian Information Retrieval Workshop, IIR 2012 - Bari, Italy
Duration: 26 Jan 201227 Jan 2012

Other

Other3rd Italian Information Retrieval Workshop, IIR 2012
CountryItaly
CityBari
Period26/1/1227/1/12

Fingerprint

Labels
Taxonomies
Classifiers
Semantics
Experiments

Keywords

  • E-learning
  • Hierarchical text classification
  • Information management applications

ASJC Scopus subject areas

  • Computer Science(all)

Cite this

Ju, Q., Ravagni, C., Moschitti, A., & Vaschetto, G. (2012). Hierarchical text classification for supporting educational programs. In CEUR Workshop Proceedings (Vol. 835, pp. 18-25)

Hierarchical text classification for supporting educational programs. / Ju, Qi; Ravagni, Chiara; Moschitti, Alessandro; Vaschetto, Giampiero.

CEUR Workshop Proceedings. Vol. 835 2012. p. 18-25.

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

Ju, Q, Ravagni, C, Moschitti, A & Vaschetto, G 2012, Hierarchical text classification for supporting educational programs. in CEUR Workshop Proceedings. vol. 835, pp. 18-25, 3rd Italian Information Retrieval Workshop, IIR 2012, Bari, Italy, 26/1/12.
Ju Q, Ravagni C, Moschitti A, Vaschetto G. Hierarchical text classification for supporting educational programs. In CEUR Workshop Proceedings. Vol. 835. 2012. p. 18-25
Ju, Qi ; Ravagni, Chiara ; Moschitti, Alessandro ; Vaschetto, Giampiero. / Hierarchical text classification for supporting educational programs. CEUR Workshop Proceedings. Vol. 835 2012. pp. 18-25
@inproceedings{4f0a42a69b3a4a0880135d264ed7fde0,
title = "Hierarchical text classification for supporting educational programs",
abstract = "More than two decades have passed since the first design of the CONSTRUE system [2], a powerful rule-based model for the categorization of Reuters news. Nowadays, statistical approaches are well assessed and they allow for an easy design of text classification (TC) systems. Additionally, the Web has emphasized the need of approaches for digesting large amount of textual information and making it more easily accessible, e.g., thorough hierarchical taxonomies like Dmoz or Yahoo! categories. Surprisingly, automated approaches have not proved yet to be indispensable for such categorization processes. This suggests that the role of TC might be different from simply routing documents to different topical categories. In this paper, we provide evidence of the promising use of TC as a support for an interesting and high level human activity in the educational context. The latter refers to the selection and definition of educational programs tailored on specific needs of pupils, who sometime require particular attention and actions to solve their learning problems. TC in this context is exploited to automatically extract several aspects and properties from learning objects, i.e., didactic material, in terms of semantic labels. These can be used to organized the different pieces of material in specific didactic program, which can address specific deficiencies of pupils. The TC experiments, carried out with state-of-the-art algorithms and a small set of training data, show that automatic classifiers can easily derive labels like, didactic context, school matter, pupil difficulties and educative solution type.",
keywords = "E-learning, Hierarchical text classification, Information management applications",
author = "Qi Ju and Chiara Ravagni and Alessandro Moschitti and Giampiero Vaschetto",
year = "2012",
language = "English",
volume = "835",
pages = "18--25",
booktitle = "CEUR Workshop Proceedings",

}

TY - GEN

T1 - Hierarchical text classification for supporting educational programs

AU - Ju, Qi

AU - Ravagni, Chiara

AU - Moschitti, Alessandro

AU - Vaschetto, Giampiero

PY - 2012

Y1 - 2012

N2 - More than two decades have passed since the first design of the CONSTRUE system [2], a powerful rule-based model for the categorization of Reuters news. Nowadays, statistical approaches are well assessed and they allow for an easy design of text classification (TC) systems. Additionally, the Web has emphasized the need of approaches for digesting large amount of textual information and making it more easily accessible, e.g., thorough hierarchical taxonomies like Dmoz or Yahoo! categories. Surprisingly, automated approaches have not proved yet to be indispensable for such categorization processes. This suggests that the role of TC might be different from simply routing documents to different topical categories. In this paper, we provide evidence of the promising use of TC as a support for an interesting and high level human activity in the educational context. The latter refers to the selection and definition of educational programs tailored on specific needs of pupils, who sometime require particular attention and actions to solve their learning problems. TC in this context is exploited to automatically extract several aspects and properties from learning objects, i.e., didactic material, in terms of semantic labels. These can be used to organized the different pieces of material in specific didactic program, which can address specific deficiencies of pupils. The TC experiments, carried out with state-of-the-art algorithms and a small set of training data, show that automatic classifiers can easily derive labels like, didactic context, school matter, pupil difficulties and educative solution type.

AB - More than two decades have passed since the first design of the CONSTRUE system [2], a powerful rule-based model for the categorization of Reuters news. Nowadays, statistical approaches are well assessed and they allow for an easy design of text classification (TC) systems. Additionally, the Web has emphasized the need of approaches for digesting large amount of textual information and making it more easily accessible, e.g., thorough hierarchical taxonomies like Dmoz or Yahoo! categories. Surprisingly, automated approaches have not proved yet to be indispensable for such categorization processes. This suggests that the role of TC might be different from simply routing documents to different topical categories. In this paper, we provide evidence of the promising use of TC as a support for an interesting and high level human activity in the educational context. The latter refers to the selection and definition of educational programs tailored on specific needs of pupils, who sometime require particular attention and actions to solve their learning problems. TC in this context is exploited to automatically extract several aspects and properties from learning objects, i.e., didactic material, in terms of semantic labels. These can be used to organized the different pieces of material in specific didactic program, which can address specific deficiencies of pupils. The TC experiments, carried out with state-of-the-art algorithms and a small set of training data, show that automatic classifiers can easily derive labels like, didactic context, school matter, pupil difficulties and educative solution type.

KW - E-learning

KW - Hierarchical text classification

KW - Information management applications

UR - http://www.scopus.com/inward/record.url?scp=84892164421&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84892164421&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84892164421

VL - 835

SP - 18

EP - 25

BT - CEUR Workshop Proceedings

ER -