ReaderBench Learns Dutch: Building a Comprehensive Automated Essay Scoring System for Dutch Language

Mihai Dascalu, W. Westera, Stefan Ruseti, Stefan Trausan-Matu, H.J. Kurvers

Research output: Chapter in Book/Report/Conference proceedingConference article in proceedingAcademicpeer-review

Abstract

Automated Essay Scoring has gained a wider applicability and usage with the integration of advanced Natural Language Processing techniques which enabled in-depth analyses of discourse in order capture the specificities of written texts. In this paper, we introduce a novel Automatic Essay Scoring method for Dutch language, built within the Readerbench framework, which encompasses a wide range of textual complexity indices, as well as an automated segmentation approach. Our method was evaluated on a corpus of 173 technical reports automatically split into sections and subsections, thus forming a hierarchical structure on which textual complexity indices were subsequently applied. The stepwise regression model explained 30.5% of the variance in students’ scores, while a Discriminant Function Analysis predicted with substantial accuracy (75.1%) whether they are high or low performance students.
Original languageEnglish
Title of host publicationArtificial Intelligence in Education
Subtitle of host publication18th International Conference, AIED 2017, Wuhan, China, June 28 – July 1, 2017, Proceedings
EditorsElisabeth André , Ryan Baker, Xiangen Hu, Ma. Mercedes T. Rodrigo , Benedict du Boulay
PublisherSpringer International Publishing AG
Pages52-63
Edition1
ISBN (Electronic)978-3-319-61425-0
ISBN (Print)978-3-319-61424-3
DOIs
Publication statusPublished - 2017
EventArtificial Intelligence in Education: 18th International Conference, AIED 2017, Wuhan, China, June 28 – July 1, 2017 - Wuhan, China
Duration: 28 Jun 20171 Jul 2017
http://119.97.166.163/

Publication series

NameLecture Notes in Artificial Intelligence
Publisherspringer
Volume10331

Conference

ConferenceArtificial Intelligence in Education
Abbreviated titleAIED 2017
CountryChina
CityWuhan
Period28/06/171/07/17
Internet address

Fingerprint

Students
Processing

Keywords

  • Automated essay scoring
  • textual complexity assessment
  • academic performance
  • Readerbench framework
  • Dutch semantic models
  • Games
  • Learning

Cite this

Dascalu, M., Westera, W., Ruseti, S., Trausan-Matu, S., & Kurvers, H. J. (2017). ReaderBench Learns Dutch: Building a Comprehensive Automated Essay Scoring System for Dutch Language. In E. André , R. Baker, X. Hu, M. M. T. Rodrigo , & B. du Boulay (Eds.), Artificial Intelligence in Education: 18th International Conference, AIED 2017, Wuhan, China, June 28 – July 1, 2017, Proceedings (1 ed., pp. 52-63). [5] (Lecture Notes in Artificial Intelligence; Vol. 10331). Springer International Publishing AG. https://doi.org/10.1007/978-3-319-61425-0_5
Dascalu, Mihai ; Westera, W. ; Ruseti, Stefan ; Trausan-Matu, Stefan ; Kurvers, H.J. / ReaderBench Learns Dutch : Building a Comprehensive Automated Essay Scoring System for Dutch Language. Artificial Intelligence in Education: 18th International Conference, AIED 2017, Wuhan, China, June 28 – July 1, 2017, Proceedings. editor / Elisabeth André ; Ryan Baker ; Xiangen Hu ; Ma. Mercedes T. Rodrigo ; Benedict du Boulay . 1. ed. Springer International Publishing AG, 2017. pp. 52-63 (Lecture Notes in Artificial Intelligence).
@inproceedings{69327f76c5c74278af3d591f33d2bcff,
title = "ReaderBench Learns Dutch: Building a Comprehensive Automated Essay Scoring System for Dutch Language",
abstract = "Automated Essay Scoring has gained a wider applicability and usage with the integration of advanced Natural Language Processing techniques which enabled in-depth analyses of discourse in order capture the specificities of written texts. In this paper, we introduce a novel Automatic Essay Scoring method for Dutch language, built within the Readerbench framework, which encompasses a wide range of textual complexity indices, as well as an automated segmentation approach. Our method was evaluated on a corpus of 173 technical reports automatically split into sections and subsections, thus forming a hierarchical structure on which textual complexity indices were subsequently applied. The stepwise regression model explained 30.5{\%} of the variance in students’ scores, while a Discriminant Function Analysis predicted with substantial accuracy (75.1{\%}) whether they are high or low performance students.",
keywords = "Automated essay scoring, textual complexity assessment, academic performance, Readerbench framework, Dutch semantic models, Games, Learning",
author = "Mihai Dascalu and W. Westera and Stefan Ruseti and Stefan Trausan-Matu and H.J. Kurvers",
year = "2017",
doi = "10.1007/978-3-319-61425-0_5",
language = "English",
isbn = "978-3-319-61424-3",
series = "Lecture Notes in Artificial Intelligence",
publisher = "Springer International Publishing AG",
pages = "52--63",
editor = "{Andr{\'e} }, Elisabeth and Ryan Baker and Xiangen Hu and {T. Rodrigo }, {Ma. Mercedes } and {du Boulay }, {Benedict }",
booktitle = "Artificial Intelligence in Education",
address = "Switzerland",
edition = "1",

}

Dascalu, M, Westera, W, Ruseti, S, Trausan-Matu, S & Kurvers, HJ 2017, ReaderBench Learns Dutch: Building a Comprehensive Automated Essay Scoring System for Dutch Language. in E André , R Baker, X Hu, MM T. Rodrigo & B du Boulay (eds), Artificial Intelligence in Education: 18th International Conference, AIED 2017, Wuhan, China, June 28 – July 1, 2017, Proceedings. 1 edn, 5, Lecture Notes in Artificial Intelligence, vol. 10331, Springer International Publishing AG, pp. 52-63, Artificial Intelligence in Education, Wuhan, China, 28/06/17. https://doi.org/10.1007/978-3-319-61425-0_5

ReaderBench Learns Dutch : Building a Comprehensive Automated Essay Scoring System for Dutch Language. / Dascalu, Mihai; Westera, W.; Ruseti, Stefan; Trausan-Matu, Stefan; Kurvers, H.J.

Artificial Intelligence in Education: 18th International Conference, AIED 2017, Wuhan, China, June 28 – July 1, 2017, Proceedings. ed. / Elisabeth André ; Ryan Baker; Xiangen Hu; Ma. Mercedes T. Rodrigo ; Benedict du Boulay . 1. ed. Springer International Publishing AG, 2017. p. 52-63 5 (Lecture Notes in Artificial Intelligence; Vol. 10331).

Research output: Chapter in Book/Report/Conference proceedingConference article in proceedingAcademicpeer-review

TY - GEN

T1 - ReaderBench Learns Dutch

T2 - Building a Comprehensive Automated Essay Scoring System for Dutch Language

AU - Dascalu, Mihai

AU - Westera, W.

AU - Ruseti, Stefan

AU - Trausan-Matu, Stefan

AU - Kurvers, H.J.

PY - 2017

Y1 - 2017

N2 - Automated Essay Scoring has gained a wider applicability and usage with the integration of advanced Natural Language Processing techniques which enabled in-depth analyses of discourse in order capture the specificities of written texts. In this paper, we introduce a novel Automatic Essay Scoring method for Dutch language, built within the Readerbench framework, which encompasses a wide range of textual complexity indices, as well as an automated segmentation approach. Our method was evaluated on a corpus of 173 technical reports automatically split into sections and subsections, thus forming a hierarchical structure on which textual complexity indices were subsequently applied. The stepwise regression model explained 30.5% of the variance in students’ scores, while a Discriminant Function Analysis predicted with substantial accuracy (75.1%) whether they are high or low performance students.

AB - Automated Essay Scoring has gained a wider applicability and usage with the integration of advanced Natural Language Processing techniques which enabled in-depth analyses of discourse in order capture the specificities of written texts. In this paper, we introduce a novel Automatic Essay Scoring method for Dutch language, built within the Readerbench framework, which encompasses a wide range of textual complexity indices, as well as an automated segmentation approach. Our method was evaluated on a corpus of 173 technical reports automatically split into sections and subsections, thus forming a hierarchical structure on which textual complexity indices were subsequently applied. The stepwise regression model explained 30.5% of the variance in students’ scores, while a Discriminant Function Analysis predicted with substantial accuracy (75.1%) whether they are high or low performance students.

KW - Automated essay scoring

KW - textual complexity assessment

KW - academic performance

KW - Readerbench framework

KW - Dutch semantic models

KW - Games

KW - Learning

U2 - 10.1007/978-3-319-61425-0_5

DO - 10.1007/978-3-319-61425-0_5

M3 - Conference article in proceeding

SN - 978-3-319-61424-3

T3 - Lecture Notes in Artificial Intelligence

SP - 52

EP - 63

BT - Artificial Intelligence in Education

A2 - André , Elisabeth

A2 - Baker, Ryan

A2 - Hu, Xiangen

A2 - T. Rodrigo , Ma. Mercedes

A2 - du Boulay , Benedict

PB - Springer International Publishing AG

ER -

Dascalu M, Westera W, Ruseti S, Trausan-Matu S, Kurvers HJ. ReaderBench Learns Dutch: Building a Comprehensive Automated Essay Scoring System for Dutch Language. In André E, Baker R, Hu X, T. Rodrigo MM, du Boulay B, editors, Artificial Intelligence in Education: 18th International Conference, AIED 2017, Wuhan, China, June 28 – July 1, 2017, Proceedings. 1 ed. Springer International Publishing AG. 2017. p. 52-63. 5. (Lecture Notes in Artificial Intelligence). https://doi.org/10.1007/978-3-319-61425-0_5