Automatic Arabic Short Answers Scoring Using Longest Common Subsequence and Arabic WordNet

Hikmat A. Abdeljaber

doi:10.1109/ACCESS.2021.3082408

Automatic Arabic Short Answers Scoring Using Longest Common Subsequence and Arabic WordNet

Hikmat A. Abdeljaber

Computer Sciences

Research output: Contribution to journal › Article › peer-review

16 Scopus citations

Abstract

The manual process of scoring short answers of Arabic essay questions is exhaustive, susceptible to error and consumes instructor's time and resources. This paper explores longest common subsequence (LCS) algorithm as a string-based text similarity measure for effectively scoring short answers of Arabic essay questions. To achieve this effectiveness, the longest common subsequence is modified by developing weight-based measurement techniques and implemented along with using Arabic WordNet for scoring Arabic short answers. The experiments conducted on a dataset of 330 students' answers reported Root Mean Square Error (RMSE) value of 0.81 and Pearson correlation r value of 0.94. Findings based on experiments have shown improvements in the accuracy of performance of the proposed approach compared to similar studies. Moreover, the statistical analysis has shown that the proposed method scores students' answers similar to that of human estimator.

Original language	English
Article number	9437188
Pages (from-to)	76433-76445
Number of pages	13
Journal	IEEE Access
Volume	9
DOIs	https://doi.org/10.1109/ACCESS.2021.3082408
State	Published - 2021

Keywords

Arabic short answers scoring
arabic wordnet
automatic essay scoring
longest common subsequence
string-based text similarity

Access to Document

10.1109/ACCESS.2021.3082408

Cite this

@article{2fa539dcdcd34f4aba4abed24bec883f,

title = "Automatic Arabic Short Answers Scoring Using Longest Common Subsequence and Arabic WordNet",

abstract = "The manual process of scoring short answers of Arabic essay questions is exhaustive, susceptible to error and consumes instructor's time and resources. This paper explores longest common subsequence (LCS) algorithm as a string-based text similarity measure for effectively scoring short answers of Arabic essay questions. To achieve this effectiveness, the longest common subsequence is modified by developing weight-based measurement techniques and implemented along with using Arabic WordNet for scoring Arabic short answers. The experiments conducted on a dataset of 330 students' answers reported Root Mean Square Error (RMSE) value of 0.81 and Pearson correlation r value of 0.94. Findings based on experiments have shown improvements in the accuracy of performance of the proposed approach compared to similar studies. Moreover, the statistical analysis has shown that the proposed method scores students' answers similar to that of human estimator.",

keywords = "Arabic short answers scoring, arabic wordnet, automatic essay scoring, longest common subsequence, string-based text similarity",

author = "Abdeljaber, \{Hikmat A.\}",

note = "Publisher Copyright: {\textcopyright} 2013 IEEE.",

year = "2021",

doi = "10.1109/ACCESS.2021.3082408",

language = "English",

volume = "9",

pages = "76433--76445",

journal = "IEEE Access",

issn = "2169-3536",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - JOUR

T1 - Automatic Arabic Short Answers Scoring Using Longest Common Subsequence and Arabic WordNet

AU - Abdeljaber, Hikmat A.

PY - 2021

Y1 - 2021

N2 - The manual process of scoring short answers of Arabic essay questions is exhaustive, susceptible to error and consumes instructor's time and resources. This paper explores longest common subsequence (LCS) algorithm as a string-based text similarity measure for effectively scoring short answers of Arabic essay questions. To achieve this effectiveness, the longest common subsequence is modified by developing weight-based measurement techniques and implemented along with using Arabic WordNet for scoring Arabic short answers. The experiments conducted on a dataset of 330 students' answers reported Root Mean Square Error (RMSE) value of 0.81 and Pearson correlation r value of 0.94. Findings based on experiments have shown improvements in the accuracy of performance of the proposed approach compared to similar studies. Moreover, the statistical analysis has shown that the proposed method scores students' answers similar to that of human estimator.

AB - The manual process of scoring short answers of Arabic essay questions is exhaustive, susceptible to error and consumes instructor's time and resources. This paper explores longest common subsequence (LCS) algorithm as a string-based text similarity measure for effectively scoring short answers of Arabic essay questions. To achieve this effectiveness, the longest common subsequence is modified by developing weight-based measurement techniques and implemented along with using Arabic WordNet for scoring Arabic short answers. The experiments conducted on a dataset of 330 students' answers reported Root Mean Square Error (RMSE) value of 0.81 and Pearson correlation r value of 0.94. Findings based on experiments have shown improvements in the accuracy of performance of the proposed approach compared to similar studies. Moreover, the statistical analysis has shown that the proposed method scores students' answers similar to that of human estimator.

KW - Arabic short answers scoring

KW - arabic wordnet

KW - automatic essay scoring

KW - longest common subsequence

KW - string-based text similarity

UR - https://www.scopus.com/pages/publications/85107162077

U2 - 10.1109/ACCESS.2021.3082408

DO - 10.1109/ACCESS.2021.3082408

M3 - Article

AN - SCOPUS:85107162077

SN - 2169-3536

VL - 9

SP - 76433

EP - 76445

JO - IEEE Access

JF - IEEE Access

M1 - 9437188

ER -

Automatic Arabic Short Answers Scoring Using Longest Common Subsequence and Arabic WordNet

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this