A hybrid automatic scoring system for Arabic essays

Alghamdi, Mohammed H.; Alkanhal, Mohamed; Al-Badrashiny, Mohamed; Al-Qabbany, Abdulaziz O.; Areshey, Ali; Alharbi, Abdulaziz

doi:10.3233/aic-130586

Cited by 14 publications

(9 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Experiment results showed that the addition of LSA over syntactic features improves the scoring performance of AES (Omar & Mezher, 2016). Many contents similarity-based AES used LSA or any of its variations in deriving grades or scores (Awaida et al, 2019;Amalia et al, 2019;Alghamdi, et al, 2014;Contreras et al, 2018;Ong et al, 2011;Shehab et al, 2018).…”

Section: Content Similarity Frameworkmentioning

confidence: 99%

A Comprehensive Review of Automated Essay Scoring (AES) Research and Development

Lim¹,

Bong²,

Wong³

et al. 2021

JST

View full text Add to dashboard Cite

Automated Essay Scoring (AES) is a service or software that can predictively grade essay based on a pre-trained computational model. It has gained a lot of research interest in educational institutions as it expedites the process and reduces the effort of human raters in grading the essays as close to humans’ decisions. Despite the strong appeal, its implementation varies widely according to researchers’ preferences. This critical review examines various AES development milestones specifically on different methodologies and attributes used in deriving essay scores. To generalize existing AES systems according to their constructs, we attempted to fit all of them into three frameworks which are content similarity, machine learning and hybrid. In addition, we presented and compared various common evaluation metrics in measuring the efficiency of AES and proposed Quadratic Weighted Kappa (QWK) as standard evaluation metric since it corrects the agreement purely by chance when estimate the degree of agreement between two raters. In conclusion, the paper proposes hybrid framework standard as the potential upcoming AES framework as it capable to aggregate both style and content to predict essay grades Thus, the main objective of this study is to discuss various critical issues pertaining to the current development of AES which yielded our recommendations on the future AES development.

show abstract

Section: Content Similarity Frameworkmentioning

confidence: 99%

A Comprehensive Review of Automated Essay Scoring (AES) Research and Development

Lim¹,

Bong²,

Wong³

et al. 2021

JST

View full text Add to dashboard Cite

show abstract

“…This method relies on generating vectors-presentation for semantic terms, words, or even the concepts [19]. Research in [20] presented a system for scoring Arabic short answers by embedding LSA with the main three important syntactic features: lemmatization, the mistake of words, and the number of common words. They employed bag-of-words (BOW) to present feature vectors that mapped into the Cosine algorithms to measure the similarity between student answers (SAs) and model answers (MAs).…”

Section: Related Workmentioning

confidence: 99%

“…Corpus-based [17], [20], [21], [23] Arabic automated short answer scoring Hybrid approaches (String-based, Corpus based) [8], [24].…”

Section: Arabic Automated Online Exam Scoringmentioning

confidence: 99%

Automatic Essay Scoring for Arabic Short Answer Questions using Text Mining Techniques

Meccawy,

Bayazed,

Al-Abdullah

et al. 2023

IJACSA

View full text Add to dashboard Cite

Automated Essay Scoring (AES) systems involve using a specially designed computing program to mark students' essays. It is a form of online assessment supported by natural language processing (NLP). These systems seek to exploit advanced technologies to reduce the time and effort spent on the exam scoring process. These systems have been applied in several languages, including Arabic. Nevertheless, the applicable NLP techniques in Arabic AES are still limited, and further investigation is needed to make NLP suitable for Arabic to achieve human-like scoring accuracy. Therefore, this comparative empirical experimental study tested two wordembedding deep learning approaches, namely BERT and Word2vec, along with a knowledge-based similarity approach; Arabic WordNet. The study used the Cosine similarity measure to provide optimal student answer scores. Several experiments were conducted for each of the proposed approaches on two available Arabic short answer question datasets to explore the effect of the stemming level. The quantitative results of this study indicated that advanced models of contextual embedding can improve the efficiency of Arabic AES as the meaning of words can differ in the different contexts. Therefore, serve as a catalyst for future research based on contextual embedding models, as the BERT approach achieved the best Pearson Correlation (.84) and RMSE (1.003). However, this research area needs further investigation to increase the accuracy of Arabic AES to become a practical online scoring system.

show abstract

“…A system based on the basis of stemming methods and processes editing Levenshtein to evaluate the students' exams online was provided [27]. Therefore, a hybrid method for an automatic essay scoring system (AES) for Arabic articles was suggested [28]. The system relies mainly on light and heavy stemming of words, whereby it relies only on a string-based algorithm (Levenshtein).…”

Section:  Levenshtein Distance Similaritymentioning

confidence: 99%

Arabic Language Documents’ Similarity and its Challenges (A Review)

Saleh¹,

Fadzli²,

El-Ebiary³

2020

IJETT

View full text Add to dashboard Cite

Measuring the similarity of documents is of great importance and has influences on many areas and subjects such as Information Retrieval (IR), redrafting discovered, classified documents, and conversational agent programs. Recently, several scientific studies have been interested in implementing the similarity of documents in Arabic language applications. In this study, we review most of the techniques used in measuring the similarity between documents in Arabic; these techniques are classified into three types, mainly lexical, semantic, and finally hybrid. Hence, most of the techniques and methods adopted to measure the similarity between documents were reviewed to determine the most appropriate ones to measure the similarity in Arabic. However, the measurement of the percentage of similarity in documents in the Arabic language represents a major challenge faced by most of the researchers due to the nature of the Arabic language, such as complex morphological processes, ambiguity, and a general lack of resources.

show abstract

A hybrid automatic scoring system for Arabic essays

Cited by 14 publications

References 13 publications

A Comprehensive Review of Automated Essay Scoring (AES) Research and Development

A Comprehensive Review of Automated Essay Scoring (AES) Research and Development

Automatic Essay Scoring for Arabic Short Answer Questions using Text Mining Techniques

Arabic Language Documents’ Similarity and its Challenges (A Review)

Contact Info

Product

Resources

About