evidoria

← Back to browse

Good practice Imported

AAEE — King Saud University's Automated Arabic Essay Evaluator for Saudi School Students

Saudi Arabia · Riyadh · See the Saudi Arabia profile

King Saud University researchers built AAEE, one of the first automated essay scorers for Arabic, modeled on Saudi schools' official rubric. Tested on 350 real student essays across eight topics, it reached 90% accuracy and a 0.756 correlation with human graders.

Details

Promoter
King Saud University, Department of Computer Science, College of Computer & Information Sciences
Period
2019 (published study; research-stage system)
Keywords
natural language processing, Arabic-language assessment, academic research, K-12 education

Description

Researchers in the Department of Computer Science, College of Computer & Information Sciences at King Saud University, Riyadh, built AAEE (Automated Evaluation of Students' Essays in Arabic), one of the first systems to automatically score and give feedback on Arabic-language essays written by Saudi intermediate (middle school) and secondary (high school) students. Arabic's rich morphology and lack of mainstream NLP tooling had left most automated essay scoring (AES) research focused on English, leaving Arabic-speaking students without equivalent AI-assessment tools.

AAEE was deliberately modeled on the scoring scheme Saudi school instructors already use, evaluating essays on three official criteria: language proficiency, essay structure, and content relevance to the assigned topic. Technically, it combines Latent Semantic Analysis (LSA) with Rhetorical Structure Theory (RST) to assess both lexical/grammatical quality and the coherence of the essay's argument structure.

The researchers evaluated AAEE against a purpose-built corpus of 350 essays spanning eight different topics, written by real intermediate and secondary students and independently scored by human instructors as ground truth. The system reached 90% accuracy and a 0.756 correlation with human graders' scores (counting both 'exact' matches and 'within-range' scores of up to 2.5 points difference). A later comparative study (Alsaif et al., 2023, Computers, Materials & Continua) cited AAEE's figures directly (accuracy 0.9, correlation 0.76 on the same 350-essay corpus) and found that newer machine-learning approaches, including Random Forest models, could push the correlation to 0.913 — evidence that AAEE was an important early benchmark for Arabic AES but has since been surpassed in raw accuracy. AAEE remains a research-stage system: the sources reviewed describe its validation on a compiled essay corpus rather than a live deployment inside Saudi classrooms or national exams.

Read the full analysis: https://www.sciencedirect.com/science/article/abs/pii/S0306457319304935

Implementation

Implementation detail (cost, timeline, staffing, conditions for success) is not yet available for this practice.

Do you run this practice? Claim it — verified implementers get a public contact pathway and can propose corrections.

Data sources

Where this practice's information was retrieved from, and when.

Similar practices you may find useful