Research report
Does Turnitin Flag Human-written ESL Essays as AI-generated?
A Word-Level Accuracy Benchmark of Turnitin on ESL Undergraduate Essays
Cite this research
In a benchmark of 340 human-written ESL undergraduate essays totaling 263,329 words, Turnitin achieved 100.0% word-level accuracy, correctly classifying every word as human-written across all domains, majors, and word-count buckets.
According to Turnitin0 Research, Turnitin correctly identified 100% of words in 340 human-written ESL essays as not AI-generated, demonstrating zero false positives at the word level across 263,329 words.
- 340 articles tested
- Checker: Turnitin
- Corpus: CELL
- 1 linked dataset
- Detection screenshots available
- Published July 28, 2026
Peng, J. (2026). Does Turnitin Flag Human-written ESL Essays as AI-generated?. Turnitin0 Research. https://www.turnitin0.com/research/reports/does-turnitin-flag-human-written-esl-essays-as-ai-generated
Licensed under CC0 1.0 Universal. You may copy, modify, distribute, and cite this research—including text, figures, tables, and datasets—without asking permission.
Overview
This report evaluates Turnitin's AI-detection performance on a corpus of 340 human-written ESL undergraduate essays from the CELL corpus, totaling 263,329 words. The benchmark measures word-level accuracy—the proportion of words correctly identified as human-written—across domains, majors, and word-count buckets. The global expectation is that Turnitin should not flag these essays as AI-generated.
- Overall word accuracy: 100.0% — Turnitin correctly classified all 263,329 words as human-written across 340 essays.
- By domain: Accuracy was 100.0% for all five domains: Business (14,698 words), Education (40,890 words), Humanities (142,534 words), Psychology (43,155 words), and STEM (22,052 words).
- By major: All 18 majors achieved 100.0% word accuracy, including the largest (Communications: 56,961 words) and smallest (Marketing: 632 words).
- By word bucket: Essays in the 400-word bucket (57,028 words), 800-word bucket (75,382 words), and 1,200-word bucket (130,919 words) each scored 100.0% accuracy.
- Dataset: 340 human-written undergraduate essays from the CELL corpus, all classified as ESL (English as a Second Language).
- Word count: 263,329 words total (excluding references/bibliographies).
- Dimensions analyzed:
- Domain: Business, Education, Humanities, Psychology, STEM.
- Major: 18 distinct majors (e.g., Biology, Communications, Economics).
- Word bucket: 400, 800, and 1,200 words.
- Metric: Word-level accuracy = (correctly classified words / total words) × 100. Only word-level counts are reported; no article-level or paragraph-level metrics are used.
- Scoring unit: accuracy is measured in words. First identify correct paragraphs under the expectation below, then sum the words in those paragraphs for the correct-word count; total words are summed over all counted paragraphs.
- Correct paragraph: a counted paragraph that was not flagged as AI. Correct words are the words in those paragraphs.
- References excluded: from a References/Bibliography-style heading onward, those paragraphs are left out of word counts.
- Limited diversity: While spanning 18 majors, some majors have very few essays (e.g., Marketing: 1 essay, 632 words), limiting statistical power for those subgroups.
- Total articles: 340
- Total words: 263,329
- Correct words: 263,329
- Word accuracy: 100.0%
- Business: 27 articles, 14,698 words, 100.0% accuracy
- Education: 47 articles, 40,890 words, 100.0% accuracy
- Humanities: 186 articles, 142,534 words, 100.0% accuracy
- Psychology: 42 articles, 43,155 words, 100.0% accuracy
- STEM: 38 articles, 22,052 words, 100.0% accuracy
- Biology: 1 article, 995 words, 100.0%
- Business Administration: 2 articles, 1,584 words, 100.0%
- Civil Engineering: 3 articles, 1,783 words, 100.0%
- Communications: 84 articles, 56,961 words, 100.0%
- Computer Science: 2 articles, 954 words, 100.0%
- Criminal Justice: 7 articles, 3,772 words, 100.0%
- Economics: 22 articles, 10,210 words, 100.0%
- Education: 47 articles, 40,890 words, 100.0%
- English: 79 articles, 66,503 words, 100.0%
- Environmental Science: 24 articles, 14,365 words, 100.0%
- Finance: 2 articles, 2,272 words, 100.0%
- Health Sciences: 7 articles, 3,279 words, 100.0%
- History: 1 article, 1,105 words, 100.0%
- Information Technology: 1 article, 676 words, 100.0%
- Marketing: 1 article, 632 words, 100.0%
- Political Science: 1 article, 551 words, 100.0%
- Psychology: 42 articles, 43,155 words, 100.0%
- Sociology: 14 articles, 13,642 words, 100.0%
- 400-word bucket: 125 articles, 57,028 words, 100.0% accuracy
- 800-word bucket: 100 articles, 75,382 words, 100.0% accuracy
- 1,200-word bucket: 115 articles, 130,919 words, 100.0% accuracy
Detection report screenshots
Turnitin marks suspected AIGC text in cyan.