Editing assistance tool validation for English language learners
Bibliographic record
Abstract
Purpose Editing assistance software programs are computer-based tools that check and make suggestions for the grammar, spelling and style of a piece of writing. These tools are becoming more popular as recommendations for students who struggle with written expression, such as English language learners (ELLs). The purpose of the present study is to compare the performance of four different programs with embedded editing assistance tools in their ability to identify errors in the writing of ELLs. Design/methodology/approach Repeated measures ANOVAs were conducted to determine whether there were differences in the number of errors (i.e. spelling, grammar, punctuation and errors that change the meaning of the text) identified by editing assistance programs (i.e. Grammarly, Ginger, Microsoft Word, Google Docs and human raters) for writing by ELLs. Findings The results of the present study indicate that the four programs did not differ in their identification of spelling errors. None of the editing assistance programs identified as many errors as the human raters; therefore, editing assistance cannot yet replace effective human editing for ELLs. Research limitations/implications Limitations with the present study include manual verification of errors flagged by editing programs, multiple raters, a small sample size and a young sample of students. Practical implications The paper includes practical factors to consider when integrating editing assistance software into the classroom, including the development needs of students, the impact of students' first language and student training on the technology. Originality/value This paper provides school psychologists, teachers and other professionals working with students with specific, evidence-based recommendations for implementation of editing assistance AT.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.032 | 0.157 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.002 | 0.003 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.003 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".