MétaCan
Menu
Back to cohort
Record W4409125889 · doi:10.1007/s40593-025-00468-8

Negative Language Transfer Identification in the English Writing of Chinese and Farsi Native Speakers

2025· article· en· W4409125889 on OpenAlexafffund
Mohammad Karimiabdolmaleki, Leticia Farias Wanderley, Maria Cutumisu, Mohsen Rezazadeh, Carrie Demmans Epp

Bibliographic record

VenueInternational Journal of Artificial Intelligence in Education · 2025
Typearticle
Languageen
FieldSocial Sciences
TopicMultilingual Education and Policy
Canadian institutionsMcGill UniversityAcsenda School of ManagementUniversity of Alberta
FundersSocial Sciences and Humanities Research CouncilNatural Sciences and Engineering Research Council of Canada
KeywordsLinguisticsIdentification (biology)Computer scienceFirst languageNatural language processingBiology

Abstract

fetched live from OpenAlex

Effective communication in English can facilitate educational and employment opportunities for learners of English as an additional language (EAL) who tend to employ rules from their native language while communicating in English. This results in negative language transfer (NLT) when the rules from the mother tongue do not match those of English. One way of assisting EAL learners is to identify NLT errors in their English writing as a first step in the feedback process. However, manually identifying and providing feedback on learner NLT is a difficult task that requires time and expertise. A model that automatically identifies NLT in learner writing could facilitate this process. In this study, four classification algorithms were implemented to identify NLT in EAL learner writing automatically. Two of the language modelling approaches employed to classify learner errors (n-gram and recurrent neural network) were grounded in the linguistic nature of NLT, whereas the other two classifiers were general-purpose classifiers (random forest and logistic regression). The results show that the models could identify NLT in the English writing of Chinese and Farsi native speakers. Random forest outperformed all other models, yielding average weighted F1-scores of 78.1% on the Chinese FCE dataset and 94.8% on the Farsi Lang-8 dataset. This work shows that the implemented models could be used to automatically identify NLT errors in the English writing of Chinese and Farsi native speakers. The correct identification of such errors and subsequent provisioning of appropriate feedback could facilitate language learning and improve educational and employment opportunities for EAL leaners.

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 imitation

Not 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.

metaresearch head score (Codex)0.001
metaresearch head score (Gemma)0.008
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Observational · Consensus signal: Observational
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.010
Threshold uncertainty score0.020

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0010.008
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0010.000
Science and technology studies0.0010.001
Scholarly communication0.0020.001
Open science0.0000.001
Research integrity0.0010.001
Insufficient payload (model declined to judge)0.0050.001

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.

Opus teacher head0.035
GPT teacher head0.474
Teacher spread0.440 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designObservational
Domainnot available
GenreEmpirical

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".

Quick stats

Citations1
Published2025
Admission routes2
Has abstractno

Explore more

Same venueInternational Journal of Artificial Intelligence in EducationSame topicMultilingual Education and PolicyFrench-language works237,207