Automated Measures of Lexical Sophistication: Predicting Proficiency in an Integrated Academic Writing Task
Bibliographic record
Abstract
Background. Advances in automated analyses of written discourse have made available a wide range of indices that can be used to better understand linguistic features present in language users’ discourse and the relationships these metrics hold with human raters’ assessments of writing. Purpose. The present study extends previous research in this area by using the TAALES 2.2 software application to automatically extract 484 single and multi-word metrics of lexical sophistication to examine their relationship with differences in assessed L2 English writing proficiency. Methods. Using a graded corpus of timed, integrated essays from a major academic English language test, correlations and multiple regressions were used to identify specific metrics that best predict L2 English writing proficiency scores. Results. The most parsimonious regression model yielded four-predictor variables, with total word count, orthographic neighborhood frequency, lexical decision time, and word naming response time accounting for 36% of total explained variance. Implications. Results emphasize the importance of writing fluency (by way of total word count) in assessments of this kind. Thus, learners looking to improve writing proficiency may find benefit from writing activities aimed at increasing speed of production. Furthermore, despite a substantial amount of variance explained by the final regression model, findings suggest the need for a wider range of metrics that tap into additional aspects of writing proficiency.
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 | 0.002 | 0.023 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.002 | 0.001 |
| Open science | 0.000 | 0.001 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.002 | 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".