Machine or Human? Evaluating the Quality of a Language Translation Mobile App for Diabetes Education Material
Bibliographic record
Abstract
BACKGROUND: Diabetes is a major health crisis for Hispanics and Asian Americans. Moreover, Spanish and Chinese speakers are more likely to have limited English proficiency in the United States. One potential tool for facilitating language communication between diabetes patients and health care providers is technology, specifically mobile phones. OBJECTIVE: Previous studies have assessed machine translation quality using only writing inputs. To bridge such a research gap, we conducted a pilot study to evaluate the quality of a mobile language translation app (iTranslate) with a voice recognition feature for translating diabetes patient education material. METHODS: The pamphlet, "You are the heart of your family…take care of it," is a health education sheet for diabetes patients that outlines three recommended questions for patients to ask their clinicians. Two professional translators translated the original English sentences into Spanish and Chinese. We recruited six certified medical translators (three Spanish and three Chinese) to conduct blinded evaluations of the following versions: (1) sentences interpreted by iTranslate, and (2) sentences interpreted by the professional human translators. Evaluators rated the sentences (ranging from 1-5) on four scales: Fluency, Adequacy, Meaning, and Severity. We performed descriptive analyses to examine the differences between these two versions. RESULTS: Cronbach alpha values exhibited high degrees of agreement on the rating outcomes of both evaluator groups: .920 for the Spanish raters and .971 for the Chinese raters. The readability scores generated using MS Word's Flesch-Kincaid Grade Level for these sentences were 0.0, 1.0, and 7.1. We found iTranslate generally provided translation accuracy comparable to human translators on simple sentences. However, iTranslate made more errors when translating difficult sentences. CONCLUSIONS: Although the evidence from our study supports iTranslate's potential for supplementing professional human translators, further evidence is needed. For this reason, mobile language translation apps should be used with caution.
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 | 0.039 | 0.179 |
| 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 | 0.003 | 0.002 |
| Open science | 0.001 | 0.001 |
| 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".