MétaCan
Menu
Back to cohort
Record W4405113448 · doi:10.1016/j.procs.2024.11.125

Automatic Classification of Psychosocial Concerns: From Traditional Approach to Deep Learning

2024· article· en· W4405113448 on OpenAlex

Why this work is in the frame

A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.

affAt least one author lists a Canadian institution in the pinned OpenAlex snapshot.

Bibliographic record

VenueProcedia Computer Science · 2024
Typearticle
Languageen
FieldPsychology
TopicMental Health Research Topics
Canadian institutionsUniversité du Québec à Rimouski
Fundersnot available
KeywordsComputer scienceArtificial intelligenceMachine learningDeep learningPsychosocialData sciencePsychiatryMedicine

Abstract

fetched live from OpenAlex

The advent of artificial intelligence (AI) technologies presents promising prospects for analyzing short texts, significantly impacting the psychosocial health sector. The classification and categorization of texts represent arduous and time-consuming tasks, necessitating systematic automation to optimize the processing of traditional manual workflows. This paper presents a comparative study of various machine learning (ML) techniques in natural language processing (NLP). These techniques, designed to replace manual data categorization effectively, primarily rely on traditional algorithms such as K-Nearest Neighbors (k-NN), Support Vector Machines (SVM), and Extreme Gradient Boosting (XGBoost), as well as deep learning approaches, including fine-tuning, SetFit, and few-shot learning based on transformers. A detailed analysis of different evaluation metrics revealed that the SetFit approach, integrating the sentence-transformer model, outperformed the best traditional models, with an average accuracy of 70.74% compared to 68.69 % achieved by the SVM model.

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.

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.001
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Other design · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.863
Threshold uncertainty score0.330

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0010.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.001
Science and technology studies0.0000.000
Scholarly communication0.0000.000
Open science0.0010.000
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0000.000

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 head0.168
GPT teacher head0.423
Teacher spread0.255 · 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