MétaCan
Menu
Back to cohort

Common N-Gram Method (CNG): A Promising Approach to Detecting Mental Health Disorders on Social Media

2024· article· en· W4394995018 on OpenAlexaff
Harshit Agarwal, Vlado Kešelj

Bibliographic record

Venuenot available
Typearticle
Languageen
FieldPsychology
TopicMental Health via Writing
Canadian institutionsDalhousie University
Fundersnot available
KeywordsSocial mediaGramComputer scienceMental healthMedicinePsychiatryWorld Wide WebBiology

Abstract

fetched live from OpenAlex

Technology and social media's growing prevalence, especially during the COVID-19 pandemic, has contributed to a rise in mental health issues. This research discusses novel applications of natural language processing which can help develop more effective and accessible diagnostic tools for mental health illnesses. To enhance the realism of our model, we created a biased dataset that reflects the real-world ratios of mental illness prevalence. The proposed solution is the Common N-grams (CNG) method that offers comparable results to the state-of-the-art CNN-LSTM model and is less resource-intensive. The CNG method performs better than the CNN-LSTM model and Support Vector Machine (SVM), baseline model, in multiclassification tasks. The CNN-LSTM surpasses performance in binary tasks compared to the best score reported in the previous study with the same dataset. The study also highlights the usefulness of the Relative N-Gram Signature method to analyze the classification decision of the CNG technique. The proposed solutions offer practical and accessible options for individuals seeking reliable and accurate mental health support.

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)0.004
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.008
Threshold uncertainty score0.016

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0010.004
Meta-epidemiology (narrow)0.0010.000
Meta-epidemiology (broad)0.0010.001
Bibliometrics0.0030.002
Science and technology studies0.0010.001
Scholarly communication0.0010.002
Open science0.0010.001
Research integrity0.0010.001
Insufficient payload (model declined to judge)0.0030.002

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 head0.100
GPT teacher head0.465
Teacher spread0.365 · 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 designSimulation or modeling
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

Citations0
Published2024
Admission routes1
Has abstractyes

Explore more

Same topicMental Health via WritingFrench-language works237,207