halolimat/Social-media-Depression-Detector
:pensive: :disappointed: :persevere: :confounded: :weary: Detect depression on social media using the ssToT method introduced in our ASONAM 2017 paper titled "Semi-Supervised Approach to Monitoring Clinical Depressive Symptoms in Social Media"
The ssToT (semi-supervised text-to-topic) method combines lexicon-based feature extraction with unlabeled social media data to improve depression detection accuracy beyond supervised baselines. Implementation uses Jupyter Notebooks for workflow automation and includes a curated depression lexicon as a reusable component. Targets researchers studying mental health monitoring and clinical NLP applications.
No commits in the last 6 months.
Stars
69
Forks
36
Language
Jupyter Notebook
License
GPL-3.0
Category
Last pushed
Feb 26, 2019
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/nlp/halolimat/Social-media-Depression-Detector"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
soumyajit4419/AI_For_Social_Good
Using natural language processing to analyze the sentiments of people and detect suicidal...
audreycs/MentalManip
Dataset and code for the paper MentalManip: A Dataset For Fine-grained Analysis of Mental...
nikhil-garg/Psychiatric-Disorders-With-Speech
In this project, we wish to identify psychiatric disorders through patient's speech
anjmittu/clpsych2021-shared-task-baseline
The baseline code for the CLPsych 2021 Shared Task.
stack-dhruv/mental-health-meme-classification
A multimodal AI that understands internet memes to detect underlying signs of anxiety and depression.