Published November 28, 2024 | Version v1.0
Dataset Open

Multi-Class Depression Detection Dataset

Authors/Creators

  • 1. ROR icon National University of Computer and Emerging Sciences

Description

This dataset was created as part of the Master's thesis titled "Multi-Class Depression Detection Through Tweets Using Artificial Intelligence." It contains tweets labeled for five types of depression (Bipolar, Major, Psychotic, Atypical, and Postpartum) using lexicons verified by psychiatrists. 

Purpose: Designed for multi-class classification of depression using AI, focusing on Explainable AI for highlighting key words in the tweets influencing the predictions.
Applications: The dataset is suitable for research in natural language processing, sentiment analysis, mental health prediction, and Explainable AI.

This dataset is shared under the Creative Commons Attribution 4.0 International (CC BY) license, requiring proper attribution for any use or modification.

Files

dataset.csv

Files (2.8 MB)

Name Size Download all
md5:e3bc36d8e0abdb47391389f00154f233
2.8 MB Preview Download

Additional details

Related works

Is supplement to
Preprint: 10.48550/arXiv.2404.13104 (DOI)

Dates

Created
2023-01-18
Dataset construction, including scraping and labeling, was finalized on this date.

Software

Repository URL
https://github.com/mnusrat786/Multiclass-Depression-Detection-of-Tweets-using-AI
Development Status
Active

References

  • Nusrat, M. O., Shahzad, W., & Jamal, S. A. (2024). Multi Class Depression Detection Through Tweets using Artificial Intelligence. arXiv preprint arXiv:2404.13104.