CNSocialDepress

数据集获取

git clone https://github.com/bucuram/depression-datasets-nlp.git

curl -L -o repo.zip https://github.com/bucuram/depression-datasets-nlp/archive/refs/heads/main.zip
unzip repo.zip

源站 README 摘录（使用方式）

<h1 align=“center”><span style=“font-weight:normal”>Datasets for depression detection using data posted on online platforms</h1>

📚 Data availability

The labels for data availability were inspired by the work of Harrigian et al. (2021), and are explained below:

• FREE - The dataset is publicly available and hosted online for anyone to access.
• AUTH - The data can be accessed by contacting the paper’'s authors.
• API - The dataset can be reproduced from the details provided in the article using dedicated APIs for different social media platforms with a reasonable degree of effort.
• DUA - The data is available only after a data usage agreement is signed. Sometimes, authorization from an Institutional Review Board (IRB) may be needed.
• UNK - The dataset availability is unknown; the authors do not mention if the data is available to the research community.
• N/AV - The dataset is no longer available or cannot be shared due to ethical considerations.
  For the datasets that are publicly available for download or can be accessed through user agreements, we provide the links to the data.

<a name=“citation”></a> 📖 Citation

If you found our list of datasets useful, please cite our papers in which we presented:

• The COVID-related datasets:

On the State of NLP Approaches to Modeling Depression in Social Media: A Post-COVID-19 Outlook

@article{Bucur2024state,
  author={Bucur, Ana-Maria and Moldovan, Andreea-Codrina and Parvatikar, Krutika and Zampieri, Marcos and KhudaBukhsh, Ashiqur R. and Dinu, Liviu P.},
  journal={IEEE Journal of Biomedical and Health Informatics}, 
  title={On the State of NLP Approaches to Modeling Depression in Social Media: A Post-COVID-19 Outlook}, 
  year={2025},
  pages={1-13},
  doi={10.1109/JBHI.2025.3540507}}

• The other social media datasets:

Datasets for Depression Modeling in Social Media: An Overview

@inproceedings{bucur2025datasets,
    title = "Datasets for Depression Modeling in Social Media: An Overview",
    author = "Bucur, Ana-Maria  and Moldovan, Andreea and Parvatikar, Krutika and Zampieri, Marcos and Khudabukhsh, Ashiqur and Dinu, Liviu",
    booktitle = "Proceedings of the 10th Workshop on Computational Linguistics and Clinical Ps


## 数据加载示例（表格/文本类）

```python
import pandas as pd, glob, os

files = (glob.glob(os.path.join(path, "**", "*.csv"), recursive=True)
       + glob.glob(os.path.join(path, "**", "*.tsv"), recursive=True)
       + glob.glob(os.path.join(path, "**", "*.xlsx"), recursive=True))
print("数据文件:", files)
df = pd.read_csv(files[0])
print(df.shape); print(df.columns.tolist()); print(df.head(3))

完整仓库：github.com/bucuram/depression-datasets-nlp