Depressive and Non-Depressive Tweets Dataset
Mental Health & Wellness
Tags and Keywords
Trusted By




"No reviews yet"
Free
About
This dataset comprises depressive and non-depressive tweets collected between December 2019 and December 2020. Its primary purpose is to provide a valuable resource for sentiment analysis and text classification, particularly in the domain of mental health and wellness. Sentiment scores have been allocated using TextBlob, and the tweets were specifically extracted by considering the top 250 most frequently used negative and positive lexicons, accessed via SentiWord and various research publications.
Columns
- id: A unique identifier for each tweet record.
- text: The complete textual content of the tweet.
- sentiment: A numerical score representing the sentiment of the tweet.
Distribution
The dataset is typically provided in a CSV file format. It contains approximately 134,347 records (rows). The structure includes distinct columns for ID, tweet text, and sentiment scores, making it readily usable for analytical tasks.
Usage
This dataset is ideal for a variety of applications, including:
- Developing and training sentiment analysis models.
- Building text classification systems to identify depressive or non-depressive content.
- Conducting research into mental health trends as expressed on social media.
- Creating tools for social media monitoring focused on mental well-being.
- Natural Language Processing (NLP) tasks related to emotional detection.
Coverage
The tweets in this dataset were collected between December 2019 and December 2020. Geographically, the data originated largely from India and various parts of the Indian subcontinent. No specific demographic notes are provided beyond the general nature of tweets.
License
CC-BY
Who Can Use It
- Researchers focusing on mental health, social media behaviour, or computational linguistics.
- Data Scientists and Machine Learning Engineers for training and evaluating text classification and sentiment analysis models.
- Academics studying online communication patterns related to well-being.
- Developers creating applications that require sentiment detection in text.
Dataset Name Suggestions
- Depressive and Non-Depressive Tweets Dataset
- Social Media Mental Health Tweets
- Tweet Sentiment Classification Data
- India Subcontinent Mental Health Tweets
Attributes
Original Data Source: Depressive/Non-Depressive Tweets Data