Dark Mode
NIFTY50 Stock Trends and Twitter Sentiment Registry
Stock & Market Data
Tags and Keywords
Trusted By
"No reviews yet"
Free
About
Integrating stock market movements with the real-time social media discourse of the NIFTY50 allows for a sophisticated analysis of modern financial ecosystems. This collection provides an empirical bridge between the quantitative price trends of eight leading Indian firms and the qualitative sentiment expressed on Twitter. By utilising CardiffNLP pretrained models to assign sentiment scores, the records facilitate an exploration into how public perception correlates with the performance of major sectors like banking and energy. This resource is instrumental for those seeking to filter customer service noise from genuine market signals to gain a clearer understanding of investor sentiment.
Columns
- Datetime: The chronological marker for both stock prices and tweet publication times.
- Id: A unique numerical identifier for each individual tweet.
- UserName: The handle of the Twitter user who posted the content.
- Tweet: The actual text content of the post, including hashtags and mentions.
- Likes: The count of positive engagements received by a tweet.
- Retweets: The number of times a post was shared by other users.
- Replies: The count of direct responses to a specific tweet.
- Quotes: The number of times a tweet was shared with an added comment.
- Negative: A probability score indicating the likelihood of the tweet's sentiment being negative.
- Neutral: A probability score representing the neutrality of the text.
Distribution
The information is delivered in a tabular CSV format, with specific files such as
ADANIENT.csv reaching a size of 3.27 MB. The collection contains approximately 12,300 valid records in its primary subsets, showing 100% data integrity with no missing or mismatched entries for core fields. It is a static archive with a usability score of 10.00, and no future updates are expected.Usage
This resource is ideal for developing machine learning models that predict stock volatility based on social media sentiment. It is well-suited for Natural Language Processing (NLP) research, specifically for creating filters to separate customer care interactions from financial discourse. Additionally, the data can be used to conduct correlation studies between digital engagement metrics, such as retweets or likes, and the intra-day price fluctuations of the Indian market.
Coverage
The geographic scope focuses on the Indian stock market, specifically targeting companies listed on the NIFTY50 index. Temporally, the records primarily span from January 2020 to January 2023, providing a historical look at the market during significant global shifts. The demographic scope encompasses a wide range of Twitter users, with specific subsets provided to account for high-quality tweet filtering.
License
CC0: Public Domain
Who Can Use It
Quantitative analysts can leverage these records to backtest sentiment-integrated trading strategies for the Indian banking sector. Data scientists specialising in finance may utilise the pre-calculated sentiment scores to refine classification algorithms. Furthermore, academic researchers can use the data to study the relationship between retail investor behaviour on social media and corporate valuation trends.
Dataset Name Suggestions
- NIFTY50 Stock Trends and Twitter Sentiment Registry
- Indian Corporate Sentiment and Market Volatility Archive
- NIFTY50 Social Media Pulse and Financial Metrics (2020–2023)
- Eight-Company Stock Performance and Twitter Engagement Data
- NIFTY50 Sentiment-Scored Financial Transaction Archive
Attributes
Original Data Source: NIFTY50 Stock Trends and Twitter Sentiment Registry
QUALITYLoading...
Free
Download Dataset in ZIP Format
Recommended Datasets
Loading recommendations...