Dataset: Stock Tweets For Sentiment Analysis And Prediction

About this Dataset

Stock Tweets For Sentiment Analysis And Prediction

Dataset Information

The dataset contains tweets for top 25 most watched stock tickers on Yahoo FInance from 30-09-2021 to 30-09-2022, additionally was added stock market price and volume data for corresponding dates and stocks.

Dataset description

Date - date and time of tweet
Tweet - full text of the tweet
Stock Name - full stock ticker name for which the tweet was scraped
Company Name - full company name for corresponding tweet and stock ticker

Inspiration

Dataset was inspired by following datasets: Stock Market Tweet | Sentiment Analysis lexicon by Zeus and Stock-Market Sentiment Dataset

This dataset can be used for:

experimenting with sentiment analysis
predicting stock prices
exploring the connection between public sentiment and stock price movement

Hope you enjoy this dataset!

Tables

Stock Tweets

@kaggle.equinxx_stock_tweets_for_sentiment_analysis_and_prediction.stock_tweets

9.52 MB
80793 rows
4 columns


CREATE TABLE stock_tweets (
  "date" VARCHAR,
  "tweet" VARCHAR,
  "stock_name" VARCHAR,
  "company_name" VARCHAR
);

Stock Yfinance Data

@kaggle.equinxx_stock_tweets_for_sentiment_analysis_and_prediction.stock_yfinance_data

268.27 KB
6300 rows
8 columns


CREATE TABLE stock_yfinance_data (
  "date" TIMESTAMP,
  "open" DOUBLE,
  "high" DOUBLE,
  "low" DOUBLE,
  "close" DOUBLE,
  "adj_close" DOUBLE,
  "volume" BIGINT,
  "stock_name" VARCHAR
);