2020

Dataset Description

The Twitter Financial News dataset is an English-language dataset containing an annotated corpus of finance-related tweets. This dataset is used to classify finance-related tweets for their sentiment.

The dataset holds 11,932 documents annotated with 3 labels:

sentiments = { "LABEL_0": "Bearish", "LABEL_1": "Bullish", "LABEL_2": "Neutral" }

The data was collected using the Twitter API. The current dataset supports the multi-class classification… See the full description on the dataset page: https://huggingface.co/datasets/zeroshot/twitter-financial-news-sentiment.

Context

Scrapped from twitters from 2016-01-01 to 2019-03-29, Collecting Tweets containing Bitcoin or BTC Tools used:

Twint Tweepy

Content

Tweet in multiple Language & Talked about Bitcoin

Acknowledgements

Thanks to Alex ( https://www.kaggle.com/alaix14 ) for his dataset (https://www.kaggle.com/alaix14/bitcoin-tweets-20160101-to-20190329 ), It is just an additional dimension where Sentiment is analyzed with a price change for Bitcoin

Financial Sentiment Analysis Dataset

  Overview

This dataset is a comprehensive collection of tweets focused on financial topics, meticulously curated to assist in sentiment analysis in the domain of finance and stock markets. It serves as a valuable resource for training machine learning models to understand and predict sentiment trends based on social media discourse, particularly within the financial sector.

  Data Description

The dataset comprises tweets… See the full description on the dataset page: https://huggingface.co/datasets/TimKoornstra/financial-tweets-sentiment.

Description

Tweets were collectect between April 9 and July 16, 2020 using not only the SPX500 tag but also the top 25 companies in the index and "#stocks". 1300 tweets were manually classified and reviewed. The proposed specialised dictionary is also present in the data of this contribution. All the source code used to download tweets, check the top words and evaluate the sentiment are present.

Content

- ID -> Contains id used for the tweet. - Date and time -> Date and time when the tweet was tweeted. - Tweet -> Tweet/text written by the user. - Sentiment -> Wheter the tweet was postive or negative.

Inspiration

Currently exploring nlp and learning more about it, found this very easy to use dataset for the topic and now sharing with other fellow kaggelers.

Notebook and a task is missing for the dataset hence it shows as 9.4 usability.

Acknowledgements

Cite - Bruno Taborda, Ana de Almeida, José Carlos Dias, Fernando Batista, Ricardo Ribeiro, April 15, 2021, "Stock Market Tweets Data", IEEE Dataport, doi: https://dx.doi.org/10.21227/g8vy-5w61.

I do not own this dataset, thanks to the authors for creating this dataset. Please cite if using the dataset.

In March 2020, the outbreak of COVID-19 precipitated one of the most significant stock market downturns in recent history. This paper explores the relationship between public sentiment related to COVID-19 and stock market fluctuations during the different phases of the pandemic. Utilizing natural language processing and sentiment analysis, we examine Twitter data for pandemic-related keywords to assess whether these sentiments can predict changes in stock market trends. Our analysis extends to additional datasets: one annotated by market experts to integrate professional financial sentiment with market dynamics, and another comprising long-term social media sentiment data to observe changes in public sentiment from the pandemic phase to the endemic phase. Our findings indicate a strong correlation between the sentiments expressed on social media and market volatility, particularly sentiments directly associated with stocks. These insights validate the effectiveness of our Sentiment(S)-LSTM model, which helps to understand the evolving dynamics between public sentiment and stock market trends from 2020 through 2023, as the situation shifts from pandemic to endemic and approaches new normalcy.

Accuracy of adjusted stock closing price prediction results for the S-LSTM for the six stocks of Long-term 2021 to 2023 Tweet sentiment dataset.

Authors, through Twitter API, collected this database over eight months. These data are tweets of over 50 experts regarding market analysis of 40 cryptocurrencies. These experts are known as influencers on social networks such as Twitter. The theory of Behavioral economics shows that the opinions of people, especially experts, can impact the stock market trend (here, cryptocurrencies). Existing databases often cover tweets related to one or more cryptocurrencies. Also, in these databases, no attention is paid to the user's expertise, and most of the data is extracted using hashtags. Failure to pay attention to the user's expertise causes the irrelevant volume to increase and the neutral polarity to increase considerably. This database has a main table named "Tweets1" with 11 columns and 40 tables to separate comments related to each cryptocurrency. The columns of the main table and the cryptocurrency tables are explained in the attached document. Researchers can use this dataset in various machine learning tasks, such as sentiment analysis and deep transfer learning with sentiment analysis. Also, this data can be used to check the impact of influencers' opinions on the cryptocurrency market trend. The use of this database is allowed by mentioning the source. Also, in this version, we have added the excel version of the database and Python code to extract the names of influencers and tweets. in Version(3): In the new version, three datasets related to historical prices and sentiments related to Bitcoin, Ethereum, and Binance have been added as Excel files from January 1, 2023, to June 12, 2023. Also, two datasets of 52 influential tweets in cryptocurrencies have been published, along with the score and polarity of sentiments regarding more than 300 cryptocurrencies from February 2021 to June 2023. Also, two Python codes related to the sentiment analysis algorithm of tweets with Python have been published. This algorithm combines RoBERTa pre-trained deep neural network and BiGRU deep neural network with an attention layer (see code Preprocessing_and_sentiment_analysis with python).

This analysis presents a rigorous exploration of financial data, incorporating a diverse range of statistical features. By providing a robust foundation, it facilitates advanced research and innovative modeling techniques within the field of finance.

Elon Musk's Twitter Dream in Free Fall

Financial data:

• Historical daily stock prices (open, high, low, close, volume)

• Fundamental data (e.g., market capitalization, price to earnings P/E ratio, dividend yield, earnings per share EPS, price to earnings growth, debt-to-equity ratio, price-to-book ratio, current ratio, free cash flow, projected earnings growth, return on equity, dividend payout ratio, price to sales ratio, credit rating)

• Technical indicators (e.g., moving averages, RSI, MACD, average directional index, aroon oscillator, stochastic oscillator, on-balance volume, accumulation/distribution A/D line, parabolic SAR indicator, bollinger bands indicators, fibonacci, williams percent range, commodity channel index)

Machine learning features:

• Feature engineering based on financial data and technical indicators

• Sentiment analysis data from social media and news articles

• Macroeconomic data (e.g., GDP, unemployment rate, interest rates, consumer spending, building permits, consumer confidence, inflation, producer price index, money supply, home sales, retail sales, bond yields)

Potential Applications:

• Stock price prediction

• Portfolio optimization

• Algorithmic trading

• Market sentiment analysis

• Risk management

Use Cases:

• Researchers investigating the effectiveness of machine learning in stock market prediction

• Analysts developing quantitative trading Buy/Sell strategies

• Individuals interested in building their own stock market prediction models

• Students learning about machine learning and financial applications

Additional Notes:

• The dataset may include different levels of granularity (e.g., daily, hourly)

• Data cleaning and preprocessing are essential before model training

• Regular updates are recommended to maintain the accuracy and relevance of the data

Performance of the main forecasting models in the DJIA data set.

Performance of stock closing price prediction results for the four algorithms for the three stocks during August and September 2020.

The study explores the relationship between investor emotions and stock market anomalies in the Indian financial landscape, examining both regular and irregular market occurrences. By utilizing mixed methods, the study uses an LSTM model for anomaly detection and sentiment analysis from Twitter data. It also includes regression analysis to measure the influence of public sentiment on stock prices. The results suggest that investor emotions play a significant role in market anomalies during extraordinary events like the 2008 financial crisis and the demonetization initiative in 2016, but have a lesser effect during expected, repetitive events. The study stands out for its empirical investigation of emotional finance theory to uncover the reasons behind stock market anomalies in India, an area that has not been thoroughly examined before. This research has two main implications: it questions the Efficient Market Hypothesis and provides suggestions for regulatory measures and investment strategies that consider emotional influences on market behavior.