SPY ETF and StockTwits tweets dataset

The dataset on which this article is based are offered by [3]. The sources of information are: The financial time series of the SPDR S&P 500 ETF (SPY), a fund replicating the S&P 500 index including the IT, finance, energy, and TLC sectors (the 500 largest US companies). It implements automatic share balancing based on stock value. A collection of 3,261,867 tweets gathered through the StockTwits API, containing the users' sentiment information on the same SPY asset.