The impact of microblogging data for stock market prediction: Using Twitter to predict returns, volatility, trading volume and survey sentiment indices

作者：

Highlights：

• Evaluation of the predictive value of Twitter data for stock market variables.

• Creation of a Kalman Filter (KF) indicator by combining five distinct indicators.

• Forecasting of two popular survey sentiment indicators using Twitter data and KF.

• Twitter features and KF were informative to forecast returns of some stocks.

• Twitter and KF indicators were useful to predict some survey indicators.

摘要

•Evaluation of the predictive value of Twitter data for stock market variables.•Creation of a Kalman Filter (KF) indicator by combining five distinct indicators.•Forecasting of two popular survey sentiment indicators using Twitter data and KF.•Twitter features and KF were informative to forecast returns of some stocks.•Twitter and KF indicators were useful to predict some survey indicators.

论文关键词：Stock market,Twitter,Data and text mining,Regression

论文评审过程：Received 10 October 2016, Revised 6 December 2016, Accepted 26 December 2016, Available online 27 December 2016, Version of Record 29 December 2016.

论文官网地址：https://doi.org/10.1016/j.eswa.2016.12.036