Dataset Link: https://github.com/nhthien/YahooFinanceMessageBoard
This dataset consists of the 18 message boards of the 18 stocks from Yahoo Finance Message Board for a period of one year (from July 23, 2012 to July 19, 2013)
For more information, please look at the following publications which used this dataset. In addition, when you use this dataset, please cite these two publications:
(1) Thien Hai Nguyen and Kiyoaki Shirai. "Topic Modeling based Sentiment Analysis on Social Media for Stock Market Prediction". The 53rd Annual Meeting of the Association for Computational Linguistics (ACL), pp.1354-1364, 2015, July.
Link: http://www.aclweb.org/anthology/P/P15/P15-1131.pdf
(2) Thien Hai Nguyen, Kiyoaki Shirai and Julien Velcin. “Sentiment Analysis on Social Media for Stock Movement Prediction”. International Journal of Expert Systems With Applications (ESWA), Vol. 42, No. 24, pp. 9603-9611, 2015.
Link: http://www.sciencedirect.com/science/article/pii/S0957417415005126