Sentiment analysis on social media for stock movement prediction
作者：
Highlights：
• A novel method for predicting stock price movement was presented.
• Topics and sentiments of them were extracted from social media as the feature.
• Two methods were proposed to capture the topic-sentiment feature.
• Integration of the sentiments was investigated via a large scale experiment.
• Our model outperformed other methods in the average accuracy of 18 stocks.
摘要
•A novel method for predicting stock price movement was presented.•Topics and sentiments of them were extracted from social media as the feature.•Two methods were proposed to capture the topic-sentiment feature.•Integration of the sentiments was investigated via a large scale experiment.•Our model outperformed other methods in the average accuracy of 18 stocks.
论文关键词：Sentiment analysis,Opinion mining,Classification,Prediction,Stock,Social media,Message board
论文评审过程：Received 2 December 2014, Revised 22 July 2015, Accepted 23 July 2015, Available online 6 August 2015, Version of Record 27 September 2015.
论文官网地址：https://doi.org/10.1016/j.eswa.2015.07.052
