Financial Microblogs Research Articles

FineNews: fine-grained semantic sentiment analysis on financial microblogs and news

In this paper, a fine-grained supervised approach is proposed to identify bullish and bearish sentiments associated with companies and stocks, by predicting a real-valued score between − 1 and + 1. We propose a supervised approach learned by using several feature sets, consisting of lexical features, semantic features and a combination of lexical and semantic features. Our study reveals that semantic features, most notably BabelNet synsets and semantic frames, can be successfully applied for Sentiment Analysis within the financial domain to achieve better results. Moreover, a comparative study has been conducted between our supervised approach and unsupervised approaches. The obtained experimental results show how our approach outperforms the others.

Stock market forecasting with financial micro-blog based on sentiment and time series analysis

During the past few decades, time series analysis has become one popular method for solving stock forecasting problem. However, depending only on stock index series makes the performance of the forecast not good enough, because many external factors which may be involved are not taken into consideration. As a way to deal with it, sentiment analysis on online textual data of stock market can generate a lot of valuable information as a complement which can be named as external indicators. In this paper, a new method which combines the time series of external indicators and the time series of stock index is provided. A special text processing algorithm is proposed to obtain a weighted sentiment time series. In the experiment, we obtain financial micro-blogs from some famous portal websites in China. After that, each micro-blog is segmented and preprocessed, and then the sentiment value is calculated for each day. Finally, an NARX time series model combined with the weighted sentiment series is created to forecast the future value of Shanghai Stock Exchange Composite Index (SSECI). The experiment shows that the new model makes an improvement in terms of the accuracy.