Contextual Sentence Analysis for the Sentiment Prediction on Financial Data
This work addresses sentiment analysis for investors using financial data, but it is incremental as it builds on existing methods like RoBERTa and sentiment dictionaries.
The paper tackled sentiment prediction on financial texts by proposing a hierarchical stack of Transformers model that fine-tuned RoBERTa and integrated sentiment dictionaries, achieving performance that outperformed the best systems from SemEval-2017 task 5 and strong baselines.
Newsletters and social networks can reflect the opinion about the market and specific stocks from the perspective of analysts and the general public on products and/or services provided by a company. Therefore, sentiment analysis of these texts can provide useful information to help investors trade in the market. In this paper, a hierarchical stack of Transformers model is proposed to identify the sentiment associated with companies and stocks, by predicting a score (of data type real) in a range between -1 and +1. Specifically, we fine-tuned a RoBERTa model to process headlines and microblogs and combined it with additional Transformer layers to process the sentence analysis with sentiment dictionaries to improve the sentiment analysis. We evaluated it on financial data released by SemEval-2017 task 5 and our proposition outperformed the best systems of SemEval-2017 task 5 and strong baselines. Indeed, the combination of contextual sentence analysis with the financial and general sentiment dictionaries provided useful information to our model and allowed it to generate more reliable sentiment scores.