Stock movement prediction with sentiment analysis based on deep learning networks

Abstract

With the development of Internet and big data, it is more convenient for investors to share opinions or have a discuss with others via the web, which creates massive unstructured data. These data reflect investors' emotions and their investment intentions, and it will further affect the movement of the stock market. Although researchers have been attempted to use sentiment information to predict the market, the sentiment features used are driven by outdated emotion extraction systems. In this article, we proposed a new sentiment analysis system with deep neural networks for stock comments and applied estimated sentiment information to the stock movement forecasting. The empirical results showed that our deep sentiment classification method achieved a 9% improvement over the logistic regression algorithm, and provided an accurate sentiment extractor for the next predicting step. In addition our new hybrid features that mix stock trading data and sentiment information achieved 1.25% improvement among 150 Chinese stocks in the testing dataset. For American stocks, the sentiment information would reduced the predicting results. We found that emotion features extracted from comments are indeed effective for stocks with a higher price to book value and a lower beta risk value in China. K E Y W O R D S deep learning, financial comments, sentiment analysis, stock movement prediction 1 INTRODUCTION Sentiment analysis is one of the most important research directions in artificial intelligence and has been applied in many fields, such as stock predicting, political science, and health science. 1,2 Among these applications, stock movement prediction has wide commercial potential and market prospects. However, the fluctuation of the stock market is closely related to the development of the national economy, and the market itself is also a complex nonlinear dynamic system that is susceptible to many factors. 3 Due to the complexity of market rules, the volatility of prices and the diversity of factors also affect the market. Generally, there are approximately two basic methods for stock prediction. The first is a kind of qualitative analysis method in which the effectiveness of forecasts depends largely on the capabilities and experience of experts. The other is the technical analysis method, which contains statistical methods and a data mining algorithm. According to academic studies and practical applications, methods relying solely on expert strategic analysis are insufficient to improve the prediction accuracy. Therefore, researchers have begun to pay more attention to the multisource heterogeneous data and to introduce deep learning methods into this field. In recent decades, the rapid development of the mobile Internet and online applications has brought the whole world into the big data era. It is more convenient for investors to share their opinions or have a discussion with others by pushing messages. People are also likely to browse the web before making investment decisions. All these activities provide multisource ...

Multisource financial sentiment analysis for detecting Bitcoin price change indications using deep learning

“…Recent works have demonstrated that taking into account external information, mainly provided in the form of sentiment regarding various financial assets [8,9,26,36], can significantly boost the performance of trading agents. At the same time, the development of powerful large-scale language models that can be trained on large collections of text documents, such as BERT [11] and roBERTA [6,7,16], which can be finedtuned on various tasks, such as sentiment analysis, provided additional powerful tools for automating sentiment extraction from online sources.…”

“…At the same time, the development of powerful large-scale language models that can be trained on large collections of text documents, such as BERT [11] and roBERTA [6,7,16], which can be finedtuned on various tasks, such as sentiment analysis, provided additional powerful tools for automating sentiment extraction from online sources. Indeed, it has been demonstrated that such information can be very useful for developing trading agents [23,26]. However, these approaches typically ignore that generic sentiment extractors, even when trained on large document collections, face significant challenges when used in domain-specific areas, such as finance [4].…”

“…Indeed, the additional complexity and development costs regarding collecting the appropriate data, preprocessing them, and then transforming them into a form that can be exploited by DL models often discourage DL researchers and companies from exploiting these valuable sources of information. Recent evidence suggests that external information, mainly provided in the form of sentiment regarding various financial assets [8,9,26,36] and typically collected from social media, often has a positive effect on the accuracy of trading agents. However, little work has been done so far in this direction, especially for exploiting large-scale datasets that contain news articles regarding financial assets, while many important questions arise when designing such a system.…”

Effect of public sentiment on stock market movement prediction during the COVID-19 outbreak

“…Online financial news and other news articles are crucial tools for making many decisions, which may be used in a variety of research areas through sentiment analysis. A novel sentiment analysis system based on a deep neural network was developed in (Shi et al 2021 ). The novel technique improved sentiment categorization by 9% when compared to the logistic regression method.…”

A Multi-Method Survey on the Use of Sentiment Analysis in Multivariate Financial Time Series Forecasting

“…Similar results were achieved in [ 16 ], where the application of text-mining technology to quantify the unstructured data containing social media views on stock-related news into sentiment scores increased the performance of the logistic regression algorithm. A more sophisticated approach that employs deep sentiment analysis was used to improve the performance of an SVM-based method in [ 17 ], indicating once again that sentiment features have a beneficial effect on the prediction.…”