Financial sentiment analysis of news articles with long text corpus for equity portfolio construction

Sentiment analysis as a sub-field of natural language processing has received increased attention in the past decade enabling organisations to more effectively manage their reputation through online media monitoring. Many drivers impact reputation, however, this thesis focuses only the aspect of financial performance and explores the gap with regards to financial sentiment analysis in a South African context. Results showed that pre-trained sentiment analysers are least effective for this task and that traditional lexicon-based and machine learning approaches are best suited to predict financial sentiment of news articles. The evaluated methods produced accuracies of 84%–94%. The predicted sentiments correlated quite well with share price and highlighted the potential use of sentiment as an indicator of financial performance. A main contribution of the study was updating an existing sentiment dictionary for financial sentiment analysis. Model generalisation was less acceptable due to the limited amount of training data used. Future work includes expanding the data set to improve general usability and contribute to an open-source financial sentiment analyser for South African data.

Financial sentiment analysis is crucial for making informed decisions in the financial markets, as it helps predict trends, guide investments, and assess economic conditions. Traditional methods for financial sentiment classification, such as Support Vector Machines (SVM), Random Forests, and Logistic Regression, served as our baseline models. While somewhat effective, these conventional approaches often struggled to capture the complexity and nuance of financial language. Recent advancements in deep learning, particularly transformer-based models like GPT and BERT, have significantly enhanced sentiment analysis by capturing intricate linguistic patterns. In this study, we explore the application of deep learning for financial sentiment analysis, focusing on fine-tuning GPT-4o, GPT-4o-mini, BERT, and FinBERT, alongside comparisons with traditional models. To ensure optimal configurations, we performed hyperparameter tuning using Bayesian optimization across 100 trials. Using a combined dataset of FiQA and Financial PhraseBank, we first apply zero-shot classification and then fine tune each model to improve performance. The results demonstrate substantial improvements in sentiment prediction accuracy post-fine-tuning, with GPT-4o-mini showing strong efficiency and performance. Our findings highlight the potential of deep learning models, particularly GPT models, in advancing financial sentiment classification, offering valuable insights for investors and financial analysts seeking to understand market sentiment and make data-driven decisions.

The purpose of this study is to investigate the enhancement of Financial Sentiment Analysis by conducting an in-depth investigation of Natural Language Processing (NLP) approaches for the purpose of improving market prediction. The purpose of this research is to investigate the potential of natural language processing (NLP) to improve the accuracy and efficiency of sentiment analysis. This is in response to the complex structure of financial markets and the crucial role that sentiment plays. The examination of the relevant literature highlights the limits of traditional methods and the urgent need for creative solutions in the field of financial sentiment research. The approach that we use entails the careful collecting of data from social media and financial news, with a particular emphasis on the utilization of strong pre-processing tools. The research assesses the performance parameters of accuracy, precision, recall, and correlation with market trends by using natural language processing (NLP) technologies such as algorithms for sentiment analysis, Named Entity Recognition, and deep learning models. The findings include a comparative examination of conventional methods and those based on natural language processing (NLP), therefore revealing insights into the significant influence that sentiment has on market patterns. The results not only provide a contribution to the theoretical knowledge of sentiment research, but they also offer real consequences for financial analysts who are looking to make market forecasts that are more accurate and timelier. The research suggests ways for refinement, with an emphasis on enhanced pre-processing and Explainable AI integration. These tactics are being proposed to address issues in data quality and bias. When looking to the future, the study provides an overview of potential future paths, which include the investigation of external influences and the development of deep learning models for accurate market forecasting respectively. To summaries, the findings of this research establish natural language processing (NLP) as a revolutionary force in the process of redefining financial sentiment analysis. Furthermore, it offers a path for future developments in the ever-changing world of market prediction.

— This paper examines the important role of analyzing financial sentiment in comprehending market trends and investor actions. In a time where public sentiment can significantly influence financial outcomes, it is crucial for both investors and analysts to evaluate the emotions present in text data from diverse sources like social media, financial news, and earnings call transcripts. The article provides a comprehensive summary of key methods such as Natural Language Processing (NLP), machine learning, deep learning, and sentiment lexicons, all of which are crucial for effectively capturing and interpreting financial sentiment. Financial sentiment analysis applications are thoroughly discussed, with an emphasis on predicting stock market trends, managing risks, and evaluating consumer sentiment. Case studies highlight practical applications, showing how sentiment analysis can improve forecast precision and impact investment tactics. Moreover, the publication addresses the challenges encountered in the field, such as identifying sarcasm and dealing with data interference, which hinder the examination of nuanced language and contextual understandings. In the future, the publication will examine predicted patterns influenced by advancements in artificial intelligence and big data technology, highlighting the potential for more thorough examination of extensive datasets. This study seeks to provide financial professionals with the understanding needed to navigate the complexities of market sentiment by presenting a fair representation of both the opportunities and constraints in financial sentiment analysis. In the end, this report contributes to the growing field of financial analysis, paving the way for further research and practical use in a market that is becoming more based on sentiment.

Financial Sentiment Analysis (FSA) is an important domain application of sentiment analysis that has gained increasing attention in the past decade. FSA research falls into two main streams. The first stream focuses on defining tasks and developing techniques for FSA, and its main objective is to improve the performances of various FSA tasks by advancing methods and using/curating human-annotated datasets. The second stream of research focuses on using financial sentiment, implicitly or explicitly, for downstream applications on financial markets, which has received more research efforts. The main objective is to discover appropriate market applications for existing techniques. More specifically, the application of FSA mainly includes hypothesis testing and predictive modeling in financial markets. This survey conducts a comprehensive review of FSA research in both the technique and application areas and proposes several frameworks to help understand the two areas’ interactive relationship. This article defines a clearer scope for FSA studies and conceptualizes the FSA-investor sentiment-market sentiment relationship. Major findings, challenges, and future research directions for both FSA techniques and applications have also been summarized and discussed.

Sentiment analysis aims to identify the way in which sentiments are expressed in texts. State-of-the-art approaches base their analyses solely on the given text, which complicates the detection of implicit sentiments and ignores the role of sentiment contagion. In the financial domain, sentiment could be spread across multiple platforms, such as in company and analyst reports, news articles, and microblogs. Thus, to capture implicit sentiments and the contagion process, we introduce a novel approach that leverages the text and contextual information of a record for fine-grained sentiment analysis. Based on this information, we generate a record representation, which is used in an adapted feed-forward neural network. Our proposed solution improves the performance by as much as 15% and 234% relative to multiple baselines. Our work demonstrates the impact of implicit sentiment as well as the importance of different relationships for sentiment prediction on company and analyst reports, news articles, and microblogs. For example, we identified timestamp information as being non-essential for the fine-grained sentiment analysis of company and analyst reports. Although we are able to showcase improvements in financial sentiment analysis, sentiment contagion and limited context are two common problems that continue to prevail. Therefore, by re-defining sentiment analysis as a multi-text problem, our proposed solution can be applied across multiple domains and text types, such as product reviews.

In this study, we explore the susceptibility of financial sentiment analysis to adversarial attacks that manipulate financial texts. With the rise of AI readership in the financial sector, companies are adapting their language and disclosures to fit AI processing better, leading to concerns about the potential for manipulation. In the finance literature, keyword-based methods, such as dictionaries, are still widely used for financial sentiment analysis due to their perceived transparency. However, our research demonstrates the vulnerability of keyword-based approaches by successfully generating adversarial attacks using the sophisticated transformer model, GPT-3. With a success rate of nearly 99% for negative sentences in the Financial Phrase Bank, a widely used database for financial sentiment analysis, we highlight the importance of incorporating robust methods, such as context-aware approaches such as BERT, in financial sentiment analysis.

Financial text analytics methods are employed to examine social media comments, allowing investors to gain insights and make informed financial decisions. Some emojis within these comments often convey diverse semantics, emotions, or intentions depending on the context. However, traditional financial text analysis methods relying on public annotations struggle to identify implicit expressions, leading to suboptimal performance. To address this challenge, this paper proposes an implicit expression recognition model of emojis in social media comments (IER-SMCEM). Firstly, IER-SMCEM innovative designs a data enhancement method based on the implicit expression of emoji. This method expands the pure text financial sentiment analysis dataset into the implicit expression dataset of emoji by homophonic replacement. Secondly, IER-SMCEM designs a prompt learning template to identify the implicit expression of emoji. Through hand-designed templates, large-scale language models can predict the true meaning that emojis are most likely to express. Finally, IER-SMCEM recovers implicit expression by choosing the predictions of models. Thus, the downstream financial sentiment analysis model can more precisely realize the sentiment recognition of the text with emoji by the recovered text. The experimental results indicate that IER-SMCEM achieves a 98.03% accuracy in semantically recovering implicit expressions within financial texts. In the task of financial sentiment analysis, the sentiment analysis model achieves the highest accuracy of 3.99% after restoring the true implied expression of the texts. Therefore, the model can be effectively applied to sentiment analysis or quantitative analysis.

The growing investment in tools that can improve decision-making and financial analysis increase the demand for developing new technologies that can support the financial and economic domains. One of the modern and more challenging technology is financial sentiment analysis (SA). SA pre-trained models have proved Their effectiveness because of the rareness of labeled data in the financial domain. The pre-trained models can deal with this issue because It's trained on corpora for specific domains. In this study, Different transformers including models based on BERT and RoBERTa are fine-tuned by a 6k Financial Sentiment dataset from Kaggle. Then we applied the ensemble learning with majority voting. Our results present the enhancement in every measured metric on current state-of-the-art results for transformer-based models and majority voting. We find that ensemble learning with majority voting outperforms state-of-the-art individual transformer-based models.

Since the research of sentiment analysis is mostly concentrated in the field of sentiment analysis on Weibo, and there is less research on sentiment analysis of financial text, this thesis proposes a financial sentiment analysis model based on pre-training and TextCNN. First, the pre-trained model is used to initially extract the emotional features of the text. It can extract text features well, and can extract information between words at arbitrary intervals when processing text sequences. Then use the improved TextCNN to construct a sentiment analysis network to further extract the sentiment features of the text, effectively identify the sentiment of the text, and complete the sentiment analysis of financial text. This thesis conducts experiments on a balanced corpus data set based on financial texts, and compares it with other classic sentiment analysis algorithms. Experimental results show that the proposed method works best in the field of financial text sentiment analysis.

Sentiment analysis of news and media material can provide important details about events and causal relationships. Bangla text sentiment analysis is getting increasingly popular. As a market indicator, financial market participants use financial sentiment analysis. In Bangla, financial sentiment analysis is a less-explored research field. In this research, we attempt to analyze the emotion of Bangla financial news items. In this study, we created a dataset with titles of news articles classified as positive or negative from a well-known online web portal that provides business and financial news. We employ vector-based feature encoding and different machine learning approaches to illustrate the method’s effectiveness. Our findings are encouraging, and they suggest the way forward for Bengali sentiment analysis research in the financial sector.

The Chinese stock market, one of the largest and most dynamic emerging markets, is characterized by individual investor dominance and strong policy influence, resulting in high volatility and complex dynamics. These distinctive features pose substantial challenges for accurate forecasting. Existing models like RNNs, LSTMs, and Transformers often struggle with non-stationary data and long-term dependencies, limiting their forecasting effectiveness. This study proposes a hybrid forecasting framework integrating the Non-stationary Autoformer (NSAutoformer), LASSO feature selection, and financial sentiment analysis. LASSO selects key features from diverse structured variables, mitigating multicollinearity and enhancing interpretability. Sentiment indices are extracted from investor comments and news articles using an expanded Chinese financial sentiment dictionary, capturing psychological drivers of market behavior. Experimental evaluations on the Shanghai Stock Exchange Composite Index show that LASSO-NSAutoformer outperforms the NSAutoformer, reducing MAE by 8.75%. Additional multi-step forecasting and time-window analyses confirm the method’s effectiveness and stability. By integrating multi-source data, feature selection, and sentiment analysis, this framework offers a reliable forecasting approach for investors and researchers in complex financial environments.

ABSTRACTThere is an increasing interest in financial text mining tasks. Significant progress has been made by using deep learning‐based models on a generic corpus, which also shows reasonable results on financial text mining tasks such as financial sentiment analysis. However, financial sentiment analysis is still demanding work because of the insufficiency of labeled data for the financial domain and its specialized language. General‐purpose deep learning methods are not as effective mainly due to specialized language used in the financial context. In this study, we focus on enhancing the performance of financial text mining tasks by improving the existing pretrained language models via NLP transfer learning. Pretrained language models demand a small quantity of labeled samples, and they could be enhanced to a greater extent by training them on domain‐specific corpora instead. We propose an enhanced model FinSentiment, which incorporates enhanced versions of a number of recently proposed pretrained models, such as BERT, XLNet, RoBERTa, GPT, Llama, and T5, to better perform across NLP tasks in financial domain by training these models on financial domain corpora. The corresponding finance‐specific models in FinSentiment are called Fin‐BERT, Fin‐XLNet, Fin‐RoBERTa, Fin‐GPT, Fin‐Llama, and Fin‐T5, respectively. We also propose variants of these models jointly trained over financial domain and general corpora. Our finance‐specific FinSentiment models, in general, show the best performance across three financial sentiment analysis datasets, even when only a subpart of these models is fine‐tuned with a smaller training set. Our results exhibit enhancement for each tested performance criteria on the existing results for these datasets. Extensive experimental results demonstrate the effectiveness and robustness of especially RoBERTa pretrained on financial corpora. Overall, we show that NLP transfer learning techniques are favorable solutions to financial sentiment analysis tasks. Our source code has been deposited at https://github.com/seferlab/finsentiment.

With a speedy development in Natural Language processing, the financial sector meets the demand of analyzing a large quantity of financial text data. Several recent research has focused on the subject of Financial Sentiment Analysis (FSA). In this article, we worked on sentiment analysis which is one of the most popular areas of natural language processing. We tried to use the sentiment analysis of news in the financial market, as sometimes news has a very strong impact on the stock market. We used the data of P. Malo [18] containing the 5,000 sentences of the finance news with labels of the sentiment. This study uses machine learning and deep learning algorithms as a research approach to develop a comprehensive comparative study on Financial News Sentiment Analysis that includes data sources. We compared the classification accuracy performance of machine learning and deep learning algorithms such as SVM, KNN, Decision Tree, Random Forest, XGBoost, CNN, and LSTM in a sentiment analysis of financial news. Our inspirations in the future direction such as handling data imbalance also discussed and applied for algorithms. The experiments demonstrate that the CNN algorithm, based on accuracy, consistently outperforms the other models in the performance of sentiment analysis of financial news.

Investors are constantly aware of the behaviour of stock markets. This affects their emotions and motivates them to buy or sell shares. Financial sentiment analysis allows us to understand the effect of social media reactions and emotions on the stock market and vice versa. In this research, we analyse Twitter data and important worldwide financial indices to answer the following question: How does the polarity generated by Twitter posts influence the behaviour of financial indices during pandemics? This study is based on the financial sentiment analysis of influential Twitter accounts and its relationship with the behaviour of important financial indices. To carry out this analysis, we used fundamental and technical financial analysis combined with a lexicon-based approach on financial Twitter accounts. We calculated the correlations between the polarities of financial market indicators and posts on Twitter by applying a date shift on tweets. In addition, correlations were identified days before and after the existing posts on financial Twitter accounts. Our findings show that the markets reacted 0 to 10 days after the information was shared and disseminated on Twitter during the COVID-19 pandemic and 0 to 15 days after the information was shared and disseminated on Twitter during the H1N1 pandemic. We identified an inverse relationship: Twitter accounts presented reactions to financial market behaviour within a period of 0 to 11 days during the H1N1 pandemic and 0 to 6 days during the COVID-19 pandemic. We also found that our method is better at detecting highly shifted correlations by using SenticNet compared with other lexicons. With SenticNet, it is possible to detect correlations even on the same day as the Twitter posts. The most influential Twitter accounts during the period of the pandemic were The New York Times, Bloomberg, CNN News and Investing.com, presenting a very high correlation between sentiments on Twitter and stock market behaviour. The combination of a lexicon-based approach is enhanced by a shifted correlation analysis, as latent or hidden correlations can be found in data.