Search results

This study quantified companies' views on the COVID-19 pandemic with sentiment analysis of US public companies' disclosures. The study aims to provide timely insights to shareholders, investors and consumers by exploring sentiment trends and changes in the industry and the relationship with stock price indices.

From more than 50,000 Form 10-K and Form 10-Q published between 2020 and 2021, over one million texts related to the COVID-19 pandemic were extracted. Applying the FinBERT fine-tuned for this study, the texts were classified into positive, negative and neutral sentiments. The correlations between sentiment trends, differences in sentiment distribution by industry and stock price indices were investigated by statistically testing the changes and distribution of quantified sentiments.

First, there were quantitative changes in texts related to the COVID-19 pandemic in the US companies' disclosures. In addition, the changes in the trend of positive and negative sentiments were found. Second, industry patterns of positive and negative sentiment changes were similar, but no similarities were found in neutral sentiments. Third, in analyzing the relationship between the representative US stock indices and the sentiment trends, the results indicated a positive relationship with positive sentiments and a negative relationship with negative sentiments.

Performing sentiment analysis on formal documents like Securities and Exchange Commission (SEC) filings, this study was differentiated from previous studies by revealing the quantitative changes of sentiment implied in the documents and the trend over time. Moreover, an appropriate data preprocessing procedure and analysis method were presented for the time-series analysis of the SEC filings.

This paper aims to investigate the impact of climate change news on the dynamics of US stock indices.

The empirical basis of the study was 3,209 news articles. Sentiment analysis was performed by a pre-trained bidirectional FinBERT neural network. Thematic modeling is based on the neural network, BERTopic.

The results show that news sentiment can influence the dynamics of stock indices. In addition, five main news topics (finance and politics natural disasters and consequences industrial sector and Innovations activism and culture coronavirus pandemic) were identified, which showed a significant impact on the financial market.

First, we extend the theoretical concepts. This study applies signaling theory and overreaction theory to the US stock market in the context of climate change. Second, in addition to the news sentiment, the impact of major news topics on US stock market returns is examined. Third, we examine the impact of sentimental and thematic news variables on US stock market indicators of economic sectors. Previous works reveal the impact of climate change news on specific sectors of the economy. This paper includes stock indices of the economic sectors most related to the topic of climate change. Fourth, the research methodology consists of modern algorithms. An advanced textual analysis method for sentiment classification is applied: a pre-trained bidirectional FinBERT neural network. Modern thematic modeling is carried out using a model based on the neural network, BERTopic. The most extensive topics are “finance and politics of climate change” and “natural disasters and consequences.”

Predicting the stock market's prices has always been an interesting topic since its closely related to making money. Recently, the advances in natural language processing (NLP) have opened new perspectives for solving this task. The purpose of this paper is to show a state-of-the-art natural language approach to using language in predicting the stock market.

In this paper, the conventional statistical models for time-series prediction are implemented as a benchmark. Then, for methodological comparison, various state-of-the-art natural language models ranging from the baseline convolutional and recurrent neural network models to the most advanced transformer-based models are developed, implemented and tested.

Experimental results show that there is a correlation between the textual information in the news headlines and stock price prediction. The model based on the GRU (gated recurrent unit) cell with one linear layer, which takes pairs of the historical prices and the sentiment score calculated using transformer-based models, achieved the best result.

This study provides an insight into how to use NLP to improve stock price prediction and shows that there is a correlation between news headlines and stock price prediction.

The goal of the study is to examine the effects of news sentiment and topics dominating in the news field prior to the initial public offering (IPO) on the IPO underpricing.

The authors’ approach has several steps. The first is textual analysis. To detect the dominating topics in the news, the authors use Latent Dirichlet allocation. The authors use bidirectional encoder representations from transformers (BERT) pretrained on financial news corpus to evaluate the tonality of articles. The second is evaluation of feature importance. To this end, a linear regression with robust estimators and Classification and Regression Tree and Random Forest are used. The third is data. The text data consists of 345,731 news articles from Thomson Reuters related to the USA in the date range from 1 January 2011 to 31 May 2018. The data contains all the possible topics from the website, excluding anything related to sports. The sample of 386 initial public offerings completed in the USA from 1 January 2011 to 31 May 2018 was collected from Bloomberg Database.

The authors found that sentiment of the media regarding the companies going public influences IPO underpricing. Some topics, namely, the climate change and environmental policies and the trade war between the US and China, have influence on IPO underpricing if they appear in the media prior to the IPO day.

The puzzle of IPO underpricing is studied from the point of Narrative Economics theory for the first time. While most of the works cover only some specific news segment, we use Thomson Reuters news aggregator, which uses such sources The New York Post, CNN, Fox, Atlantic, The Washington Post ? Buzzfeed. To evaluate the sentiment of the articles, a state-of-the-art approach BERT is used. The hypothesis that some common narratives or topics in the public discussion may impose influence on such example of biased behaviour like IPO underpricing has also found confirmation.

This study aims to explore the risk spillover effects among different sectors of the Chinese stock market after the outbreak of COVID-19 from both Internet sentiment and price fluctuations.

The authors develop four indicators used for risk contagion analysis, including Internet investors and news sentiments constructed by the FinBERT model, together with realized and jump volatilities yielded by high-frequency data. The authors also apply the time-varying parameter vector autoregressive (TVP-VAR) model-based and the tail-based connectedness framework to investigate the interdependence of tail risk during catastrophic events.

The empirical analysis provides meaningful results related to the COVID-19 pandemic, stock market conditions and tail behavior. The results show that after the outbreak of COVID-19, the connectivity between risk spillovers in China's stock market has grown, indicating the increased instability of the connected system and enhanced connectivity in the tail. The changes in network structure during COVID-19 pandemic are not only reflected by the increased spillover connectivity but also by the closer relationships between some industries. The authors also found that major public events could significantly impact total connectedness. In addition, spillovers and network structures vary with market conditions and tend to exhibit a highly connected network structure during extreme market status.

The results confirm the connectivity between sentiments and volatilities spillovers in China's stock market, especially in the tails. The conclusion further expands the practical application and theoretical framework of behavioral finance and also lays a theoretical basis for investors to focus on the practical application of volatility prediction and risk management across stock sectors.

Environmental, social and governance (ESG) factors have become increasingly important in investment decisions, leading to a surge in ESG investing and the rise of sustainable investment assets. Nevertheless, challenges in ESG disclosure, such as quantifying unstructured data, lack of guidelines and comparability, rampantly exist. ESG rating agencies play a crucial role in assessing corporate ESG performance, but concerns over their credibility and reliability persist. To address these issues, researchers are increasingly utilizing machine learning (ML) tools to enhance ESG reporting and evaluation. By leveraging ML, accounting practitioners and researchers gain deeper insights into the relationship between ESG practices and financial performance, offering a more data-driven understanding of ESG impacts on business communities.

The authors review the current research on ESG disclosure and ESG performance disagreement, followed by the review of current ESG research with ML tools in three areas: connecting ML with ESG disclosures, integrating ML with ESG rating disagreement and employing ML with ESG in other settings. By comparing different research's ML applications in ESG research, the authors conclude the positive and negative sides of those research studies.

The practice of ESG reporting and assurance is on the rise, but still in its technical infancy. ML methods offer advantages over traditional approaches in accounting, efficiently handling large, unstructured data and capturing complex patterns, contributing to their superiority. ML methods excel in prediction accuracy, making them ideal for tasks like fraud detection and financial forecasting. Their adaptability and feature interaction capabilities make them well-suited for addressing diverse and evolving accounting problems, surpassing traditional methods in accuracy and insight.

The authors broadly review the accounting research with the ML method in ESG-related issues. By emphasizing the advantages of ML compared to traditional methods, the authors offer suggestions for future research in ML applications in ESG-related fields.

As one of the most influential theories in strategic management, Hambrick and Mason’s Upper Echelons Theory has yielded significant conceptual and empirical advancements linking executive characteristics and perceptions to decision-making. Specifically, work on this theory consistently shows that CEOs’ decisions are biased by personal characteristics to the benefit and detriment of firms. While this stream of research links executive decision processes to outcomes such as executive dismissals, analyst evaluations, and press coverage, surprisingly little is understood about if and whether the information CEOs convey is subject to the same filtering process by a firm’s key evaluators. Thus, in this chapter, we aim to extend Upper Echelons Theory by positing that a double filtering process occurs whereby the cognitive aids CEOs use can be informed by not only their cognitive base and values but also the characteristics and priorities of those who evaluate the nonverbal and verbal signals they send. To do so, we build on recent conceptual and empirical advancements to make a case for the decision-making biases and tendencies that influence signal interpretation by three key evaluator groups internal and external to the firm: boards of directors, financial analysts, and the media. We conclude by considering the implications of evaluators’ information filtering and how this more holistic view of Upper Echelons decision-making can enable executive teams to be strategic with the cognitive aids they use to influence evaluations.

The purpose of this study is to determine stock market reactions to the news about innovations and other types of publications for illiquid stocks.

(1) The authors opt for machine learning techniques and expert analysis and propose their own lexicon of innovations based on the news articles published on the professional website; (2) the dataset consists of the data on 2,000 US companies for 6 years; (3) the text analysis including BERT and Top2 Vec models which are superior to Latent Dirichlet allocation (LDA) in information criteria allows for more accurate evaluation of news sentiment and idea; and (4) furthermore, random forest and gradient boosting were applied to increase validity of results and demonstrate factor importance.

(1) The paper presents theoretical findings adding to signalling theory and efficient market hypothesis for US illiquid stocks; (2) this study suggests that information on product innovations (unlike other types of innovations) has a direct and significant effect on the return of illiquid stocks; (3) the results also give evidence that under uncertainty innovation-related publications do not affect the return of illiquid stocks; and (4) the analysis of the news topics (narratives) demonstrates that only the narrative related to important corporate announcements has a positive impact on the return of illiquid stocks.

(1) The authors are the first to conduct a large-scale study of the impact of various information on the return of illiquid stocks; (2) the paper focuses on information on several types of innovations with regard to the return of illiquid stocks; (3) based on Top2 Vec model, this study identifies the key topics-narratives discussed by investors and assesses their impact on the return of illiquid stocks; and (4) as an information source, the authors use the sample comprising a total of 1.4m news articles released on the professional website for investors “Benzinga”.