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.

The purpose of this study is to propose a method of measuring service quality as well as suggesting to detect customer complaints through analysis of customer online reviews of mobile bank, which is unstructured data.

This study uses text mining approach for customer online reviews analysis. The research procedure includes: (1) extracting users' reviews for Kakao Mobile Bank, (2) pre-processing of the extracted review data, (3) analyzing the sentiment of each review, (4) measuring the service quality score of each dimension by analyzing keyword frequency and network for each polarity, (5) evaluating total score for mobile bank service quality, and (6) detecting customer complaints on online reviews.

There are some findings. First, from the customer's point of view, it was possible to see which factors are important among the various dimensions of service quality and which factors should be managed well in mobile banking setting. Second, by periodically finding customer complaints, service failures can be prevented early, and service quality and customer satisfaction can be improved.

From a practical point of view, mobile bank managers should pay more attention to the service quality dimensions of practicality and enjoyment. In addition, the results mean that the app design and aesthetics with the most negative reviews should be reviewed from the user's perspective rather than from the company's point of view. Second, it is possible for them to establish a systematic complaint management system that can prevent service failure in advance by detecting customer complaints early. Third, it is possible for them to make quick decisions regarding service quality with the help of real-time customer response through dashboard construction.

This paper is a pioneer study measuring service quality with sentiment analysis, one of the text mining applications, using customers' reviews of a mobile bank.

The purpose of this paper is to investigate investor behavior under two broad categories, market-wide sentiment and herding.

Using a dynamic factor model, that extracts distinct latent factors representing fluctuations in asset returns due to changes in fundamentals as well as investors’ sentiments, the paper investigates the impact of investor behavior on asset pricing.

Consistent with the literature, the results suggest that the behavioral factors play a significant role in explaining variation in the asset prices. However, the degree of influence depends on the nature of the stocks or portfolios. The findings conform to the hypothesis that behavioral factors play a more important role in explaining the price movements of high and medium valued stocks than those of smaller valued stocks. Further, the behavioral factors also exhibit high auto-correlation, depicting the pervasive nature of such factors, and proving that information cascades and other behavioral mechanisms propagate over a period of time leading to bubbles and market crashes. Finally, since herding is often associated with market volatility, the authors test the hypothesis using two measures of volatility and the result shows positive significant associations between them as suggested in the literature.

The paper presents a dynamic factor model to study the impact of investor behavior on asset returns using a conventional three factors model with behavioral factors. A factor model is proposed to extract distinct latent factors representing fluctuations in asset returns due to changes in fundamentals as well as investors’ sentiments. The study investigates investor behavior under two broad categories, market-wide sentiment and herding. Consistent with the literature, the results suggest that the behavioral factors play a significant role in explaining variation in the asset prices. However, the degree of influence depends on the nature of the stocks or portfolios. The findings conform to the hypothesis that behavioral factors play a more important role in explaining the price movements of high and medium valued stocks than those of smaller valued stocks. Further, the behavioral factors also exhibit high auto-correlation, depicting the pervasive nature of such factors, and proving that information cascades and other behavioral mechanisms propagate over a period of time leading to bubbles and market crashes.

The purpose of this paper is to analyse the NAV discount of European REITs listed in France, the Netherlands and the UK between 2003 and 2014, considering elements of both “rational” and “noise trader” approaches.

The analysis examines the hypothesis that discounts (premiums) are the result of leverage, size, liquidity, risk, performance, investment activity and sentiment. The regressions are initially run against the traditional NAV discount, subsequently using the unlevered NAV discount measure introduced by Morri et al. (2005) in order to clean out the bias generated by the level of leverage. The NAV discount is then adjusted for investor sentiment (appraisal reduction) with the aim of better identifying firm-specific factors, considering distortions induced by sentiment.

Higher liquidity commands lower discounts for French REITs, while Dutch and British REITs, which trade in markets characterized by a higher number of average daily transactions, do not seem to feature discounts resulting from liquidity. For all three samples, operational risk and performance are significant in explaining the NAV discount, the former having a positive relationship with the discount, and the latter a negative one. When measured using the average sector discount, sentiment has a profound effect on the discount, accounting alone for 10-15 per cent of the explanatory power of the model.

REITs listed in different markets behave differently. When the discount is adjusted in order to remove the bias resulting from the level of debt, the relationship between leverage and the unlevered discount becomes less pronounced in all cases.

The paper considers a new approach to NAV discount puzzle that takes into account market sentiment and appraisals.

The purpose of this paper is to determine whether individual investor sentiment and its factors influence investment decision-making behavior in the Indian stock market. The study contributes to the novel conceptual framework that integrates the impact of investor sentiment and outlines the role of its factors (herding, media factor, advocate recommendation and social interaction) during the investment decision-making process.

In this paper, data were collected using a structured questionnaire survey from Indian individual investors. It uses self-reported sources of information collected via a survey of individual investors and estimated the linkage via path modeling. The collected data were analyzed using partial least square structural equation modeling to examine the relationship between the construct, namely, herding, media, advocate recommendation and social interaction with investor sentiment and investment decision-making.

The study shows that herding, media factor, advocate recommendation and social interaction significantly and positively influence the investor sentiment. Among all the factors, social interaction has the lowest influence on investor sentiment. The study also reveals that investor sentiment has a positive impact on investment decision-making.

The study provides valuable insights for the individual investors, financial advisors, policymakers and other stakeholders. Knowledge of behavioral finance would enhance the decision-making capabilities of individual investors in the stock market. Thus, the study calls for the need to increase awareness among Indian investors about behavioral finance and its usefulness in investment decision-making. The paper also sheds light upon the influence of investor sentiment and its antecedents on investment decision-making. The study confirms that the investor relies on their sentiment while making investment decisions. Hence, the stakeholders in the stock market should focus on investor sentiment and other psychological aspects of individual investors as well.

There are very few studies that deal with the behavioral aspects of individual investors in an emerging market context. The study mainly focuses on the antecedent of investor sentiment and its influence on investment decision-making in the Indian stock market. To the best of authors’ knowledge, the present study unique nature that examines the impact of the antecedent of investor sentiment which was not explored in the Indian context and investment decision-making of individual investors.

A composite sentiment index (CSI) from quantitative proxy sentiment indicators is likely to be a lag sentiment measure as it reflects only the information absorbed in the market. Information theories and behavioral finance research suggest that market prices may not adjust to all the available information at a point in time. This study hypothesizes that the sentiment from the unincorporated information may provide possible market leads. Thus, this paper aims to discuss a method to identify the un-incorporated qualitative Sentiment from information unadjusted in the market price to test whether sentiment polarity from the information can impact stock returns. Factoring market sentiment extracted from unincorporated information (residual sentiment or sentiment backlog) in CSI is an essential step for developing an integrated sentiment index to explain deviation in asset prices from their intrinsic value. Identifying the unincorporated Sentiment also helps in text analytics to distinguish between current and future market sentiment.

Initially, this study collects the news from various textual sources and runs the NVivo tool to compute the corpus data’s sentiment polarity. Subsequently, using the predictability horizon technique, this paper mines the unincorporated component of the news’s sentiment polarity. This study regresses three months’ sentiment polarity (the current period and its lags for two months) on the NIFTY50 index of the National Stock Exchange of India. If the three-month lags are significant, it indicates that news sentiment from the three months is unabsorbed and is likely to impact the future NIFTY50 index. The sentiment is also conditionally tested for firm size, volatility and specific industry sector-dependence. This paper discusses the implications of the results.

Based on information theories and empirical findings, the paper demonstrates that it is possible to identify unincorporated information and extract the sentiment polarity to predict future market direction. The sentiment polarity variables are significant for the current period and two-month lags. The magnitude of the sentiment polarity coefficient has decreased from the current period to lag one and lag two. This study finds that the unabsorbed component or backlog of news consisted of mainly negative market news or unconfirmed news of the previous period, as illustrated in Tables 1 and 2 and Figure 2. The findings on unadjusted news effects vary with firm size, volatility and sectoral indices as depicted in Figures 3, 4, 5 and 6.

The related literature on sentiment index describes top-down/ bottom-up models using quantitative proxy sentiment indicators and natural language processing (NLP)/machine learning approaches to compute the sentiment from qualitative information to explain variance in market returns. NLP approaches use current period sentiment to understand market trends ignoring the unadjusted sentiment carried from the previous period. The underlying assumption here is that the market adjusts to all available information instantly, which is proved false in various empirical studies backed by information theories. The paper discusses a novel approach to identify and extract sentiment from unincorporated information, which is a critical sentiment measure for developing a holistic sentiment index, both in text analytics and in top-down quantitative models. Practitioners may use the methodology in the algorithmic trading models and conduct stock market research.

The purpose of this paper is to investigate the risk appetite in Hong Kong real estate and property security markets in the recent episode of global financial crisis.

An advanced methodology developed from the previous risk appetite measurement and Markov Chain Monte Carlo simulation is used. Traditional research on risk appetite had never been applied to the real estate market before because no options underlying properties exist. However, this paper makes a contribution that in the absence of options, risk appetite indicators are derived for the real estate and property security markets.

The empirical results show that the risk appetite for the real estate market started to fall markedly in the third quarter of 2008, matching the very period of the Sub‐prime Mortgage Crisis in the USA. By contrast, those for the property security index were stabilizing in that period. This implies that investors' risk attitude to the real estate market differs from that to the property security market. Furthermore, the correlations between the index prices and the corresponding risk appetite in each market suggest that investors are “risk neutral” in the real estate market, while they are “risk lovers” in the property security market.

This paper, to the authors' best knowledge, is the first study to explore the risk appetite indicator in the real estate market, which could enable us to shed new light on the market price movement from the perspective of investors' market sentiment.

The paper focuses on the variables that help analyze peer-to-peer (P2P) lending platforms. It explores the characteristic factors of identifying problematic platforms, and designs a P2P platform risk early warning model.

With the help of web crawler software, this paper crawls the information of 1427 P2P platforms from the two largest third-party lending information platforms (i.e. P2Peye and WDZJ) in China. SPSS 22.0 was mainly used for basic descriptive statistical analysis, reliability and validity analysis, and regression analysis of the data. MPLUS 7.0 was used for confirmatory factor analysis and structural equation models analysis.

Based on the multi-dimensional information, this paper performs text mining to develop an investor sentiment index. This study shows that the characteristics of the platform (i.e. basic features, capital security, operations management, and social network) have a significant impact on identifying problematic platforms.

There are some limitations to this research. In the process of model construction, some external factors may be ignored, such as government policies. Future research will need to consider the impact of policy and other factors more comprehensively on P2P lending platform risk identification.

This study proposes an effective method for investors and regulators to identify the risk factors of P2P lending platforms. The research findings provide valuable insights for promoting government participation in platform management as well as a healthy development of the P2P lending industry.

The paper addresses the factors that influence platform risks to help analyze P2P lending platforms. Prior research has not explored how to identify problematic P2P lending platforms in-depth and is limited by only focusing on either soft information or hard information. It identifies the characteristic factors of identifying problematic platforms and designs a P2P platform risk early warning model.

This paper is about the effects of unemployment on consumption behaviour through “job security” in Switzerland. Based on a behavioural model of consumption the paper establishes the links between job security and consumption empirically. In a second step, perceived “job security” as reported in the Swiss Consumer Survey is then connected with the labour market. The paper finds that the record high level of unemployment since 1991 has mainly caused the observed deterioration of the perceived “job security”. Two different scenarios of unemployment rates are then developed to show the quantitative effects unemployment had on perceived “job security” and finally through this measure of consumer confidence on consumption expenditures. In conclusion the unusually high number of unemployed have acted as a psychological shock to change the subjective assessment of “job security” to such a degree that significant changes in consumer behaviour have resulted.

The purpose of this paper is to assess whether the decision to issue warrants in an initial public offering (IPO) is subject to catering influences.

The approach used was to measure the market “warrant premium” and assess whether it relates to the probability of firms including warrants in their IPOs.

The evidence is strongly supportive of a catering influence on the firm's decision to include warrants in its IPO.

Sentiment is a factor in the selection of what securities a firm sells at its IPO. The findings lend further credence to the pervasiveness of catering.

No prior study has examined the role that catering plays in the selection of types of securities to sell.