Sentiment Index Research Articles

Market informed portfolio optimization methods with hybrid quantum computing

AbstractThis document presents a portfolio optimization framework that employs a hybrid quantum computing algorithm and a futures market sentiment indicator—The Market Sentiment Meter (MSM) variable, developed jointly by CME Group and 1QBit. The methodology used was the Variational Quantum Eigensolver (VQE). The work presented here is divided into four portfolio optimization problem formulations, of binary and continuous variable formulations, determining which assets to pick their weights. This work demonstrates that adding the MSM variable can improve the performance of hybrid quantum solutions, by informing the asset selection problem with market environment information through the four MSM states.

Integrating sentiment information for risk prediction: the case of crude oil futures market in China

AbstractThis paper incorporates investor sentiment indexes into the traditional standard heterogeneous autoregressive (HAR) model to improve its power on predicting crude oil futures risk. Using the 5-min high-frequency trading data to construct the daily realized volatility, the original and revised HAR models are used for in-sample regression and out-of-sample forecasting on a daily, weekly, and monthly basis. The results show that the sentiment indexes and the search trend contain incremental information for forecasting the realized volatility of INE crude oil futures in the short and medium term. The search volume is the best indicator for weekly risk forecasting of INE crude oil futures. No robust index can improve the performance of HAR-type model on long-term risk prediction. This paper thus highlights that market participants should select appropriate strategies to minimize risk when volatility is at stake for their decisions.

Stock Market Forecasting Using a Neural Network Through Fundamental Indicators, Technical Indicators and Market Sentiment Analysis

AbstractThe objective of this research is to provide evidence that it is possible to obtain a prediction that better aligns with the future performance of a stock if a neural network model is trained with stock market analysis variables and qualitative variables. As a case study, thirty-three companies’ representative of the S&P 500 are selected, and a multilayer perceptron artificial neural network is built and trained with input parameter indicators of fundamental analysis, technical analysis, and market sentiment. By incorporating the latter as an additional variable, the model's accuracy increases by 1.5% for 66% of the companies analyzed. The results confirm the crucial role played by the selection of the neural network model and its variables depending on the type of company to be analyzed. The main contributions of this research are the identification of the best variables combination to train a neural network model depending on the market sector to be analyzed, likewise it is demonstrated that, by using market sentiment, it is possible obtain a high accuracy or increase the accuracy to an existing model.

Predicting Tourist Arrivals in Greece With a Novel Tourism-Specific Business Leading Indicator

We introduce a novel tourism-specific business expectations sentiment index and explore whether it can operate as a leading indicator for international tourist arrivals in Greece. Using monthly data spanning 2002‐2021 and employing a VAR model, we document that this newly introduced tourism-specific business expectations index serves as a leading indicator, whose higher levels foreshadow increased demand for international travel. We also find that its inclusion in a tourism-oriented model increases forecasting accuracy, which can be utilized by travel agent businesses, local government officials, and policymakers in their efforts to predict tourist arrivals in Greece.

The construction of a Chinese fine-grained sentiment dictionary for Chinese domestic investors (CN-FSD) and its application

Stock bar comment texts are used to forecast stock market trends because they contain sentiment data provided by investors. However, previous research has relied on generic or polar sentiment dictionaries to construct sentiment indicators, which has limited progress in this field. This paper crawls nearly 1.8 million stock bar comment texts from the Eastmoney (www.eastmoney.com) Stock Bar Forum to perform sentiment analysis in this specialized area of the financial market. It reclassifies existing Chinese sentiment dictionaries, and utilizes Word2Vec and CNN models and word frequency statistics with a penalty mechanism to extract polar sentiment words. Additionally, the improved PMI (Pointwise Mutual Information) algorithm was utilized for fine-grained segmentation of negative emotion words. Finally, a fine-grained sentiment dictionary (four categories: happy, anger, sad and fear; with a total of 6155 words) was established for Chinese domestic investors (denoted by CN-FSD). We found that the improved PMI algorithm increased accuracy by 14%. In addition, we introduce the investor sentiment quantification indicators from two aspects, i.e., fine-grained sentiments and on the emotion theory dimension of psychology from the valence and arousal dimensions. This is done to verify the validity and robustness of the constructed dictionary. The case study from 2019 to 2022 discovered that under the influence of extreme occurrences like COVID-19, the fine-grained sentiment indicators constructed in this study are found to be significantly more strongly correlated with market trend indicators like index return and trading volume than the existing polar or fine-grained sentiment dictionaries. ‘fear’ emotions in fine-grained emotions dominate the stock market. Just as this case study emphasize the importance of ‘fear’ sentiment, studying the indicators of high arousal sentiment is also important. This case study further validates the efficacy of CN-FSD.

The Impact of Park Environmental Characteristics and Visitor Perceptions on Visitor Emotions from a Cross-Cultural Perspective

Assessing the perception of urban parks and understanding the relationship between environmental characteristics and conflicts in park usage are crucial for the design and management of urban parks. However, quantifying perceptions of parks in large spaces poses challenges, and different regional cultures also exhibit variations in park usage. Therefore, this study aims to explore from a cross-cultural perspective how the environmental characteristics and perceptions of parks affect visitors' emotions. This research collected online comment data from Weibo check-ins in Shanghai and tweets in London between 2022 and 2023. It applied natural language processing (NLP) technology using SnowNLP for sentiment semantic keyword extraction, identifying the sentiment index of each data entry to quantify visitors' sentiments towards urban parks in Shanghai and London. Simultaneously, street view panoramas were obtained for semantic segmentation using the SegNet model and ADE20K to quantify spatial perceptions as independent variables. On this basis, we used nonlinear regression models and MGWR models to explore the relationship between visitors' sentiment values in parks and the park environment. The results showed that walkability in Shanghai was found to more easily bring positive sentiments to visitors, while visitors in London paid more attention to imageability. Walkability, accessibility, and imageability are of the same importance in Shanghai and London, but the correlation and emphasis of visitor perceptions differ, indicating potential conflicts in park usage among different user groups in the two cities' urban parks. Overall, our study offers differentiated planning suggestions that can provide information for urban design decisions, ultimately contributing to the improvement of human well-being.

The effect of COVID-19 vaccine on the international financial markets

Existing studies on the COVID-19 pandemic and vaccine development have primarily documented their effects on stock markets, with limited attention to international financial markets. This paper constructs a news-based sentiment index on COVID-19 vaccine development and examines its effects on international financial markets during the first year of the pandemic. We find positive vaccine sentiment decreases the CBOE Volatility Index (VIX) while boosting capital inflows and currency appreciation in emerging markets. It also reduces the unit price of risk in the context of carry trade risk premiums, as positive developments lower future risk and economic uncertainty.

Examining the Relationship Between Consumer Sentiment and Stock Price Returns

This study centers on exploring the dynamic relationship between the University of Michigan Consumer Sentiment Index (UMCSI) and the S&P 500 Index, employing both a bivariate regression model and Granger Causality analysis. The aim is to provide deeper insights into how fluctuations in consumer sentiment, as reflected by the UMCSI, impact and are impacted by movements in the S&P 500 Index. Furthermore, Granger Causality analysis is employed to discern the directionality of this relationship. The results indicate that the S&P 500 Index Granger Causes the UMCSI, implying that past values of the S&P 500 Index contain predictive information about future changes in consumer sentiment. This finding suggests that stock market movements can potentially serve as leading indicators of shifts in consumer confidence, offering predictive insights into broader economic trends and consumer behavior.

Results of Economic Tendency Surveys in Nowcasting GDP Growth

The article proves the usefulness of including aggregate information from economic tendency surveys in the system of nowcasting of economic growth. The authors compare the efficiency of vector autoregressive models that include the economic sentiment indicator based on the results of Rosstat business activity and consumer expectations surveys, and the business climate indicator based on the results of the Bank of Russia enterprise monitoring.Statistical testing of time series of composite indicators and GDP volume index confirmed a significant correlation and causality between them, as well as the similarity of their cyclical profiles. Both indices pass cyclical turning points synchronously or ahead of the GDP volume index, their predictive capabilities are enhanced by the early availability of information. The capabilities of GDP growth nowcasting using survey information are assessed in three specifications of the vector autoregressive model with dummy variables. On the in-sample period, the model including two composite indicators and the GDP volume index demonstrates the highest accuracy.The proposed approach allows us to obtain flash estimates of GDP growth prospects that are significantly ahead of the official statistical information

Research on the Impact of Economic Policy Uncertainty and Investor Sentiment on the Growth Enterprise Market Return in China—An Empirical Study Based on TVP-SV-VAR Model

This study employs the economic policy uncertainty index to gauge the level of economic policy uncertainty in China. Utilizing textual data from the growth enterprise market internet community, we construct the growth enterprise market investor sentiment index by applying the deep learning ERNIE (Enhanced Representation through Knowledge Integration) model, thereby capturing investors’ sentiment within the growth enterprise market. The dynamic interplay between economic policy uncertainty, investor sentiment, and returns of the growth enterprise market is scrutinized via the TVP-SV-VAR (time-varying parameter stochastic volatility vector auto-regression) model, and the asymmetric response of different industries’ stock returns within the growth enterprise market to economic policy uncertainty and investor sentiment shock. The findings of this research are that economic policy uncertainty exerts a negative influence on both investor sentiment and returns of the growth enterprise market. While it may trigger a temporary decline in stock prices, the empirical evidence suggests that the impact is of short duration. The influence of investor sentiment on the growth enterprise market returns is characterized by a reversal effect, suggesting that improved sentiment may initially boost stock prices but could lead to a subsequent decline over the long term. The relationship between economic policy uncertainty, investor sentiment, and returns of the growth enterprise market is time-variant, with heightened sensitivity observed during bull markets. Lastly, the effects of economic policy uncertainty and investor sentiment on the returns of different industries within the growth enterprise market are found to be asymmetric. These conclusions contribute to the existing body of literature on the Chinese capital market, offering a deeper understanding of the complex dynamics and the factors influencing market behavior.

Exploring information demand in the maritime industry: a Google Trends approach

ABSTRACT The fundamental impetus for this research is the documented wide use of Google and the ensuing applications of Google Trends in behavioural economics. Expanding the existing literature, we focus on addressing the question of whether information demand from individual investors can reflect a freight rates sentiment. This is achieved by analysing Google queries referring to investment in maritime stocks and other related markets. These searches comprise essentially a blend of information and intuition. More specifically, we examine whether the most frequently searched term and topic referred to Baltic Dry Index (BDI) can serve as a reliable and valid positive or negative sentiment market proxies. We find a negative impact on freight rates, capital markets, and the number of available dry bulk fleet, providing evidence aligned with the risk-averse investor theory. We unveil bidirectional interactions between our sentiment index and the two out of three examined maritime markets, supporting the rejection of the efficient market hypothesis. Our study also verifies the similar effects of information demand and media-produced sentiment indexes on the corresponding market. We succeed in confirming sentiment’s predictability out-of-sample for BDI. Beyond the academic value, our findings suggest a manner of enhancing the accuracy of freight rates predictions for practitioners.

Opinion divergence, investor sentiment, and stock liquidity: Evidence from social media

ABSTRACT This paper developed a mediating effect model of retail opinion divergence, investor sentiment, and stock liquidity to investigate how investor comments and bullish-bearish-polling activities on social media affect investors’ attitudes and behaviours, thus, the stock market. The paper first used the Python programming language to scrape the bullish-bearish-polling outcomes for each stock and developed an investor opinion divergence index. Next, the study collected online investor comments, from which an online investor sentiment index was developed through machine-learning-based ways. The analysis results show that both investor sentiment and retail opinion divergence significantly impact stock liquidity, and investor sentiment plays a mediating role in it.

Unravelling the complex interactions between sentiment of uncertainty and foreign capital flows: Evidence from Brazil and South Korea

Brazil and South Korea have both been known to implement capital controls during emerging market crises to address the complexity of foreign capital flows, which affects international investor behaviour. This research studies Brazil and South Korea bond and stock flows and sentiment of economic and political uncertainty (SEPU), a local news-based sentiment indicator, using a novel time-varying technique. Findings show multiple short-term occasions where increased SEPU strangely boosts equity flows, contrary to the assumption that uncertainty discourages equity investment. This paradoxical discovery is linked to a "behavioural arbitrage strategy" in which risk-seeking investors employ informational asymmetries to capitalize on increased uncertainty. Foreign investors prefer South Korean over Brazilian bonds due to the former country's stronger policy framework. The second significant finding is that equity inflows increase uncertainty (negative domestic sentiment in media) during acute crises. We conclude that inflation, recession, geopolitical risk, financial instability, and tight monetary policy amplify this feedback loop.

Time-frequency comovements between news sentiments, Non-fungible tokens, and DeFi assets: evidence from the wavelet analysis

ABSTRACT Growth in digitalization has created a potential boost for Non-fungible tokens (NFTs) and decentralized finance (DeFis) assets in the modern world. Therefore, this study aims to examine the comovement between the recently developed comprehensive measure of news sentiment index (NSI) and selected digital assets. For this purpose, we have utilized the wavelet transform, wavelet correlation, and wavelet coherence econometric model to assess interdependency in both time and frequency between news sentiments and digital assets. Our wavelet correlation and covariance results suggest that almost all the digital assets exhibit a negative relationship with NSI. Moreover, the wavelet coherence results confirm that there is no significant comovement in the short to medium-term horizon, suggesting that both NFTs and DeFi can be used as hedges against the NSI. Furthermore, we observe small patches of significant negative comovement between NSI and digital assets in the long term, which correspond to the initial days of COVID-19. Our results confirm selected digital assets’ hedging role against news-driven uncertainty. This study finding provides essential information to policymakers, international investors, and investment managers to make effective decisions.

Embracing market dynamics in the post-COVID era: A data-driven analysis of investor sentiment and behavioral characteristics in stock index futures returns

This paper aims to enhance the understanding and prediction of stock market behavior during unexpected events like the COVID-19 pandemic, with a specific focus on the role of market attention, social media sentiment indicators, and the development and evolution of unexpected events. We highlight that the common trading and technical indicators used in forecasting the stock index futures prices often overlook investor sentiment and pandemic-related data, which can be instrumental in predicting stock market behavior during significant emergencies. In response, we propose a multi-faceted approach that incorporates these overlooked factors. First, we enhance the predictive index system by integrating investor sentiment, derived from stock message board commentary, and investor behavior influenced by the development and evolution of the pandemic. This innovative approach refines our model's predictive capabilities and is validated through comparative analysis. Second, we introduce a hybrid framework for predicting stock index futures closing prices. By decomposing the closing price series into long-term trends, cyclical variations, and random fluctuations, we create a more nuanced forecast. Each component is predicted separately using appropriate time-series algorithms, improving the overall predictive accuracy and offering generalizability and scalability. Third, we devise a dynamic trading strategy that recognizes pandemic-related data, evolving over time, as a pivotal factor. This strategy is adaptable to evolving market conditions, and our experimental evidence demonstrates its effectiveness in yielding higher returns and reducing associated risks. Our findings underline the importance of incorporating investor sentiment and pandemic-related data into stock market predictions, thus offering a more comprehensive and accurate approach to market forecasting and risk management.

Sentiment and Stock Characteristics: Comprehensive Study of Individual Investor Influence on Returns, Volatility, and Trading Volumes

Abstract Background Traditional asset pricing models face challenges from financial anomalies, prompting exploration through behavioural finance theory. This study analyses the nuanced relationship between individual investor sentiment and key stock market variables. Objectives To assess the impact of individual investor sentiment on stock returns, volatilities, and trading volumes using the American Association of Individual Investors (AAII) sentiment index. Methods/Approach Using regression models, we examine the relationship between individual investor sentiment and various stock characteristics across 480 components of the Standard & Poor's 500 index. Results We find a positive relationship between the AAII sentiment index and stock returns and a negative relationship with volatility and trading volume. Conclusions Our study contributes to understanding the intricate role of individual investor sentiment in financial markets.

Economic Influences on Plantation Sector Stock Prices in Malaysia: A Quantile Regression Approach

This study aims to examine the relationship between microeconomic, sentiment, and macroeconomic variables across three quantiles (q25, q50, and q75) of stock prices in the Malaysian plantation sector. This study used Earnings per share (EPS) and return on equity (ROE) as the proxy for microeconomic variables, consumer sentiment index (CSI), and business condition index (BCI) as the proxy for sentiment variables, while inflation (INF which proxy from consumer price index) and exchange rate (ER, RM/USD) as the proxy for macroeconomic variables. Using a panel dataset covering 32 listed companies in plantation sector from 2008Q3 to 2023Q3. Result of quantile regression indicates that EPS, BCI, INF have a consistently positive and statistically significant relationship with stock prices across all quantiles. ROE has a mixed impact, with a positive relationship at the 25th and 50th quantile, but with a negative relationship at the 75th quantile. Furthermore, CSI and ER have a consistently negative and statistically significant relationship with stock prices across all quantiles.

Spillover between investor sentiment and volatility: The role of social media

We examine the spillover effects between social media sentiments and market-implied volatilities among stock, bond, foreign exchange, and commodity markets. We find that information mainly spillovers from volatility to sentiment indices, with the VIX being the most significant net transmitter. Within each asset class, there is a more pronounced spillover from volatility to sentiment compared to the reverse, implying that a significant portion of investor sentiment is volatility-driven. This relationship intensifies in turbulent economic periods, such as during the Global Financial Crisis, Brexit, the US-China trade war, and the COVID-19 pandemic. Our analysis also reveals that sentiment indices can transition from net receivers to net transmitters of shocks during turbulent periods. This can be explained by the echo chamber effect, where social media echo prevailing news signals, and some investors interpret repeated signals as genuinely new information.

Does Twitter happiness predict bullish markets? A study of the US stock markets

The evolving literature on using Twitter to capture investor sentiment suggests that stock market performance is linearly associated with Twitter's public mood. We investigate whether investor sentiment determined by the Twitter sentiment index (TSI) has a nonlinear predictive power for stock market behaviour. Using a dataset of seven US stock markets, we apply the cointegration techniques to show the relationship between Twitter sentiment and stock market behaviour. The results suggest a dynamic nonlinear cointegrating relationship. During the short run, Twitter happiness has a substantial effect on stock market indices, while in the long run, it has a moderating effect. Twitter happiness has a dominant effect on the US stock market indices than unhappy Twitter. These results highlight Twitter's growing role in predicting the stock market behaviour and show that the TSI acts as a better predictor of investor sentiment.

Demystifying the dynamic relationship between news sentiment index and ESG stocks: Evidence from time-frequency wavelet analysis

Using the Time-Frequency Wavelet Analysis, this study investigates the dynamic connectedness between the News Sentiment Index (NSI) and ESG leader indices of developed countries. The empirical findings clearly show nontrivial dynamic comovements between NSI and the ESG indices and the existence of the ESG market volatility in different frequency scales. We also report some discrepancies in cross-linkage patterns among different countries. In particular, such associations for some countries (e.g., Australia and the United Kingdom) are negative, with the leading role of the ESG index against market risk due to high fluctuations in sentiments. These findings suggest that ESG stocks possess potential hedging and diversifying features and safe-haven attributes against market risk driven by negative sentiment during the outbreak of Black Swan events. Our empirical results have insightful implications for investors, portfolio managers, and policymakers.