Sentiment Index Research Articles

Deep Reinforcement Learning in Cryptocurrency Trading: A Profitable Approach

This study proposes an Automatic Cryptocurrency Trading System using Deep Reinforcement Learning (DRL). Six popular cryptocurrencies were used: Bitcoin, Ethereum, BinanceCoin, DogeCoin, Cardano, and WAVES. Development of the trading system started with building three timeseries models – Temporal Convolutional Neural Network (TCNN), Long Short-Term Memory Network (LSTM), and Gated Recurrent Unit Network (GRU) – to predict future prices. Then, cryptocurrency sentiment data was scraped using the Alternative.me API. Data on historical prices, predicted future prices, cryptocurrency sentiment index, technical indicators, and trading account information was fed as input states to three DRL Agents — Deep Q Network (DQN), Advantage Actor Critic (A2C), and Recurrent Proximal Policy Optimization (RPPO) — which were trained using a custom-developed trading environment. Each agent was given $1000 initial capital for all six cryptocurrencies to trade using three possible actions — Buy, Sell and Hold — and were back-tested on one year of unseen data. Our DQN model had the highest overall return on investment (ROI) of $740, an average 12.3% ROI across all six cryptocurrencies, with an ROI of 63.98% achieved for BinanceCoin. However, A2C and RPPO both had negative ROI.

Quantile connectedness between social network sentiment and sustainability index volatility: Evidence from the Moroccan financial market

The goal of this paper is to investigate the connectedness between investor sentiment and volatility on the environmental, social, and governance index (ESG) in Morocco. Therefore, on the basis of an investor sentiment index constructed from the X platform, and using quantile and frequency connectedness approaches, the findings reveal a significant connectedness between sentiment and ESG volatility, particularly during turbulent events. Although sentiment acts most of the time as a net receiver of shocks, notably during the COVID-19 pandemic and geopolitical crises, it sometimes becomes a net sender of shocks. Furthermore, the spillovers between sentiment and ESG volatility are determined mainly by the long-term component, especially during extreme events, implying the persistence of shock transmission due to high uncertainty. The results also illustrate the impact of market conditions on the spillovers between sentiment and ESG volatility. The conclusions of this study provide useful guidance for pro-ESG investors, policymakers, and companies.

Effect of Market-Wide Investor Sentiment on South African Government Bond Indices of Varying Maturities under Changing Market Conditions

The excess levels of investor participation coupled with irrational behaviour in the South African bond market causes excess volatility, which in turn exposes investors to losses. Consequently, the study aims to examine the effect of market-wide investor sentiment on government bond index returns of varying maturities under changing market conditions. This study constructs a new market-wide investor sentiment index for South Africa and uses the two-state Markov regime-switching model for the sample period 2007/03 to 2024/01. The findings illustrate that the effect investor sentiment has on government bond indices returns of varying maturities is regime-specific and time-varying. For instance, the 1–3-year government index return and the over-12-year government bond index were negatively affected by investor sentiment in a bull market condition and not in a bear market condition. Moreover, the bullish market condition prevailed among the returns of selected government bond indices of varying maturities. The findings suggest that the government bond market is adaptive, as proposed by AMH, and contains alternating efficiencies. The study contributes to the emerging market literature, which is limited. That being said, it uses market-wide investor sentiment as a tool to make pronunciations on asset selection, portfolio formulation, and portfolio diversification, which assists in limiting investor losses. Moreover, the findings of the study contribute to settling the debate surrounding the efficiency of bond markets and the effect between market-wide sentiment and bond index returns in South Africa. That being said, it is nonlinear, which is a better modelled using nonlinear models and alternates with market conditions, making the government bond market adaptive.

Online Portfolio Based on Trend Trading Strategy Considering Investor Sentiment Using Text Analysis

Intelligent online portfolios have become an important research topic in the field of quantitative finance. This paper proposes an online portfolio based on trend trading strategy using fuzzy logic technology analysis method and considering investor sentiment. Firstly, the paper uses SVM classification algorithm to analyze stock comment text data in online forums and constructs investor sentiment indicators. Secondly, the paper transforms the heuristic algorithm of technical trading into corresponding fuzzy IF-THEN rules and combines them into a fuzzy investment decision system. Thirdly, the paper constructs a new online portfolio based on trend trading strategy. Finally, the paper uses the text data of investor reviews and stock trading data on the internet for empirical analysis to illustrate the effectiveness of the online portfolio strategy constructed. The results indicate that online portfolios constructed based on trend trading strategies can achieve higher performance than benchmark strategies while considering transaction costs.

Exploring the synergy of guided numeric and text analysis in e-commerce: a comprehensive investigation into univariate and multivariate distributions

This research adopts a holistic approach to analyze customer reviews in the e-commerce industry by utilizing a combined approach of numerical and text analysis. Specifically, this study integrates univariate, multivariate, and sentiment analysis to gain comprehensive insights into product preferences and customer satisfaction. The methodology includes a detailed examination of univariate distributions to uncover numerical trends in product ratings and preferences. Multivariate distributions are explored to understand the complex relationships between related variables. Sentiment analysis is performed using the Sentiment Intensity Analyzer to categorize reviews into positive, neutral, and negative sentiments. Additionally, N-gram analysis is applied to both recommended and non-recommended reviews to identify key themes, such as dissatisfaction with product size and satisfaction with fit. Logistic regression and naive Bayes models are employed to classify sentiment, with logistic regression achieving high accuracy on both training (91.3%) and validation data (89.2%). This research highlights the significant role of product recommendations as indicators of positive sentiment, while product ratings reveal the complexity in consumer judgment. The study contributes significantly to understanding the dynamics of customer reviews in the e-commerce industry, providing a solid foundation for smarter decision-making to improve customer experience and product quality.

Shipping Market Forecasting Considering the Individual Investor Emotions: A Novel Twofold Partial Swarm Optimization Based Stacked Long Short-Term Memory Model

ABSTRACT Purpose The general purpose of shipping market prediction is to help shipping analysts design a strategy to make shipping strategies. Previous studies have pointed out human emotions has an obvious impact on markets, however, few research focus on utilizing human emotions to improve the shipping market forecasting issue. This paper fills the gap in the literature of considering industrial individual emotions to shipping market prediction issue Methodology We proposed a conceptual framework of an emotion-based shipping market prediction (ESMP) system focused on considering the multidimensional emotions of individual investors. To make it precisely, a two-fold Particle Swarm Optimization (TFPSO) algorithm is proposed conduct the shipping forecasting under the framework of ESMP, with advantages of automatically finding the architecture and hyperparameters of the Deep Long Short-Term Memory (DLSTM) simultaneously in the shipping market forecasting the values of the Baltic Dry, Dirty Tanker and Container indices of ocean transportation in the world ocean during the crisis period 2010–2022 Findings The prediction accuracy of the ESMP was higher than that of the models using the conventional factors in all learning periods of the study, and it was determined that the results complement the sentiment indicator employed to predict the shipping indices. Additionally, the accuracy of the proposed method is superior to conventional neural network models in all used error metrics. Additional Mann–Whitney U test on MSE difference between TFPSO-DLSTM and compared models demonstrates that the significant advantages boosted by TFPSO-DLSTM Originality Shipping sentiment has provided further proof that shipping decisions are significantly driven by emotions. our study shows that individual shipping investors’ sentiment are able to improve shipping rate forecasts significantly, although the magnitudes of the improvements are relatively small from an economic point of view Research implications This study undertook the initiative to procure BDI, BDTI, BCTI, COVID-19 data and shipping sentiment index data through in-depth interviews to provide first-hand perspectives into whether shipping sentiments impact the shipping market trend. It builds upon existing literature on the present stance of deep learning models, which largely relies non-sentiment factors. The study also extends prior literature on hyperparameter searching methods by highlighting the structure of searching method. Besides this, the contribution of this study also aligns with the prior discussions on evolving methodologies in temporal forecasting research Practical implications This study implies that shipping sentiments enables to make better shipping marketing trends, and foster sustainable growth. Shipping fear index serves for measuring investors’ attitude and mood toward shipping markets in terms of the general and certain sectors or assets, possibly promoting the movement of price and providing long-term investors and active traders with trading or arbitrage opportunities. Due to the complexities and regulations of the shipping market, it is essential to collaborate exclusively with shipping sentiment indices with artificial intelligent model in shipping market forecasting research

Media tone and trading activity on the Sydney Stock Exchange 1901–1950

We examine how media reports influenced trading volumes and order imbalances on the Sydney Stock Exchange (SSX) from 1901 to 1950, focusing on wool market reports as a substitute for broader financial advice in the absence of a specialised investment press. Given wool's status as Australia's primary export and its integration with various sectors, we construct a weekly media sentiment index based on news about wool sales and auctions from the Sydney Morning Herald. Our findings reveal that positive news about the wool market correlates with increased trading volumes and reduced order imbalances on the SSX. This relationship persisted during significant events such as the UK government's wool purchase plans, the 1929 Wall Street Crash, World War II-related trading restrictions, and the short selling ban.

The Contagion of Debt Default Risk in Energy Enterprises Considering Carbon Price Fluctuations

Under the constraints of low-carbon transformation goals, energy enterprises have significantly increased their debt default risk levels due to carbon price fluctuations. This article first analyzes the contagion mechanism of debt default risk among energy enterprises, and based on this, constructs a debt default risk contagion model among energy enterprises considering carbon price fluctuations, and then simulates and analyzes the evolution characteristics of debt default risk contagion among energy enterprises. The research results indicate that: (1) As the proportion of carbon emission cost increment and investor sentiment index increase, the stability of the debt network of energy enterprises strengthens. As the ratio of commercial credit among energy enterprises and influence of energy enterprises increase, the impact of debt risk gradually intensifies. (2) The investor sentiment index has a strengthening effect on the influence of energy enterprises, the proportion of commercial credit among energy enterprises, and the proportion of carbon emission cost increment. The commercial credit ratio between energy enterprises and its influence has a mutually reinforcing effect. (3) The investor sentiment index has suppressed debt default risk for various energy enterprises. The joint risk suppression effect of the proportion of carbon emission cost increment and the influence of energy enterprises in petroleum and petrochemical enterprises is more prominent. The joint risk constraint ability between the proportion of carbon emission cost increment and investor sentiment index in coal enterprises is stronger.

Effects of oil shocks on markets in G7 countries

This paper aims to assess the effects of oil price shocks on the stock markets of the G7 countries. We develop an oil sentiment indicator that measures the volatility of oil prices. We analyze oil shocks on the stock market of the G7 countries, using a structural VAR and Local Projection approach. Our results suggest that oil shocks explain 8% of the US stock market, 10% in Germany, and 7% in the UK. These results point out the possibility of using this sentiment variable for forecasting the stock market’s volatility.

A study on the impact of investor sentiment on individual stocks based on text mining

This paper investigates the influence of investor sentiment on individual stock prices through text mining. By reviewing relevant theories and literature, we utilized web crawler technology to collect comment data from the Eastmoney Stock Bar, constructing a comprehensive index of investor sentiment and an index of investor sentiment for individual stocks. Employing the VAR model and Granger causality test, we analyzed the correlation and dynamic relationship between investor sentiment and stock price fluctuations. The study found that stocks of different types of financial institutions react differently to investor sentiment, and that investor sentiment significantly affects stock prices. This paper puts forward corresponding policy recommendations, which can help market investors make scientific decisions and promote the healthy development of the market.

Time-varying risk aversion and international stock returns

We estimate aggregate, time-varying risk aversion inferred from options, stock returns and macroeconomic data for a panel of 8 countries. We document that, for most countries, the estimated risk aversion measure is counter-cyclical. Moreover, we show that estimated risk aversion forecasts monthly stock index returns up to 12 months ahead. This effect is statistically significant in panel regressions, and it survives the inclusion of additional control variables, such as an estimated of the variance risk premium, an investors’ sentiment index, and a measure of economic uncertainty. Finally, we show that risk aversion provides useful information to an investor who aims at timing the market. An investment strategy that uses the estimated time-varying risk aversion measure to solve a mean–variance asset allocation problem, delivers significantly positive returns.

African and international financial markets interdependencies: Does Covid-19 media coverage make any difference?

This study examines the co-movement and time-varying integration between equity, exchange rate, and international market volatility indices across different time–frequency domains using the wavelet and dynamic conditional correlation-generalised autoregressive conditional heteroskedasticity (DCC-GARCH) model and BEKK GARCH for selected African countries. First, the findings indicate that the co-movement between equity and exchange rates during the pandemic was exacerbated by global COVID-19 media coverage. The findings indicate that there has been a substantial risk transfer between exchange rates and stock returns during the COVID-19 pandemic, resulting in a decline in domestic stock returns and subsequent capital outflows, which in turn increased the exchange rate. Given the growing difficulties in diversification, specific information on the volatility of financial market connectedness is required to plan hedging strategies. To explore the influence of global market volatility on Africa’s equity and currency markets, it is crucial to analyse the relationship between regional and global market fluctuations, especially given the negative impact of the COVID-19 pandemic. Our empirical research demonstrates that the VIX and OVXCL indices play a significant role in transmitting spillovers to currency and equity markets in Africa. This suggests that the sentiment indicators provided by the VIX and OVXCL can be useful in predicting the behaviour of Africa’s currency and equity markets

Market perceptions of distress and its impact on returns: evidence from the U.S. commercial real estate market

ABSTRACT This paper examines the relationship between market participants’ sentiment regarding distress in the real estate market, captured through internet search queries, and the U.S. commercial real estate market. We use Google search frequency to construct a measure of market perception of distress, the Market Distress Perception Index (MDP Index), and determine the extent to which this index can help predict future private commercial real estate returns in the U.S. The results show that our pessimistic sentiment index predicts returns of commercial real estate up to three quarters in advance. These results hold at the national, regional, and state levels and are robust across various model specifications. The predictability of the sentiment index is especially pronounced during recessionary periods. We also analyse different property sectors and find that the inverse relationship between the MDP Index and future private commercial real estate returns persists across all sectors except the industrial sector. The relationship is strongest for the office sector.

Headlines or Hashtags? The battle in social media for investor sentiment in the stock market

This study tackles the complex task of measuring investor sentiment, a latent variable often measured through various proxies. The focus here is on textual sentiment extracted from online sources, specifically news media and social media sentiment. The central inquiry is whether these proxies are equivalent indicators of investor sentiment. Employing firm-level daily sentiment scores for DJIA stocks and leveraging Granger causality and transfer entropy, the research investigates the dynamics of information flow between these proxies. The findings show a prevailing pattern: information predominantly flows from social media to news for the majority of stocks while a reverse relationship is established for some stocks. The variations across stocks suggest that these proxies do not uniformly capture the same underlying phenomena. The study shows the significant role of social media in shaping news media sentiment and prompts considerations about regulating social media platforms in the context of their impact on financial markets.

Business Cycle Variations in Manager and Investor Sentiment Indices

I find that the highly regarded investor and manager sentiment indices demonstrate both cyclical and persistent variations. The presence of cyclicality in the orthogonalized indices suggests the existence of feedback loops connecting sentiment with economic or market outcomes. For example, optimistic sentiment can stimulate increased consumer spending and investment, thereby fostering economic growth and further boosting sentiment. These feedback loops have the potential to amplify cyclical sentiment trends and increase the volatility of economic and market cycles, leading to persistent cycles driven by feedback mechanisms. Importantly, my results remain robust against potential mean reversion resulting from heuristic behaviors such as herding and overreaction, as well as against random behavior arising from intermittent bubbles characterized by near-rational learning and potential overextrapolation bias.

Influence and predictive power of sentiment: Evidence from the lithium market

This study aims to unveil the relationship between the lithium market and sentiment indicators across various levels: market-wide (VIX), industry-specific (DRIV), and individual perspectives (ChatGPT-extracted scores), and to assess their predictive power on lithium prices. Our analysis reveals the significant impact of three sentiments on lithium markets regarding impulse response. Furthermore, VIX primarily serves as a spillover transmitter while others act as receivers concerning spillover transmission. Lastly, we empirically demonstrate the predictive power of VIX, and combining VIX with DRIV further enhances predictive performance. These findings emphasize the importance of sentiments in the lithium market and offer valuable insights for industry stakeholders.

The Nexus Between Investors’ Sentiment and Hedge Funds Risk Premiums

Abstract In this study, we analyzed how the systematic risk of hedge funds affects different portfolio strategies. Using monthly returns data from a sample of developed market hedge funds grouped by five strategies, we identified the systematic factors influencing returns variation from January 2003 to December 2023. Market, size effect, momentum, investment effect, and bond spread were found to be the main risk factors explaining hedge fund returns dynamics. We proposed an enhanced version of the Fung and Hsieh (2004a) model, which demonstrated improved representativity with Baker and Wurgler sentiment index included as a risk premium. The quantile regression revealed that for most strategies, the estimated models performed better for the bottom quantiles.

Expectations, sentiments and capital flows to emerging market economies

This paper provides a novel look at capital flow determinants by assessing the role of expectations and media sentiments. Analyzing eight emerging market economies, we assess the effects of macroeconomic expectations and disagreement among professionals and various media-based sentiment indicators. Our results show that survey and sentiment indicators which are available in real time contain useful information about capital flow dynamics which go beyond the effects of conventional push and pull factors for all countries we analyze. News sentiment related to the exchange rate have the strongest effects on capital flows. Finally, we identify substantial heterogeneity across countries.

The role of central bank communication in the long-term stock-bond correlations: Evidence from China

In this paper, we extend the traditional DCC-MIDAS-X model by incorporating the central bank communication sentiment indicator to examine its effect on the long-term correlations between stock and bond returns. Our results show that positive central bank communication can reduce stock-bond correlation. The effect changes over time depending on the state of the economy, which is significant during upturns but not noticeable during recessions.

Public Opinion in Conflict Situations: A Sentiment Analysis of Tweets About Russia During the War on Ukraine

ABSTRACT Wars not only bring death and suffering to the conflicting parties, but they can also trigger a spiral of negative emotions in the countries observing the conflict. This study examines global public opinion at the start of the invasion of Ukraine in 2022 by analyzing comments about Russia on X (formerly Twitter) in 127 countries. Using Python, the sentiment levels (positive, negative, neutral) of a total sample of 429,408 tweets in 48 languages were estimated. In addition to quantifying a net sentiment index for each country, the study focuses on the possible existence of differences in terms of military, political and cultural factors. The results show that sentiment towards Russia after the invasion was negative in most countries around the world, although there were significant differences between opinions in NATO countries and those allied with Russia. Additionally, public opinion was less negative in individualistic countries compared to those with collectivist societies.