Daily happiness and stock returns: Some international evidence
Introduction
Traditional financial theory is based on the assumptions of investors’ rationality and homogeneity that leaves no role for irrational behavior in asset pricing [1]. However, the behavioral economics has shifted the academic focus to investigate the relations between investor sentiment and asset prices. Meanwhile, market participants play an active role in generating “fashion” in stock market, which leads to investor’s maniac behavior.1 All the facts recognize the role of sentiment in explaining and predicting the stock returns.
The existence of noise traders and psychological biases are viewed as the assumptions by most theoretical models on investigating the impact of investor sentiment on stock prices. De Long et al. [3] firstly observe that irrational noise traders could not be offset by limited arbitrageurs; rather, with erroneous beliefs and diverse sentiment, they could actually affect the stock prices and earn higher expected returns. Barberis et al. [4] develop a parsimonious model of investor sentiment to partially explain the underreaction and overreaction. Daniel et al. [5] propose a model populated with overconfidence and self-attribution bias and show that both of them can cause the changes in autocorrelations of returns and excess volatility. Hong et al. [6] also develop a model with boundedly rational investors (news watchers and momentum traders) and show their explanatory power for the short-run continuation and long-run reversal of the prices. All these theoretical predictions provide a general framework for analyzing and interpreting the empirical results.
In order to investigate the implications of the above-mentioned theoretical predictions, scholars endeavor to construct various proxies for investor sentiment in their empirical work. In general, there are mainly three categories of proxies to measure investor sentiment according to the source of sentiment from which the proxy is extracted. The first category refers to the stock market-based proxies. This category includes the fluctuations in discounts of closed-end funds [7], the net mutual fund redemptions [8], bid–ask spreads and turnover [9], the combinations of the closed-end fund discount, NYSE share turnover, the number and average first-day returns on IPOs, the equity share in new issues and the dividend premium [10], [11] as well as the portfolio allocations to equity versus cash and fixed-income securities [12]. As for the second category, empiricists use the survey-based proxies such as the Investor Intelligence by American Association of Individual Investors [13], [14], [15], [16], [17], Consumer Confidence by the Conference Board (CBIND) and Consumer Confidence by University of Michigan Survey Research Center [18], UBS/Gallup survey [19] and animusX-Investors sentiment [20]. The third category is the proxies extracted from the news and social media content. This category includes sentiment extracted from the Raging Bull [21], Yahoo! Finance [22], [23], [24], Wall Street Journal [25], Twitter [26], Google Insights [27], Facebook [28] and Google Trends [29]. These studies usually construct a time series proxy for investor sentiment and examine the contemporaneous and lead-lag relations between the constructed sentiment proxy and market variables (short-term returns, abnormal trading volume and excess volatility) as well as give mixed findings on the predictability and correlation coefficient.
In this paper, we also attempt to examine the relations between the investor sentiment released by social media and the stock market activities. Naturally, it is also connected to plenty of studies on the dynamics between online behaviors and stock market movements [30], [31], [32], [33], [34], [35], [36], [37], [38], [39], [40], [41], [42], [43], [44]. The main contribution of our paper compared with others is to exploit a novel sentiment proxy, i.e., the daily happiness index extracted from Twitter, across 11 international stock markets, perform the contemporaneous correlation regression model with the consideration of trading volume as well as provide impact of happiness on index return and range-based volatility with cross-sectional analysis.
The remainder of this paper is organized as follows. Section 2 describes the daily happiness index and capital data. Section 3 performs the contemporaneous correlation, the Granger causality and the cross-sectional analysis between the daily happiness and major stock indexes. Section 4 sets forth the robustness test and Section 5 concludes.
Section snippets
Data description
We obtain raw daily happiness from the website (http://hedonometer.org/index.html). The raw daily happiness scores are derived from the natural language processing technique based on a random sampling of about 10% (50 million) of all messages posted in Twitter. To quantify the happiness of the language, the Amazon’s Mechanical Turk service is used to score the level of happiness of selected words appeared on Twitter, e.g., laughter, joy, successful, winning, excellent, rainbow. To avoid the
Empirical analysis
This section presents relations between happiness sentiment and index return. We calculate contemporaneous correlation and Kendall correlation coefficient in Section 3.1, perform the Granger causality test in Section 3.2 and provide the cross-sectional analysis of the impact of happiness on index return and volatility in Section 3.3.
Robustness
To ensure that our main results are not driven by the classification of subgroup, we re-estimate the models in Sections 3.1 The contemporaneous correlation, 3.2 Granger causality with classifying the happiness sentiment into quintiles from the least to the happiest days, i.e., the least-happiness subgroup, the 2-happiness subgroup, 3-happiness subgroup and most-happiness subgroup. Table 10 reports the main results on Kendall correlation coefficients, as well as the impact of happiness
Concluding remarks
This paper employs daily happiness index from Twitter as a novel proxy for sentiment and investigate its relations to index return across 11 international stock markets. By partitioning the happiness sentiment into quintiles from the least to the happiest days, we firstly observe the statistical property of daily happiness and show the contemporary correlation coefficients between happiness and index return in the 4 and most-happiness subgroups are higher than that in the least, 2, 3-happiness
Acknowledgment
This work is supported by the National Natural Science Foundation of China (71201112, 71320107003 and 71532009).
References (50)
- et al.
A model of investor sentiment
J. Financ. Econ.
(1998) - et al.
Market liquidity as a sentiment indicator
J. Financ. Mark.
(2004) - et al.
Stock market volatility, excess returns, and the role of investor sentiment
J. Bank. Finance
(2002) - et al.
Investor sentiment and the near-term stock market
J. Empir. Finance
(2004) - et al.
Investor sentiment from internet message postings and the predictability of stock returns
J. Econ. Behav. Organ.
(2014) - et al.
Twitter mood predicts the stock market
J. Comput. Sci.
(2011) - et al.
Forecasting abnormal stock returns and trading volume using investor sentiment: Evidence from online search
Int. J. Forecast.
(2011) - et al.
Facebook’s daily sentiment and international stock markets
J. Econ. Behav. Organ.
(2014) - et al.
Trading and non-trading period Internet information flow and intraday return volatility
Physica A
(2016) - et al.
Network interdependency between social media and stock trading activities: Evidence from China
Physica A
(2016)
Open source information, investor attention, and asset pricing
Econ. Modell.
Has microblogging changed stock market behavior? Evidence from China
Physica A
Internet information arrival and volatility of SME PRICE INDEX
Physica A
Some recent development in a concept of causality
J. Econometrics
Capital asset prices: A theory of market equilibrium under conditions of risk
J. Finance
DotCom mania: The rise and fall of internet stock prices
J. Finance
Noise trader risk in financial markets
J. Polit. Econ.
Investor psychology and security market under- and overreactions
J. Finance
A unified theory of underreaction, momentum trading, and overreaction in asset markets
J. Finance
Investor sentiment and the closed-end fund puzzle
J. Finance
Do measures of investor sentiment predict returns?
J. Financ. Quant. Anal.
Investor sentiment and the cross-section of stock returns
J. Finance
Investor sentiment in the stock market
J. Econ. Perspect.
Relative sentiment and stock returns
Financ. Anal. J.
How useful is the sentiment index?
Financ. Anal. J.
Cited by (77)
Firm-specific new media sentiment and price synchronicity
2024, Research in International Business and FinanceManagerial sentiments, non-performing loans, and banks financial performance: A causal mediation approach
2023, Chaos, Solitons and FractalsDoes happy Twitter forecast gold price?
2023, Resources PolicyExtreme sentiment and herding: Evidence from the cryptocurrency market
2022, Research in International Business and FinanceTwitter's daily happiness sentiment, economic policy uncertainty, and stock index fluctuations
2022, North American Journal of Economics and FinanceCitation Excerpt :Despite several proxies for such emotions (like closed-end fund discount, stock turnover, number of IPOs, dividend premium, etc.) have been proposed to measure investor sentiment (Laborda & Olmo, 2014), Twitter’s happiness sentiment has been proved to be an important predictor of stock price fluctuations due to widespread use of the Internet (Bollen et al., 2011). Following this strand of literature, the linkage between Twitter’s happiness sentiment variation and stock price fluctuation (or stock return) has been found in major stock markets worldwide (Naeem, Farid, Faruk, & Shahzad, 2020; Shen et al., 2018; Zhang et al., 2016, 2018) and some specific stock markets such as Singapore (Zhao, 2019) and the U.S. (Affuso & Lahtinen, 2019; Arias et al., 2014; Broadstock & Zhang, 2019; Lee & Chen, 2020; Li et al., 2017; You et al., 2017a; Zhao, 2020a, 2020b). Economic policy uncertainty (EPU) is a theme that has been widely explored ever since EPU was constructed by Baker, Bloom, and Davis (2016), and it is shown to be a good proxy for real economic policy uncertainty.
Quantile connectedness between sentiment and financial markets: Evidence from the S&P 500 twitter sentiment index
2022, International Review of Financial AnalysisCitation Excerpt :These include the Twitter happiness index and the S&P500 Twitter Sentiment Index. Many studies explore the relationship between the Twitter happiness index and financial markets (e,g., Zhang, Li, Shen, and Teglio (2016), You, Guo, and Peng (2017), Li, Shen, Xue, & Zhang, 2017, Zhao, 2020, Naeem, Farid, Balli, & Shahzad, 2020; Li, Goodell, & Shen, 2021b)), results from these studies reveal that the Twitter sentiment index significantly causes the returns of various international markets. A second index, the recently created S&P500 Twitter sentiment index measures the performance of 200 S&P500 companies with high sentiment scores.