Impact of network investor sentiment and news arrival on jumps

This paper studied the influence of news announcements and network investor sentiment on Chinese stock index and index futures market jumps. A machine learning text analysis algorithm was employed to measure investor forum sentiment. It was found that news arrivals were an important reason for jump occurrences, jumps were significantly associated with network investor sentiment, and while occasionally the news and network investor sentiment resulted in simultaneous market jumps, they appeared to be relatively independent. The network investor sentiment time-lag and asymmetric effects were also tested, from which it was found that network investor sentiment had a significant asymmetric effect on the jumps, but time-lag effects had little influence. News announcements and the top 25% of the extreme network sentiments were found to explain more than 50% of the jumps, with extreme sentiments tending to increase the volatility of the news-related jumps and persistently influencing returns after the news-related jumps.     

News will tell: Forecasting foreign exchange rates based on news story events in the economy calendar

The paper proposes a novel approach to predict intraday directional-movements of currency-pairs in the foreign exchange market based on news story events in the economy calendar. Prior work on using textual data for forecasting foreign exchange market developments does not consider economy calendar events. We consider a rich set of text analytics methods to extract information from news story events and propose a novel sentiment dictionary for the foreign exchange market. The paper shows how news events and corresponding news stories provide valuable information to increase forecast accuracy and inform trading decisions. More specifically, using textual data together with technical indicators as inputs to different machine learning models reveals that the accuracy of market predictions shortly after the release of news is substantially higher than in other periods, which suggests the feasibility of news-based trading. Furthermore, empirical results identify a combination of a gradient boosting algorithm, our new sentiment dictionary, and text-features based-on term frequency weighting to offer the most accurate forecasts. These findings are valuable for traders, risk managers and other consumers of foreign exchange market forecasts and offer guidance how to design accurate prediction systems.     

News sentiment,credit spreads,and information asymmetry

This paper examines how the sentiment of firm-specific news affects CDS spreads conditional on the degree of information asymmetry. Using a large set of news releases, we document a strong negative relationship between the sentiment of firm-specific news and CDS spreads. More importantly, consistent with the role of public news in reducing information asymmetry, we find evidence that the relation between news sentiment and CDS spreads is stronger for firms with higher information asymmetry. Furthermore, the relation is stronger for news with negative sentiment and during the 2008 financial crisis. Our results are robust to alternative sentiment measures.     

How does news sentiment impact asset volatility? Evidence from long memory and regime-switching approaches

This paper examines the dynamic relationship between firm-level return volatility and public news sentiment. By using the new RavenPack News Analytics ⿿ Dow Jones Edition database that captures over 1200 types of firm-specific and macroeconomic news releases and their sentiment scores at high frequencies, we investigate the circumstances in which public news sentiment is related to the intraday volatility of the constituent stocks in the Dow Jones Composite Average (DJN 65). Two different conditionally heteroskedastic models are employed: the Fractionally Integrated Generalized Autoregressive Conditionally Heteroskedastic (FIGARCH) and the two-state Markov Regime-Switching GARCH (RS-GARCH) models. For most of the DJN 65 stocks, our results confirm the significant impact of firm-specific news sentiment on intraday volatility persistence, even after controlling for the potential effects of macroeconomic news. Compared with macroeconomic news sentiment, firm-specific news sentiment apparently accounts for a greater proportion of overall volatility persistence. Moreover, negative news has a greater impact on volatility than positive news. Furthermore, the results from the RS-GARCH model indicate that news sentiment accounts for a greater proportion of volatility persistence in the high-volatility regime (turbulent state) than in the low-volatility regime (calm state). In-sample forecasting performance and residual diagnostic tests suggest that FIGARCH generally outperforms RS-GARCH.     

Scheduled macroeconomic news announcements and intraday market sentiment

We analyze the effects of scheduled macroeconomic news on intraday and daily market sentiment by comparing sentiment on news announcement dates with that on non-announcement dates. Announcements of macroeconomic indicators change neither intraday nor daily market sentiment. However, the directions of the announced values have asymmetric effects on intraday market sentiment, although they do not affect daily market sentiment. For example, an announcement of an increase in the gross domestic product (GDP) reduces short-term intraday market sentiment, whereas an announcement of a decrease in GDP does not significantly affect intraday market sentiment. We also find that the effect of intraday market sentiment on short-term market returns is greater following announcements of macroeconomic indicators that significantly affect intraday market sentiment.     

Jumps,cojumps and macro announcements

We use recently proposed tests to extract jumps and cojumps from three types of assets: stock index futures, bond futures, and exchange rates. We then characterize the dynamics of these discontinuities and informally relate them to US macroeconomic releases before using limited dependent variable models to formally model how news surprises explain (co)jumps. Nonfarm payroll and federal funds target announcements are the most important news across asset classes. Trade balance shocks are important for foreign exchange jumps. We relate the size, frequency and timing of jumps across asset classes to the likely sources of shocks and the relation of asset prices to fundamentals in the respective classes. Copyright © 2010 John Wiley & Sons, Ltd.     

Daily news sentiment and monthly surveys: A mixed-frequency dynamic factor model for nowcasting consumer confidence

Policymakers, firms, and investors closely monitor traditional survey-based consumer confidence indicators and treat them as an important piece of economic information. To obtain a daily nowcast of monthly consumer confidence, we introduce a latent factor model for the vector of monthly survey-based consumer confidence and daily sentiment embedded in economic media news articles. The proposed mixed-frequency dynamic factor model uses a Toeplitz correlation matrix to account for the serial correlation in the high-frequency sentiment measurement errors. We find significant accuracy gains in nowcasting survey-based Belgian consumer confidence with economic media news sentiment.     

Political sentiment and MAX effect

The well-known “MAX effect” documents that stocks with high maximum daily returns in the past month underperform those with low maximum daily returns. We show that such an effect varies with firm-level political sentiment. Among firms with low political sentiment, the usual MAX strategy gives a monthly risk-adjusted return of 1.52% and is statistically significant. However, the MAX effect weakens substantially or even reverses for firms with high political sentiment. Our findings provide novel guidance for trading on the MAX effect. Moreover, the results challenge the usual sentiment-based explanation for the MAX effect. Further evidence suggests that the prospect theory or investors’ underreaction to news may be consistent with our findings, although these channels cannot empirically explain the impact of political sentiment.     

Risk,jumps, and diversification

We test for price discontinuities, or jumps, in a panel of high-frequency intraday stock returns and an equiweighted index constructed from the same stocks. Using a new test for common jumps that explicitly utilizes the cross-covariance structure in the returns to identify non-diversifiable jumps, we find strong evidence for many modest-sized, yet highly significant, cojumps that simply pass through standard jump detection statistics when applied on a stock-by-stock basis. Our results are further corroborated by a striking within-day pattern in the significant cojumps, with a sharp peak at the time of regularly scheduled macroeconomic news announcements.     

The impact of sentiment and attention measures on stock market volatility

We analyze the impact of sentiment and attention variables on the stock market volatility by using a novel and extensive dataset that combines social media, news articles, information consumption, and search engine data. We apply a state-of-the-art sentiment classification technique in order to investigate the question of whether sentiment and attention measures contain additional predictive power for realized volatility when controlling for a wide range of economic and financial predictors. Using a penalized regression framework, we identify the most relevant variables to be investors’ attention, as measured by the number of Google searches on financial keywords (e.g. “financial market” and “stock market”), and the daily volume of company-specific short messages posted on StockTwits. In addition, our study shows that attention and sentiment variables are able to improve volatility forecasts significantly, although the magnitudes of the improvements are relatively small from an economic point of view.     

Press freedom and jumps in stock prices

Press freedom varies substantially across countries. In a free environment, any news immediately becomes public knowledge through mediums including various electronic media and published materials. However, in an unfree environment, (economic) agents would have more discretionary powers to disclose good news immediately, while hiding bad news or releasing bad news slowly. We argue that this discretion affects stock prices and that stock markets in countries with a free press should be better processors of economic information. Using an equilibrium asset-pricing model in an economy under jump diffusion, we decompose the moments of the returns of international stock markets into a diffusive risk and a jump risk part. Using stock market data for a balanced panel of 50 countries, our results suggest that in countries with a free press, the better processing of bad news leads to more frequent negative jumps in stock prices. As a result, stock markets in those countries are characterized by higher volatility, driven by higher jump risk and more negative return asymmetry. The results are robust to the inclusion of various controls for governance and other country- or market-specific characteristics. We interpret these as good stock market characteristics because a free press improves welfare and increases economic growth.     

Crude oil price forecasting incorporating news text

Sparse and short news headlines can be arbitrary, noisy, and ambiguous, making it difficult for classic topic model LDA (latent Dirichlet allocation) designed for accommodating long text to discover knowledge from them. Nonetheless, some of the existing research about text-based crude oil forecasting employs LDA to explore topics from news headlines, resulting in a mismatch between the short text and the topic model and further affecting the forecasting performance. Exploiting advanced and appropriate methods to construct high-quality features from news headlines becomes crucial in crude oil forecasting. This paper introduces two novel indicators of topic and sentiment for the short and sparse text data to tackle this issue. Empirical experiments show that AdaBoost.RT with our proposed text indicators, with a more comprehensive view and characterization of the short and sparse text data, outperforms the other benchmarks. Another significant merit is that our method also yields good forecasting performance when applied to other futures commodities.     

Competing for the Public Through the News Media

Interest groups seek to influence economic activity through public and private politics. Public politics takes place in the arena of public institutions, whereas private politics takes place outside public institutions often in the arena of public sentiment. Private politics refers to action by interest groups directed at private parties, as in the case of an activist group launching a campaign against a firm. This paper presents a model of informational competition between an activist and an industry, where both interest groups seek to influence public sentiment and do so by advocating their positions through the news media. Citizen consumers make both a private consumption decision and a collective choice on the regulation of a product that has an externality associated with it. In the absence of the news organization, the collective choice is not to regulate. The activist and the industry obtain private, hard information on the seriousness of the externality and provide favorable information to the news media and may conceal unfavorable information. The news media can conduct investigative journalism to obtain its own information, and based on that information and the information it has received from its sources, provides a news report to the public. Because of its role in society, the media has an incentive to bias its report, and the direction of bias is toward regulation. Its bias serves to mitigate both market failure by decreasing demand and a government failure by shifting votes in favor of regulation. The activist then has incentive to conceal information unfavorable to its interests, whereas the industry fully reveals its information.     

Facts, Fiction, and the Fourth Estate

A bstract .   This paper examines the reaction of the market to news that the Washington Post had won a Pulitzer Prize for a story that was demonstrably false. The reaction to the stock price of the Post as well as the stock prices of other newspapers is examined using dummy variables for two days, four days, and six days. The results show that while the decline in the Post 's stock price was relatively small, the t-statistics for all of the dummy variables are significant. The paper also examines the McChesney (1987 ) hypothesis that the nature of the newspaper business is such that it is difficult for the residual claimants of the paper to receive the financial gains of important news stories. These rents, he points out, are distributed to others. We look to see whether or not residual claimants of that newspaper can be harmed if that newspaper publishes a false story and receives large amounts of bad publicity for its error.     

America's worst charities: The effect of bad press on philanthropic giving behavior

Negative media stories about nonprofits can potentially lead to decreased financial donations. We used agenda setting theory to study donors' perceptions of what could arguably be called one of the most negative nonprofit media stories in recent times: the 2013 Tampa Bay Times report titled “America's worst charities.” This news story identified and ranked America's 50 worst charities based on solicitation (i.e., fundraising) costs and was investigated further by CNN. We surveyed 655 individuals in August 2016 and found that approximately 3 years since the story had aired, 278 (42.4%) of the sample still remembered the news story, and the majority of them reported that it negatively influenced their thinking (63%) and philanthropic donation behavior (62%). These findings have implications for nonprofit media relations and fundraising.     

Infused with news value: Management,managerial knowledge and the institutionalization of business news

This article explores the development and institutionalization of business news, and its implications for management. Business news is often seen either as a sign of media commercialization or as a target for corporate communication strategies. In contrast to this, business news is explored in the present article as a particular type of knowledge that has emerged and become institutionalized in recent decades. The empirical analysis first describes the institutional development of business news in Denmark and then examines changes in business news texts from the 1960s to the present, not just as a particular type of business-oriented media content but ultimately as a form of managerial knowledge characterized by being simultaneously autonomous, negotiated and boundary-spanning.     

The state of #digitalentrepreneurship: a big data Leximancer analysis of social media activity

This paper examined online sentiment, key themes and patterns evident in social media activity about digital entrepreneurship. It provides a snapshot-in-time, visual-first perspective on social media user-generated-content (UGC) to better understand the topic of digital entrepreneurship. Global data consisting of 31,017 publicly available UGC which used the #digitalentrepreneurship (hashtag) and the keywords ‘digital entrepreneurship’ were collected. A computer assisted qualitative data analysis software (CAQDAS), Leximancer, was used for an automated text-mining analysis. There is positive online sentiment surrounding digital entrepreneurship technology, ecosystem and industry, and one which promotes women transformation of digital entrepreneurship globally. Negative sentiment pointed out that future development and support of youth in digital entrepreneurship is needed. Digital entrepreneurs were identified as needing to focus on strategy, leadership, management, and social media platforms. A comprehensive perspective on the state of digital entrepreneurship in online UGC is provided. Insights into the challenges, issues, changes, success stories and key topics in digital entrepreneurship are highlighted. Future research is encouraged to adopt longitudinal and quantitative approaches, to provide further insights into the evolution of digital entrepreneurship. The paper contributes to the entrepreneurship literature by applying the Social Exchange Theory and the Social Media User Engagement Framework to better understand social media activity around digital entrepreneurship. The findings show that there are real challenges and issues to overcome but there are also changes occurring in digital entrepreneurship and social media users are keen to share and learn from digital entrepreneurship success stories.

     

The sentiment pricing dynamics with short-term and long-term learning

Combining the behavioral characteristics of rational uninformed investors with learning information behavior of sentiment investors, this paper establishes a mathematical model about the impact of learning information behavior on the investor's transaction and asset equilibrium price under asymmetric information. Research shows that when rational uninformed investors learn information in the short term, on the one hand, they choose to bet against sentiment investors, thus reducing the influence of sentiment; on the other hand, they occasionally mistake sentiment for information to chase sentiment investors, then amplifying sentiment shocks. Furthermore, sentiment investors can also gain valuable information indirectly by observing the price in the long term. When sentiment investors learn information in the long term, the price fluctuations caused by sentiment and information, informativeness of the price system and market efficiency are no longer dependent on the quality of information.     

SIGN- AND VOLATILITY-SWITCHING ARCH MODELS: THEORY AND APPLICATIONS TO INTERNATIONAL STOCK MARKETS

This paper develops two conditionally heteroscedastic models which allow an asymmetric reaction of the conditional volatility to the arrival of news. Such a reaction is induced by both the sign of past shocks and the size of past unexpected volatility. The proposed models are shown to converge in distribution to absolutely continuous Itô diffusion processes, as happens for other heteroscedastic formulations. One of the schemes developed in the paper—the Volatility-switching ARCH—differs from the existing asymmetric models insofar as it is able to capture a particular aspect of the behaviour of the volatilities, i.e. the reversion of their asymmetric reaction to news. Empirical evidence from stock market returns in six countries shows that such a model outperforms traditional asymmetric ARCH equations. © 1997 by John Wiley & Sons, Ltd.     

创业板投资者情绪及其收益率相关性研究

本文采用向量自回归模型VAR方法分别研究了我国主板市场与创业板市场投资者情绪与收益率之间影响是系。研究发现我国主板市场中投资者情绪对收益率有显著影响,而收益率对投资者情绪无显著影响;而创业板市场表现不同,投资者情绪对收益率无显著相关影响。研究表明:出现上述现象的原因是由于两市场的投资者结构存在差异,创业板市场投资者更成熟、创业板政策及监管更为全面等原因。