Economic News Research Articles

Portrayals of Chinese companies in American and British economic news tweets during China’s macroeconomic transitions 2007–2023

This study investigates how Chinese companies are portrayed in American and British economic news tweets, as well as their relationship to Chinese economic fluctuations. The analysis included a corpus of 55,394 tweets (934,155 words) from well-known media outlets between 2007 and 2023. It also incorporated China’s quarterly Gross Domestic Product (GDP) and monthly Purchasing Managers’ Index (PMI) to contextualise the tweets in terms of their actual economic performance. Using van Dijk’s ingroup and outgroup ideologies, this project examined the ideological depiction through sentiments and emotions. RoBERTa-based transformer models were used to analyse sentiments and emotions, whereas Large Language Models (LLMs) were used for evaluative target annotation. Positive and negative sentiments were found to be significantly (p < 0.01) correlated with China’s macroeconomic indices. The representation of Chinese companies trended between ingroup and outgroup portrayals. Positive sentiment diminished as the economy transitioned from expansion to contraction, while negative sentiment increased. American news tweets were most positive during economic balance and most negative during downturns, while British news tweets were most positive during stability or early recovery and most negative when a downturn was predicted. As the economy shifted from growth to decline, positive sentiment emphasised corporate external opportunities alongside corporate strengths, with both evaluative targets reinforcing ingroup representation. Negative sentiment shifted from corporate weaknesses to contextual threats, both strengthening outgroup representation. Moreover, certain emotions had a significant (p < 0.0001) influence on sentiment swings and ideological transitions. These findings emphasise how economic changes and journalistic factors influence the ideological representation of Chinese firms in economic news on social media.

News Sentiment and Liquidity Risk Forecasting: Insights from Iranian Banks

This study addresses the critical challenge of predicting liquidity risk in the banking sector, as emphasized by the Basel Committee on Banking Supervision. Liquidity risk serves as a key metric for evaluating a bank’s short-term resilience to liquidity shocks. Despite limited prior research, particularly in anticipating upcoming positions of bank liquidity risk, especially in Iranian banks with high liquidity risk, this study aimed to develop an AI-based model to predict the liquidity coverage ratio (LCR) under Basel III reforms, focusing on its direction (up, down, stable) rather than on exact values, thus distinguishing itself from previous studies. The research objectively explores the influence of external signals, particularly news sentiment, on liquidity prediction, through novel data augmentation, supported by empirical research, as qualitative factors to build a model predicting LCR positions using AI techniques such as deep and convolutional neural networks. Focused on a semi-private Islamic bank in Iran incorporating 4,288,829 Persian economic news articles from 2004 to 2020, this study compared various AI algorithms. It revealed that real-time news content offers valuable insights into impending changes in LCR, particularly in Islamic banks with elevated liquidity risks, achieving a predictive accuracy of 88.6%. This discovery underscores the importance of complementing traditional qualitative metrics with contemporary news sentiments as a signal, particularly when traditional measures require time-consuming data preparation, offering a promising avenue for risk managers seeking more robust liquidity risk forecasts.

Global Economic Policy Uncertainty and Global Economic Leaders’ Influence on Regional Economic Growth

This study aims to evaluate the regional economic growth of select American, European, and Asian countries amidst global economic uncertainty. The proposed methodology incorporates mixed frequencies in the data (VAR-MIDAS), facilitating the assessment of their reliance on lagged values, the impact of economic growth in other countries within the same region, and the influence of Global Economic Policy Uncertainty (GEPU). This sheds light on the effects of economic news from relevant newspapers on GDP growth. The primary hypothesis suggests a significant influence of other countries within the same region and the two major global economic powers on the Gross Domestic Product (GDP) growth of each studied region, namely the United States and China. This research also examines this hypothesis across 19 GEPU-included economies, categorizing them regionally by continent. The econometric results confirm the influence of the two leading economies on economic growth and identify causal relationships, with GEPU also exhibiting effects on GDP. Additionally, in-sample estimations reveal disparities in the influence of leaders on the economic growth of the examined economies.

Markaðsvæðing frétta: Greining á innihaldi frétta í tveimur dagblöðum og tveimur vefmiðlum fyrir og eftir hrun

Miklar breytingar hafa orðið í fjölmiðlun undanfarna áratugi. Breytingarnar eiga sér pólitískar, efnahagslegar og ekki síst tæknilegar rætur og hafa m.a lýst sér í samþjöppun eignarhalds, aukinni markaðsvæðingu og harðnandi samkeppni. Erlendar rannsóknir benda margar til þess að þessi þróun hafi haft veruleg áhrif á blaða- og fréttamennsku og fjölmiðlar leggi aukna áherslu á fréttir af glæpum, íþróttum og frægu fólki, en minni á fréttir af stjórnmálum, efnahagsmálum eða alþjóðamálum. Ýmsir fræðimenn hafa einnig haldið því fram að þessa sjái stað í netmiðlum í ríkari mæli en hefðbundnum miðlum á borð við dagblöð, þar sem eiginleikar netsins og stafrænnar miðlunar ýti undir slíkt. Ísland hefur ekki farið varhluta af þessum breytingum, en lítið er vitað um áhrif þeirra á efnið sem fjölmiðlar framleiða. Í þessari grein er gerð grein fyrir niðurstöðum rannsóknar á innihaldi frétta í stærstu dagblöðum og veffréttamiðlum hér á landi árin 2005 og 2013, eða fyrir og eftir efnahagshrunið 2008. Þær benda til þess að umfang frétta af pólitík og efnahagsmálum sé hlutfallslega minna nú en var fyrir hrun, en svokallaðar mjúkar fréttir, af íþróttum, afþreyingu og frægu fólki séu að sama skapi hlutfallslega fleiri. Það á einkum við um vefmiðlana en síður um dagblöðin.

Indonesian GDP movement detection using online news classification

Gross Domestic Product (GDP) stands as a pivotal indicator, offering strategic insights into economic dynamics. Recent technological advancements, particularly in real-time information dissemination through online economic news platforms, provide an accessible and alternative data source for analyzing GDP movements. This study employs online news classification to identify patterns in the movement and growth rate of Indonesia’s GDP. Utilizing a web scraping technique, we collected data for analysis. The classification models employed include transfer learning from pre-trained language model transformers, with classical machine learning methods serving as baseline models. The results indicate superior performance by the pre-trained language model transformers, achieving the highest accuracy of 0.8880 and 0.7899. In comparison, hyperparameter-tuned classical machine learning models also demonstrated commendable results, with the best accuracy reaching 0.845 and 0.7811. This research underscores the efficacy of leveraging online news classification, particularly through advanced language models. The findings contribute to a nuanced understanding of economic dynamics, aligning with the contemporary landscape of information accessibility and technological progress.

LEST: Large language models and spatio-temporal data analysis for enhanced Sino-US exchange rate forecasting

Exchange rate forecasting has a significant impact on a country’s balance of international payments, financial security and stability. Under the context of Sino-US trade war, a series of news events have happened thus increasing the abnormal fluctuations in the RMB exchange rate, and these fluctuations have made it more difficult to forecast the exchange rate. The analysis of news events’ impact on exchange rate fluctuations focused on assigning emotional labels to different economic news and political events by building an emotional lexicon. However, the previous method of using an offline emotional lexicon to analyze events could not be updated promptly making it difficult to better exploit implicit information of news events. Also, the offline emotional lexicon requires manual annotation of events which is unavoidable and subjective and therefore influences the sentiment analysis of the event. Therefore, we build a fusion forecasting framework of spatio-temporal and emotional information for accurate, real-time exchange rate forecasting. First, in the preprocessing phase, we leveraged the situational learning capabilities of Large Language Models (LLMs), specifically ChatGPT, combined with prompt engineering to enable ChatGPT to provide real-time, online, and precise automated sentiment analyses of Sino-US trade events. Second, we proposed the SG-TL fusion model, which integrates Spatio-Temporal Graph Convolutional Networks (STGCN) and Gated Recurrent Unit (GRU) models in the feature processing approach to accurately extract exchange rate features in spatial and temporal dimensions. We also employed Transformer and Long Short-Term Memory (LSTM) models in the forecasting phase to forecast the Sino-US exchange rates. Finally, Experiment results demonstrate that the exchange rate forecasting framework LEST can accurately capture the exchange rate fluctuations during the period of Sino-US trade war. Furthermore, its forecasting performance is more precise, efficient, and stable than existing works. The source code of our developed method is publicly available at https://gitee.com/andyham_andy.ham/lest-forecasting-framework.

The exposure level media teachers for the news (eight o'clock PM) of Kurdish television channels

The aim of this research is to understand the idea and direction of the media instructors for the news at 8:00PM in the Kurdish Satellite Channels. The majority of the viewers of the satellite channels pay more attention to the news at 8:00 PM, as the habit of the international channels. The Kurdish satellite channels solicitude to the news of 8:00 PM. The Kurdish channels are preparing special news covering and the companies that are working in the economic fields are emphasizing on showing their advertisements at 8:00 PM news as it is considered as Golden Time by some of the Media Analysts. This research is considered as descriptive research and depends on media theory (Media Tools) and relies on questionnaire forms as a used tool in the research. In the end, the researchers concluded some outcomes such as; decrease the percentage of the News and TV viewers in general as there are alternatives for the Satellite channels. There are some kinds of debate during watching the news at 8:00 PM among family members and, friends and on the other side with the sample of the research, the mass majority of this research samples come first to follow the Political news, then Miscellaneous news, Economy news and then the social news. Most of the research samples show that the Kurdish channels are not alternative for the other news resources

A new perspective on how investor sentiment affects herding behavior in the cryptocurrency market

This study examines how news sentiment impacts herding (anti-herding) behavior in the cryptocurrency market. We categorize the cryptos into “clean” and “dirty” based on their energy consumption. The results show that news sentiment has divergent effects. When economic news positively overwhelms investors, herding becomes more apparent among the "clean" cryptocurrencies while the "dirty" exhibits more pronounced anti-herding. In clean cryptocurrencies, as the market is downward (upward), herding (anti-herding) is more evident if the investors are more optimistic about economic news. The findings are crucial for regulators and other participants to better manage investments in the bitcoin market.

Natural language processing and financial markets: semi-supervised modelling of coronavirus and economic news

AbstractThis paper investigates the reactions of US financial markets to press news from January 2019 to 1 May 2020. To this end, we deduce the content and uncertainty of the news by developing apposite indices from the headlines and snippets of The New York Times, using unsupervised machine learning techniques. In particular, we use Latent Dirichlet Allocation to infer the content (topics) of the articles, and Word Embedding (implemented with the Skip-gram model) and K-Means to measure their uncertainty. In this way, we arrive at the definition of a set of daily topic-specific uncertainty indices. These indices are then used to find explanations for the behavior of the US financial markets by implementing a batch of EGARCH models. In substance, we find that two topic-specific uncertainty indices, one related to COVID-19 news and the other to trade war news, explain the bulk of the movements in the financial markets from the beginning of 2019 to end-April 2020. Moreover, we find that the topic-specific uncertainty index related to the economy and the Federal Reserve is positively related to the financial markets, meaning that our index is able to capture the actions of the Federal Reserve during periods of uncertainty.

News and Asset Pricing: A High-Frequency Anatomy of the SDF

Abstract Utilizing real-time newswire data, together with a robustly estimated intraday stochastic discount factor (SDF), we identify and quantify the economic news that is priced. News related to monetary policy and finance on average accounts for most of the variation in the SDF, followed by news about international affairs and macroeconomic data. We also document nontrivial temporal variation in the relative importance of the news, along with marked differences in the estimated news risk premiums in the “factor zoo.” To further highlight the economic mechanisms at work, we associate the different news effects with interest rate, growth, and risk premium shocks. (JEL C58, G12, G14)

Application of machine learning optimization in cloud computing resource scheduling and management

In recent years, cloud computing has been widely used. Cloud computing refers to the centralized computing resources, users through the access to the centralized resources to complete the calculation, the cloud computing center will return the results of the program processing to the user. Cloud computing is not only for individual users, but also for enterprise users. By purchasing a cloud server, users do not have to buy a large number of computers, saving computing costs. According to a report by China Economic News Network, the scale of cloud computing in China has reached 209.1 billion yuan.Rational allocation of resources plays a crucial role in cloud computing. In the resource allocation of cloud computing, the cloud computing center has limited cloud resources, and users arrive in sequence. Each user requests the cloud computing center to use a certain number of cloud resources at a specific time.

Trading Activity in the Corporate Bond Market: A SAD Tale of Macro-Announcements and Behavioral Seasonality?

This study investigates the determinants of trading activity in the U.S. corporate bond market, focusing on the effects of Seasonal Affective Disorder (SAD) and macroeconomic announcements. Employing the General-to-Specific (Gets) Autometrics methodology, we identify distinct behavioral responses between retail and institutional investors to SAD, noting a significant impact on retail trading volumes but not on institutional trading or bond returns. This discovery extends the understanding of behavioral finance within the context of bond markets, diverging from established findings in equity and Treasury markets. Additionally, our analysis delineates the influence of macroeconomic announcements on trading activities, offering new insights into the market’s reaction to economic news. This study’s findings contribute to the broader literature on market microstructure and behavioral finance, providing empirical evidence on the interplay between psychological factors and macroeconomic information flow within corporate bond markets. By addressing these specific aspects with rigorous econometric techniques, our research enhances the comprehension of trading dynamics in less transparent markets, offering valuable perspectives for academics, investors, risk managers, and policymakers.

Unpacking the Nuances of Agenda-Setting in the Online Media Environment: An Hourly-Event Approach in the Context of Chinese Economic News

ABSTRACT The study of agenda-setting has faced considerable challenges in the digital age. Not only are the existing conceptualizations inadequate regarding the new features of online media outlets, but traditional analysis has also become insufficient to address the nuances of agenda-setting in the dynamic online media environment. In this study, we refined assumptions of reverse and intermedia agenda-setting theory, introduced the news events and hourly intervals approach, and considered economic news events in China as an appropriate theme. Our analysis showed that the few popular media played a gatekeeping role in the Chinese online media environment, and the average time interval in which agendas transferred across media and netizens was about 4 h. This study, thereby, advanced the understanding of agenda-setting dynamics in the digital society and showed directions for future agenda-setting research in terms of establishing more up-to-date conceptual assumptions and employing more nuanced methodological approaches.

Exploring the Impact of Media Content on Social Media Engagement Through Comment Analysis

This study investigates audience participation on the social media platforms of Kantipur Daily, Sagarmatha Radio, and Nepal Television using survey data collected in 2024. A review of comments on Facebook and X(Twitter) indicated that positive feedback is primarily focused on sports and social/health/lifestyle news Moreover, opinions and economic news receive relatively less attention than political news. The study highlights particular areas that need more research and offers insightful information about audience dynamics in the context of digital communication. This finding emphasizes the value of social media as a political communication tool, which is especially clear from the positive comments on Political News. Additionally, despite certain restrictions, the results show how the communication landscape is changing and how social media is improving news accessibility and content quality. The finding indicates that social media has become a new arena for public affairs, and its results show that Facebook is more widely used than X.

The S&amp;P 500 sectoral indices responses to economic news sentiment

AbstractThis study explores the dynamic relationship between economic news sentiment and the US stock market using a non‐linear empirical framework. The analysis focuses on both sectoral indices and the aggregate stock market index from November 2011 to November 2021. Using causality tests and a rolling window detrended cross‐correlation coefficient, the study reveals several key findings. First, the causal effect of investor sentiment on sectoral returns varies over time, with each sector responding differently. Second, while no evidence of dependence exists for time scales less than 2 months, a positive relationship emerges for time scales greater than 6 months, except for the utilities sector, which is found to be negative. Third, the study shows that the relationships between all pairs of variables are time‐dependent. Finally, economic news sentiment might have a varying impact on market inefficiency over different periods, making it challenging to predict market behaviour based on sentiment data.

Prediction of Economic Growth by Using Machine-Learning Algorithms through Sentiment Index Analysis in Economy of Pakistan

The neural network method's ability to mimic nonlinear communications without prior information is a major benefit for accurate function approximation. It differs from ARIMA and linear regression, which need linearity and may not work for all data sorts. Compared to (seasonal) ARIMA models, neural networks yield similar results. Neural networks also model and predict multivariate time series using causal and co-integration research. In contrast to the traditional economic forecasting approach, machine-learning techniques have prioritized precise forecasting without predetermined assumptions or conclusions. Owing to their enhanced predictive abilities and technological advancements, they provide more adaptability and have gained widespread acceptance in several fields. In terms of estimating US real estate values, machine-learning technology fared better than traditional econometric models, as shown. Total there were 131601 economic and financial news, which may include the phrases along with the names specified by the bank, and it may also include local media and mainstream. Machine learning uses the strength of data-driven algorithms and state-of-the-art computational techniques to improve decision-making in a range of industries. The findings of this research contribute to better forecasting practices and show how machine learning may provide more accurate forecasts in real-world scenarios.

Forecasting the Future Value of a Colombian Investment Fund with LSTM Recurrent Neural Networks (LSTM)

Forecasting the Future Value of a Colombian Investment Fund with LSTM Recurrent Neural Networks (LSTM)

MDGNN: Multi-Relational Dynamic Graph Neural Network for Comprehensive and Dynamic Stock Investment Prediction

The stock market is a crucial component of the financial system, but predicting the movement of stock prices is challenging due to the dynamic and intricate relations arising from various aspects such as economic indicators, financial reports, global news, and investor sentiment. Traditional sequential methods and graph-based models have been applied in stock movement prediction, but they have limitations in capturing the multifaceted and temporal influences in stock price movements. To address these challenges, the Multi-relational Dynamic Graph Neural Network (MDGNN) framework is proposed, which utilizes a discrete dynamic graph to comprehensively capture multifaceted relations among stocks and their evolution over time. The representation generated from the graph offers a complete perspective on the interrelationships among stocks and associated entities. Additionally, the power of the Transformer structure is leveraged to encode the temporal evolution of multiplex relations, providing a dynamic and effective approach to predicting stock investment. Further, our proposed MDGNN framework achieves the best performance in public datasets compared with the state-of-the-art stock investment methods.

The impact of monetary policy shocks — Do not rule out central bank information effects or economic news

This paper reassesses the impact of monetary policy and central bank information shocks while accounting for the influence of economic news. We regress a set of monetary policy surprises on a measure of economic news and incorporate these new instruments into an SVAR model. Furthermore, we distinguish between the two shocks via sign restrictions on the instruments’ impulse response functions. Our findings indicate significantly stronger and more enduring economic effects for monetary policy shocks, while the economic effects of central bank information shocks are weaker, if not vanish entirely. Nevertheless, persistent financial effects prevent us from completely dismissing the existence of central bank information effects. Consequently, it is important to account for both the effects of central bank information shocks and economic news in monetary policy settings.

Attitudes Formation toward Minority Outgroups in Times of Global Crisis-The Role of Good and Bad Digital News Consumption.

This paper examines the relationships between the consumption of 'bad' or 'good' digital economic news and attitudes toward immigrant and ethnic minorities during the crisis that developed during the COVID-19 pandemic. The study considered attitudes toward two minority groups in Israel: immigrant citizens from English-speaking countries, and Israeli Palestinian citizens, an ethnic minority. The data were collected through an online survey of 866 respondents, who were members of the majority population group. The study found that, during the global crisis, exposure to bad digital news was associated with more positive attitudes toward both disadvantaged and non-disadvantaged minority groups. Moreover, in times of global crisis, people focused mostly on local rather than global digital news. In contrast to the idea of Intergroup Threat Theory, the study revealed that feelings of economic threat during the global crisis engendered higher cohesion between different population groups, and more positive attitudes toward minorities. In times of crisis, bad news for the economy brings good news for social solidarity-people tend to rally around the flag; this phenomenon even occurs between groups engaged in years-long, protracted conflict.