Measuring news media sentiment using big data for Chinese stock markets

Shen, Shulin; Xia, Le; Shuai, Yulin; Gao, Dawen

doi:10.1016/j.pacfin.2022.101810

Cited by 23 publications

(15 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Secondly, we add to the literature by examining the role of news media sentiment in a European and less developed market—the Portuguese stock market. As noted by Shen et al (2022), previous research on investor sentiment and, especially, on news media sentiment focus mainly on the United States and, more recently, on China. Finally, given the lack of an adequate index to capture the effects of ESG media on the Portuguese stock market, we develop a NSI that classifies the media reports into three sentiment groups, capturing positive, negative, and neutral ESG news on companies listed in the PSI‐20.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

The impact of ESG news on the volatility of the Portuguese stock market—Does it change during recessions?

Zanatto,

Catalão‐Lopes,

Pina

et al. 2023

Bus Strat Env

View full text Add to dashboard Cite

This paper assesses how environmental, social, and governance (ESG) news influence Portuguese stock market volatility depending on the business cycle. Given the lack of an adequate index to capture the effects of ESG media on the Portuguese stock market, a News Sentiment Index is developed. This index, which captures positive and negative ESG news on companies listed in the Portuguese Stock Index (PSI‐20), is then used as an external regressor in symmetric and asymmetric GARCH‐type models employed to model the stock market volatility. Results show that during non‐crisis periods ESG news reduce returns' volatility, and that when considering the period preceding the financial crisis the disclosure content (positive or negative) of the news matter. However, during economic downturns, neither the amount nor the content disclosure of ESG news affect volatility; thus, ESG preoccupations might no longer be paramount.

show abstract

Section: Introductionmentioning

confidence: 99%

“…Secondly, we add to the literature by examining the role of news media sentiment in a European and less developed market-the Portuguese stock market. As noted by Shen et al (2022), previous research on investor sentiment and, especially, on news media sentiment focus mainly on the United States and, more recently, on China.…”

mentioning

confidence: 99%

The impact of ESG news on the volatility of the Portuguese stock market—Does it change during recessions?

Zanatto,

Catalão‐Lopes,

Pina

et al. 2023

Bus Strat Env

View full text Add to dashboard Cite

show abstract

“…A hierarchical news propagation network is also used for news data propagation. Multilevel operations and functions are used here that detect the quality and content of the news before the propagation process [6].…”

Section: Introductionmentioning

confidence: 99%

Research on Data News Propagation Path Based on the Big Data Algorithm

Hao

Liu

Wang

2022

International Transactions on Electrical Energy Systems

View full text Add to dashboard Cite

News propagation originates from a person/location, dwelling with an event that grabs significance. News data propagation relies on telecommunication and big data for precise content distribution and mitigation of false news. Considering these factors, the event-dependent data propagation technique (EDPT) was introduced to improve the data precision. These data refer to the news information originating and propagating from digital media. The data analysis considers the external factors for fake information and precise projection medium for preventing multiviewed false circulations. In this technique, the liability of the information is analyzed using a linear pattern support vector classifier. The data modification and propagation changes are classified based on liability information across the circulation time. The SVM classifier identifies these two factors with close liability validation, preventing false data. The data accumulation and analysis rates for the abovementioned classifications are performed in the propagation process using the classifier hyperplane. This plane is updated from the previous propagation point from which the events are identified. The proposed technique’s performance is analyzed using propagation accuracy, precision, false rate, time, and rate.

show abstract

“…The machine learning approach has seen an increased interest in the recent literature [38], especially with the advent of large transfer learning models, such as BERT and its variants [33]. Two of the most popular topics where sentiment analysis, polarity analysis and stance detection have been widely studied in the literature are COVID-19-related social phenomena, such as the role of China [39], vaccinations [2], [7], [40], [41], and lockdowns [42], and finance-related research, either related to the stock market [42], [43] or cryptocurrencies [44], [45].…”

Section: B Stance Detectionmentioning

confidence: 99%

1000 Days of COVID-19: A Gender-Based Long-Term Investigation into Attitudes With Regards to Vaccination

et al. 2023

View full text Add to dashboard Cite

The coronavirus pandemic has undoubtedly been one of the major recent events that have affected our society at the global level. During this period, unprecedented measures have been imposed worldwide by authorities in an effort to contain the spread of the disease. These measures have led to a worldwide debate among the public, occurring not least within the forum of social media, tapping into preexisting trends of skepticism, such as vaccine hesitancy. At the same time, it has become apparent that the pandemic affected women and men differently. With these two themes in view, the paper aims to analyze using a data-driven approach the evolution of opinions with regards to vaccination against COVID-19 throughout the entire duration of the pandemic from the point of view of gender. For this analysis, approximately 1,500,000 short user-contributed texts have been retrieved from the popular microblogging platform Twitter, posted between 30 January 2020 and 30 November 2022. Using a machine learning approach, several classifiers have been trained to identify the likely gender (female or male) of the author, as well as the stance of the specific post towards the COVID-19 vaccines (neutral, in favor, or against), achieving 85.69% and 93.64% weighted accuracy measures for each problem, respectively. Based on this analysis, it can be observed that most tweets exhibit a neutral stance, while the number of tweets in favor of vaccination is greater than the number of tweets opposing vaccination, with the distribution varying across time in response to specific events. The subject matter of the tweets varied more between stances than between genders, suggesting that there is no significant difference between the contents of tweets posted by females and males. We also find that while the overall engagement on Twitter with the topic of vaccination against COVID-19 is on the wane, there has been a rise in the number of against tweets continuing into the present.

show abstract

Measuring news media sentiment using big data for Chinese stock markets

Cited by 23 publications

References 38 publications

The impact of ESG news on the volatility of the Portuguese stock market—Does it change during recessions?

The impact of ESG news on the volatility of the Portuguese stock market—Does it change during recessions?

Research on Data News Propagation Path Based on the Big Data Algorithm

1000 Days of COVID-19: A Gender-Based Long-Term Investigation into Attitudes With Regards to Vaccination

Contact Info

Product

Resources

About