Scholarlink

<p>Global crises, such as wars or the COVID-19 pandemic, underscore the need for real-time economic monitoring. Traditional economic indicators often fall short, prompting the exploration of alternative data sources, including online and social media content. This study examines the relationship between media sentiment in press articles and traditional economic indicators: the Purchasing Managers' Index (PMI), Consumer Confidence Index (CCI), and average employment in the enterprise sector. We evaluate four pre-trained natural language processing models for sentiment analysis to assess their applicability. The analysis also explores the impact of time shifts in media reporting on the correlation between sentiment scores and economic indicators. Results reveal that a + 24-day shift in article dates produces the strongest correlation with PMI, suggesting media sentiment can predict changes in PMI with a lead time of about 3.5 weeks. Further analysis shows a positive correlation between sentiment scores and the CCI with a + 6-day shift, indicating media sentiment may signal changes in consumer confidence approximately one week in advance. Additionally, a + 70-day shift reveals that media sentiment can predict changes in average employment in the enterprise sector up to 10 weeks before they are officially recorded. These findings highlight the potential of media sentiment as an early indicator of economic trends, emphasizing the importance of considering time dynamics in such analyses. The study demonstrates that sentiment analysis offers valuable insights into economic trends through media reporting, potentially aiding in more timely economic forecasting and decision-making.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Integrating media sentiment with traditional economic indicators: a study on PMI, CCI, and employment during COVID-19 period in Poland

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年2月24日

查看全文
  • Iwona Kaczmarek,
  • Adam Iwaniak,
  • Grzegorz Chrobak,
  • Jan K. Kazak

摘要

Global crises, such as wars or the COVID-19 pandemic, underscore the need for real-time economic monitoring. Traditional economic indicators often fall short, prompting the exploration of alternative data sources, including online and social media content. This study examines the relationship between media sentiment in press articles and traditional economic indicators: the Purchasing Managers' Index (PMI), Consumer Confidence Index (CCI), and average employment in the enterprise sector. We evaluate four pre-trained natural language processing models for sentiment analysis to assess their applicability. The analysis also explores the impact of time shifts in media reporting on the correlation between sentiment scores and economic indicators. Results reveal that a + 24-day shift in article dates produces the strongest correlation with PMI, suggesting media sentiment can predict changes in PMI with a lead time of about 3.5 weeks. Further analysis shows a positive correlation between sentiment scores and the CCI with a + 6-day shift, indicating media sentiment may signal changes in consumer confidence approximately one week in advance. Additionally, a + 70-day shift reveals that media sentiment can predict changes in average employment in the enterprise sector up to 10 weeks before they are officially recorded. These findings highlight the potential of media sentiment as an early indicator of economic trends, emphasizing the importance of considering time dynamics in such analyses. The study demonstrates that sentiment analysis offers valuable insights into economic trends through media reporting, potentially aiding in more timely economic forecasting and decision-making.