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

Iwona Kaczmarek, Adam Iwaniak, Grzegorz Chrobak and Jan K. Kazak ()
Additional contact information
Iwona Kaczmarek: Wrocław University of Environmental and Life Sciences
Adam Iwaniak: Wrocław University of Environmental and Life Sciences
Grzegorz Chrobak: Wrocław University of Environmental and Life Sciences
Jan K. Kazak: Wrocław University of Environmental and Life Sciences

Journal of Computational Social Science, 2025, vol. 8, issue 2, No 14, 23 pages

Abstract: Abstract 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.

Keywords: Sentiment analysis; Text processing; Economic forecasting; Purchasing managers' index; Consumer confidence index (search for similar items in EconPapers)
Date: 2025
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
http://link.springer.com/10.1007/s42001-025-00375-x Abstract (text/html)
Access to the full text of the articles in this series is restricted.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:jcsosc:v:8:y:2025:i:2:d:10.1007_s42001-025-00375-x

Ordering information: This journal article can be ordered from
http://www.springer. ... iences/journal/42001

DOI: 10.1007/s42001-025-00375-x

Access Statistics for this article

Journal of Computational Social Science is currently edited by Takashi Kamihigashi

More articles in Journal of Computational Social Science from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().