Skip to main navigation Skip to search Skip to main content

Time Series of Media Implied Economic Sentiments (Linear Support Vector Machine)

    Dataset

    Description

    This dataset consists of economic implied sentiments based on filtering of articles based on economic policy keywords. The process of filtering is described in :

    Rambaccussing, D., & Kwiatkowski, A. (2020). Forecasting with news sentiment: Evidence with UK newspapers. International Journal of Forecasting, 36(4), 1501-1516.

    Bowden, J., Kwiatkowski, A., & Rambaccussing, D. (2019). Economy through a lens: distortions of policy coverage in UK national newspapers. Journal of Comparative Economics, 47(4), 881-906.

    The construction of the sentiment scores uses supervised machine learning where the training, testing and validation is performed using Linear Supportn Vector systems.
    Date made available2 Dec 2022
    PublisherUniversity of Dundee
    Temporal coverageFeb 1990 - Dec 2018
    Geographical coverageUnited Kingdom

    UN SDGs

    This dataset contributes to the following UN Sustainable Development Goals (SDGs)

    1. SDG 1 - No Poverty
      SDG 1 No Poverty
    2. SDG 3 - Good Health and Well-being
      SDG 3 Good Health and Well-being
    3. SDG 9 - Industry, Innovation, and Infrastructure
      SDG 9 Industry, Innovation, and Infrastructure
    4. SDG 12 - Responsible Consumption and Production
      SDG 12 Responsible Consumption and Production
    5. SDG 16 - Peace, Justice and Strong Institutions
      SDG 16 Peace, Justice and Strong Institutions

    Contact

    Access Dataset

    • ReadMe.txt

      File: text/plain, 195 bytes

      Type: Text

      Licence: CC0

    • svm.RData

      File: application/octet-stream, 24.2 KB

      Type: Dataset

      Licence: CC BY

    • svm.dta

      File: application/octet-stream, 50.2 KB

      Type: Dataset

      Licence: CC BY

    • svm.xlsx

      File: application/vnd.openxmlformats-officedocument.spreadsheetml.sheet, 53.9 KB

      Type: Dataset

      Licence: CC BY

    Cite this