Data & Analysis Compendium for the Epistemic Overconfidence in Algorithmic News Selection Paper Pre-registered at https://osf.io/u462t/, pdf file of the Pre-Analysis Plan, i.e. PAP, here, ethical approval here.
The following data files might be of interest:
- Cleaned data Cleaned data with constructed scales for analysis of the US MTurk sample and the Dutch Pollfish sample. We use this data to test whether people have more algorithmic appreciation when consuming news to pass time, entertain oneself or escape from daily worries than when using news to keep up-to-date with politics (hypotheses 1) and. whether people are confident in their own cognitive abilities moderates that relationship (hypothesis 2). In addition, we use the data to conduct exploratory analyses as reported in the paper.
See the script in src/data-processing/Prep_data for details on how these files were constructed.
-
Conducted analyses Demonstrates the analyses to test and visualise hypothesis 1 and hypothesis 2. In addition, we report the exploratory results for:
- the role of gender in hypothesis 2;
- the relationship between Appreciation for News Selector and Trust in Media;
- the relationship between Appreciation for Journalists as News Selectors and Overconfidence
- the relationship between Appreciation for Self Selecting the News and Overconfidence