1. Filename: Unique identifier of this advertisement
2. URLs TheEconomistPageScans: comma separated list of URLs to JPG image files of scanned The Economist pages containing this ad. For multi page ads this can be multiple URLs.
3. Date of Issue: Date of The Economist issue (Years-Month-Day)
4. Ad size (pages): e.g. 1 = one full page, 0.75 = 3/4 of a page, 2 = two pages
5. Ad size < 1/4: 1 if Ad covers less than 25% of the page; 0 if Ad does not cover less than 25% of the page
6. 1/4 <= Ad size < 2/4: 1 if Ad covers at least 25% of the page, but less than 50%; 0 if Ad size is not in this range
7. 2/4 <= Ad size < 3/4
8. 3/4 <= Ad size < 4/4
9. 4/4 <= Ad size < 8/4
10. 8/4 <= Ad size
11. Bounding Box relative X1: Left-top coordinate of a rectangle identifying the ad on the page, relative to the pixel coordinates of the image from column 2 (“URLs …”). Multiply this value by the width of the image to get the absolute x coordinate. If the ad is a multi page ad, the images from column 2 have to be horizontally concatenated first.
12. Bounding Box relative Y1: Left-top coordinate
13. Bounding Box relative X2: Right-bottom coordinate
14. Bounding Box relative Y2: Right-bottom coordinate
15. Feature Complexity (JPG file size in kb / Ad Size): More complex images will have higher values.
16. JPG File Size (Byte): e.g. 186609
17. OCR GoogleVision: Advertisement text, based on text recognition using Google Vision API (2021) of the full ad image.
18. Brand: Brand name of advertiser
19. Brand is generic (e.g. ‘Notices’): If “True” then this ad doesn’t represent a single brand, but a category of ad-like content. Most common categories are “Notices”, “Appointments”, “Courses”.
20. Text Class GoogleVision: Based on the OCR text the ad was classified using GoogleVision API (2021). See full list of categories. This column contains a JSON string with a list of text classes and their class probabilities.
21. Category most confident, Level 1: Top level category from Google Vision text analysis for this ad. E.g. “/Finance“
22. Category most confident, Level 2: e.g. “/Finance/Banking”
23. Category most confident, Level 3
24. Colorfulness (Hasler & Suesstrunk, 2003): Colorfulness of ad, based on this paper.
25. Color variety (Ke et al., 2006): Color variety of ad, based on this paper.
26. Brightness_Mean: Mean of brightness values of all pixels in ad.
27. Brightness_SD: Standard deviation of brightness values of all pixels.
28. Red_Mean: Mean value of redness of all pixels.
29. Red_SD
30. Green_Mean
31. Green_SD
32. Blue_Mean
33. Blue_SD
34. Text readability Gunning Fog: Text readability measure according to Gunning Fog index.
35. Text readability SMOG
36. Text readability Flesch Reading Ease
37. Text readability Dale Chall

Authors

Kluge, S., Gehrmann, L., Stahl, F., Knäble, M., Nadj, M., Maedche, A.

Funding / Grants

DFG

License

Creative Commons Attribution 4.0 International

DOI

https://doi.org/10.7801/382