As we continue to analyze the Fake News dataset, another field is “Author”. Below is a subset copied from the Author field after removing duplicates. Removing duplicates resulted in over 4,000 unique Author entries, however the misaligned rows issue continues to be a factor. I estimate between 25-40% of the 4,000 unique rows are actual names like below, as opposed to long strings of text.
This subset was chosen for a reason because a particular name jumped out. HINT: he has run for President under the Green political party ticket.
Suffice to say, it may not be easy to determine credible origins based on the Author field, but we will look closer.
|Contributed Daily News Bin Staff|