Investigate whether reliable prediction models can be built to detect accounts with paid editing activity. From some offline discussions, we know:
- the patterns of paid editors are fairly clear and it would be useful to have them picked up by AI.
- If we ever get good enforcing the TOU than the paid editing pattern will shift more from one sock for multiple jobs to one sock per job. Such algorithms can be even more useful in that case.
- Check out the discussion at https://en.wikipedia.org/wiki/User_talk:Jytdog/Archive_16#meta:Grants:IdeaLab.2FBot_to_detect_and_tag_advocacy_editing
Current detection steps
The following steps are taken by users (in group XX) to identify account that do paid editing:
How prevalent are the paid edit accounts?
Let's define paid edit accounts (for now loosely) as those account who have done at least one edit activity associated with paid editing since their creation. Do we have a sense how prevalent such accounts are?