We are about to run an online complain system for our online news press system with about 10000 members and readers daily. Like any other online forum, we receive improper (spammy) comments containing bad words and offensive comments everyday.

Our plan is to ask our readers to report them. The question is, how many "BAD" reports is considered enough to remove that comment?

The number will be set up in the automated system and all comments with more than that number of "complaints" will be removed.


2 Answers 2


I would suggest that in a site where a large number of users will be seeing the content, you don't want a set number, but rather a set percentage.

If you use a fixed number and set the number high, less popular articles will have a hard time getting rid of undesirable content. If you set it too low, people who simply don't like an opinionated comment may remove it even though they are a small minority of the viewers. That said, you also want a minimum number of required flags as well. Otherwise, if the first viewer doesn't like it and flags it, then 100% of viewers flagged it.

As for exact levels to set at, this is just as tricky as anything in dealing with user moderated content. It depends very widely on your readers and how pro-active they are about reporting content. Just like a good spam filter, it takes time and effort to train properly for your environment.

If it isn't too difficult to do so, I'd recommend putting the system up for a week or two where reports simply send it to a queue of comments to be manually reviewed. Take a look at what kind of report rates you are getting for both accurately and inaccurately flagged comments and then set the levels such that you have relatively few false positives while generating few or no false negatives.

If that simply isn't an option, you'll need to guess and check. I'd start with a minimum of flags from about 0.5% of the typical day 1 viewership of a small article and make sure at least 1% to 2% of the viewers have flagged, but that's probably still going to make some false positives unless you have a very well behaved viewership, so be sure to check what posts are getting removed and raise it as necessary.

If you would prefer early false negatives, I'd try something more like 1.5-3% of day 1 viewership as a min and 5% of viewers have flagged. That's a lot more likely to result in false negatives due to the portion of people that typically bother reporting anything but the worst violations, but it should be a lot safer against false positives. Still, check for errors in either direction though, as individual communities can differ greatly.

Another, more advanced option, is to have allow a pool of active participants who show good judgement in comment moderation to review flagged posts as well. This is actually similar to how Stack Exchange deals with questions and answers that don't fit. You gain the ability to access a review queue after a certain level of involvement and then have the ability to actually review if issues are actually issues. It is likely a more accurate system, but it is also much harder to get running well.

  • I really like the idea of percentage. We are hardly working on an automated filtering system to get rid of those comments automatically, but as no computer software can actually think like a sick minded person, it was our initial solution to ask READERS to help us on that.
    – Ben Bozorg
    Aug 21, 2015 at 1:02
  • @behnambozorg - Right, I'm not talking about an automated system that works without human interaction, but rather an automated system for dealing with the flags that people submit.
    – AJ Henderson
    Aug 21, 2015 at 13:52

Adding to AJ Henderson's answer:

  • The percent of users that will see offensive content and notice a flag button may be lower than you would think, depending on your target audience. You may want to do so A/B testing if you wish (leave spam up on ONE article that isn't offensive and see how many people see it vs. click it)
  • A lot of people don't read the comments, so factor that into the percent. In fact not everyone even reads the post before commenting on it (see "The Ars Banana Experiment" on http://blog.codinghorror.com/because-reading-is-fundamental-2/). That shows that a lot of people skim the posts themselves, let alone reading every comment.
  • People may flag a comment if it's incorrect (personal experience on SE), so you can't delete something that may be flagging for another reason than spam. A simple dialog that makes the user select spam/offensive/other (add comment) may help you categorize the data to prioritize rankings and allow you to do stuff like make you manually review "other" flags.

One thing to consider: what are your goals for auto-deletion? If you only want to get it off the post quickly to not tarnish the reputation of your blog, you could have them auto delete after a small percent of visitors and review all the deleted posts. If it's to handle workload, be careful that you aren't over-deleting. If there's somewhat of a doubt, it's always better to send it to a (hopefully) smarter human to decide on it.

  • 1
    @behnambozorg would you care to elaborate? I don't understand how that makes a difference compared to any other type of login. Aug 21, 2015 at 1:09
  • My description was to clarify your point on "be careful that you aren't over-deleting...". As there is more than 500 Posts coming everyday, it has to be an automated process. Otherwise someone has to sit and go through about 1000 lines of content and decide. Cheers
    – Ben Bozorg
    Aug 21, 2015 at 4:06
  • @behnambozorg but that isn't related to your first comment. Aug 21, 2015 at 15:45

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Not the answer you're looking for? Browse other questions tagged or ask your own question.