msgbartop
Social media analytics for decision-making
msgbarbottom

15 Dec 08 Social media at its worst – post-mortem cyber-bullying

It is possible, I am sure, to put on rose-colored glasses and see only good coming out of the explosion of social media. This kind technology is driving influence away from big media and that’s good. It is shifting people away from passive consumption toward interactive participation and that also is good. But let’s not ignore the need to form new habits and traditions, to define boundaries of appropriateness and even pass new legislation occasionally.

The problem of cyber-bullying hit me hard last week. As I wrote last week, I volunteer as a critical incident stress management debriefer. Most of the debriefings I do are with first responders – fire, EMS, police, dispatchers and similar workers. But our team also reaches out to the community; when you hear on the news that grief counselors are available to an organization after an incident, that’s us. The reason cyber-bullying is on my mind is that over the last few weeks, I have spent quite a bit of time with teenagers who are trying to cope with the suicides of friends.

Confidentiality is paramount, so I cannot offer any details of any incident I’ve been involved in. But imagine a middle school or high school student who learns that a friend has committed or attempted suicide, who goes to that friend’s MySpace, Facebook or other social media home page and finds mean and horrible things written about them. What’s worse, imagine if those things were written after their friend took that awful step.

I came away from one recent set of debriefings absolutely convinced that if there is any possible way to do it, the industry should figure out a rapid way to disable, freeze or at least moderate the pages of any minor who has been a victim of violence. I emphasize “rapidly” because word gets around fast (a whole separate problem; texting is not a good way to find out your friend is dead) and cyber-bullies can post unbelievably nasty messages in no time at all.

While I agree with those who argue that the best solution to cyber-bullying is education, in this kind of situation, it is too late to teach new behavior and the consequences are too severe. Any solution to this problem faces great technical and political challenges, but I have little doubt that the work will be worthwhile.

  • How about a comment hold when there is a burst of negative comments? The hold could be lifted by the owner or a moderator.

    Sentiment extraction is getting better and probably good enough for this application. I'm sure there are some other features to train on, maybe negative comments from first-time commenters.
  • Nick Arnett
    Good thoughts... The big challenge is figuring out how to make it happen fast.
  • A rapid burst is an indicator by itself.

    When a user gets five messages per day from the same three people suddenly gets 30 messages in 10 minutes from 30 people with half of them negative, that is an event worth flagging.

    Traffic analysis has been pretty well-understood by the military intelligence folk for a few decades, including rapidly flagging a new pattern of messages. Banks use similar algorithms for fraud detection, so there are good unclassified methods.

    The main problem is the cost of manual moderation for false positives. My wild guess is that this would take a few hours of data to recognize a burst, but it might be much less, maybe 30 minutes.
blog comments powered by Disqus