Measuring Traffic Manipulation on Twitter(comprop.oii.ox.ac.uk)
comprop.oii.ox.ac.uk
Measuring Traffic Manipulation on Twitter
https://comprop.oii.ox.ac.uk/research/working-papers/twitter-traffic-manipulation/
6 comments
The problem is similar to bots in gaming. Banning bots predictably gives the attacker (bot builder) clear success/failure signals for evading detection, then it becomes a detect-vs-evade arms race that the bot builders will likely win.
Detecting and monitoring the bots provides a possibly similar outcome, but t with the advantage that he platform knows the bots. If there are bots with way, the platform would probably prefer the option that allowes them to know who the bots are.
The middle ground is basic auto detection/bans for simple abuse and infrequent ban waves for the rest, where bots are detected and all banned together. This makes it hard for the writers to understand which signals have them away and gives them the disincentive of uncertainty. This is popular in gaming, where bot and cheat farms are detected and studied by they platform for up to several months before bans are handed out.
Detecting and monitoring the bots provides a possibly similar outcome, but t with the advantage that he platform knows the bots. If there are bots with way, the platform would probably prefer the option that allowes them to know who the bots are.
The middle ground is basic auto detection/bans for simple abuse and infrequent ban waves for the rest, where bots are detected and all banned together. This makes it hard for the writers to understand which signals have them away and gives them the disincentive of uncertainty. This is popular in gaming, where bot and cheat farms are detected and studied by they platform for up to several months before bans are handed out.
Another issue is punishment. Ideally, if a particular user paid a bot service to add 100k new followers to their profile, not only the bots but the manipulative user should be banned.
But there's no way for Twitter (or any other platform) to determine who's actually responsible. "False flags" (framing a user by buying followers for them, or running bots themselves to follow them) are not uncommon, so the best Twitter can do is remove the followers and improve bot detection capabilities. This lets users continually pay for more bots to replenish their periodically purged follower count.
But there's no way for Twitter (or any other platform) to determine who's actually responsible. "False flags" (framing a user by buying followers for them, or running bots themselves to follow them) are not uncommon, so the best Twitter can do is remove the followers and improve bot detection capabilities. This lets users continually pay for more bots to replenish their periodically purged follower count.
The most interesting are coordinated human and machine traffic manipulation
How does this account for "reputation"? I know that, to avoid flagging new users, most platforms use reputation based algorithms that rate users based on their internet activity prior.
I don't understand how the platform owners don't put a stop to this when it's this easy to detect.
I guess engagement is a key metric that looks good to shareholders and advertisers.