If there is a reason why people get in trouble for comments online or get into arguments is that without the tone of voice, it becomes hard to tell if someone is joking or being sarcastic, unless of course you know that person really well and if they were being very obvious about it. However it seems that in order to better detect threats to the government, the US Secret Service has recently put in a request for automated Twitter monitoring.
Apart from monitoring the usual threats and spotting red flags, the request also asks that it be able to detect sarcasm and false positives, meaning that the system should be able to tell what might have been a bad attempt at humor/sarcasm versus an actual threat or potential threat online. Speaking to the Washington Post, a spokesman claims that this system will help them gauge their online influence, as well as address complaints that they might receive.
One example they gave was the incident back in 2009 regarding the bottleneck in the tunnels The spokesperson, Ed Donovan, claimed that if the Secret Service had their own system that could monitor Twitter, they’d have been able to detect the problem early and could have done something about it.
“Our objective is to automate our social media monitoring process. Twitter is what we analyze. This is real time stream analysis . The ability to detect sarcasm and false positives is just one of 16 or 18 things we are looking at. We are looking for the ability to quantity our social media outreach.” It’s an interesting proposal, but we have to wonder how will a computer be able to tell if a statement is sarcastic or not? And what if a threat were to be made under the guise of sarcasm so as to fly under the radar?
Filed in Twitter.. Read more about