The Secret Service is in the market for software capable of detecting sarcastic language online, according to the Washington Post.
In a note posted on FBO.gov, the agency indicated that it wants a software tool that can perform real-time stream analysis, sentiment and trend analysis, audience and geographic segmentation, access to historical Twitter data and “ability to detect sarcasm and false positives,” among other attributes.
“Our objective is to automate our social-media monitoring process,” Secret Service spokesman Ed Donovan told the Post. “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.”
In theory, sarcasm detection would give the Secret Service a better idea of which online postings were genuine threats, as opposed to jokes. Because a piece of software is totally capable of figuring out every possible nuance of human language and making the right decision, 100 percent of the time.
Efforts at efficient sarcasm detection have actually been underway for quite some time. In summer 2013, for example, the BBC reported that French tech firm Spotter had crafted an analytics platform that could scan social media and surface sarcastic comments.
The subtleties of human speech, however, gave Spotter’s software a bit of trouble. “One of our clients is Air France. If someone has a delayed flight, they will tweet, ‘Thanks Air France for getting us into London two hours late’—obviously they are not actually thanking them,” Spotter executive Richard May told the BBC at the time. “We also have to be very specific to specific industries.” No, really?
Seriously, though, tech companies are hard at work on the most effective methods of automated sentiment analysis, if only so that clients can better respond to community and customer feedback. If the software can also prevent at least a few people from being arrested for making innocent jokes, that would also count as a win.
- Data Analytics’ Next Big Feat: Sarcasm Detection
- Do All Companies Really Need ‘Big Data’?
- 4 Buzzwords Ripe for Elimination
Image: David Stuart Productions/Shutterstock.com