Ever get a message from a friend but can't determine if they're being serious or joking? Well that could be a thing of the past as French analytics company Spotter has developed an analytics tool that claims to be able to identify sarcastic comments posted online.
It claims that it"s able to identify sentiment with an accuracy rate of up to 80%. The software featured uses a combination of linguistics, semantics and heuristics to create algorithms that generate reports about online reputation. Algorithms have been developed to reflect various tones in 29 different languages including Chinese, Russian and Arabic. Some of its clients include the UK Home Office, the EU Commission and Dubai Courts and the company only monitors those posts that are made public.
If there"s any uncertainty, the company says that clients can verify the reports themselves if they wish, although there"s debate as to whether an algorithm is really the best tool to use to decide whether something is a joke or not. While there are some obvious clues, saying that its accuracy rate is up to 80% might be a little ambitious, considering how subtle we can be with such statements.