Skip to content

The code is fighting liars

July 7, 2016

pin.jpg

Humans are seriously bad at detecting a lie. Contrary to popular opinion nearly half of the written texts containing an untruth go undetected, making room for the deceivers. But a new computer algorithm is now promising to protect us from wilful blindness.

After studying thousands of emails with both, lies and truthful contents, the researchers at the City University London came up with a list of specific tendencies that writers are using in order to conceal their wrongdoings. To dissociate themselves from the content, tricksters are avoiding personal pronouns like I, memine and like to mirror the structures of the sentences to those they are trying to deceive. Liars also more often use adjectives, such as brilliant or sublime and try to link sentences to create the appearance of a coherent text.

Since we are not very good at discovering liars, the impartial helper to do the job for us would come in handy. That is why all of these specifics have been incorporated in the new algorithm. The code proved to be very successful at showing whether the text contains lies. Just by analysing the word use, structure and context, the program currently prides itself with 70% accuracy and will even become better with time. Watch out liars computers are onto you.

Advertisements

From → Hic Salta

Leave a Comment

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out / Change )

Twitter picture

You are commenting using your Twitter account. Log Out / Change )

Facebook photo

You are commenting using your Facebook account. Log Out / Change )

Google+ photo

You are commenting using your Google+ account. Log Out / Change )

Connecting to %s

%d bloggers like this: