A newly-developed Dutch program called TweetGenie has adapted the age-old (so to speak) carnival game of guessing a contestant’s height, weight, or birthday to the digital age.
TweetGenie can guess any Twitter user’s age and gender based solely on tweets, without a name or photo.
The program, currently available only to Dutch Twitter users, analyzes data from the contents of a user’s last 200 tweets.
Then, using its database with lists of words and sequences gathered from almost 3,000 Twitter users, TweetGenie cross-references the content of the specific user’s tweets to determine his or her age and gender.
TweetGenie was developed by researchers at the Meertens Institute and the University of Twente in the Netherlands, who caution that the program has a margin error of four years, which dips for younger users and increases when users are older. They claim that TweetGenie can correctly guess a tweeter’s gender 85% of the time.
So what makes the data skew either towards women or men?
“The distinction between men and women is actually very stereotypical. Men talk about football and women about their nails.”
Further, she adds,
“We note that users use more uniform language from about 35 years and older. There are larger differences between users aged 15 and 20 then there are between users aged 45 and 55.”
That is to say, it’s easy to suss out younger tweeters through their use of emoticons and lingo, but there’s not as much differentiation among adults on Twitter.
Apparently the Twente team, in collaboration with the Meertens Dutch Language and Culture Institute, are planning to update TweetGenie for other languages and even adapt it for Facebook.
If TweetGenie becomes available in the U.S., is it something you’d want to try out for yourself? Do you think your tweets accurately reflect your age and gender?
(Image via Shutterstock)