Why Your Online Impersonation of a 16-year Old Girl Won't Last Long

An anonymous reader writes "Can computers pick up your age and gender from your tweets? If you want to give it a try, here's your chance: 'To develop your software for age and gender identification, we provide you with a training data set that consists of blog posts, Twitter tweets, social media texts, as well as hotel reviews.' Well, at least my paid Amazon reviews are safe for the time being..."

Comments

Re:assuming too much

[TWX]

like totally bieberiffic!

Indeed, I expect that should a learning-capable system monitor the posted text from actual teenage females, it should be able to identify aberrations, especially if that system manages to derive proper nouns and verbs. There will certainly be regional variation, variation based on ones' interests, and variation based on maturity, but with a large enough sample size it should be possible to figure out what is average/normal and what is an outlier.

If the same system was also monitoring groups that are not teenage females, it would learn what that group uses for vernacular and over time could track the migration of speech from high school into adulthood and be able to figure out when someone uses too many previous-generation words or expressions and not enough current-generation words or expressions, to then analyze their postings further. Some precocious teenagers will speak like adults, and probably get false-positive tagged, but it's unlikely that adults could pull it off the reverse correctly for any significant length of time. Even those that work around teenagers in schools or elsewhere will most likely fall out of formal speech into their own youth slang, not current youth slang.