For all of you singles out there — imagine meeting someone at, let’s say, a bookstore. The conversation is going well and you think, maybe, you’re catching a flirty vibe. You pull out your iPhone and take a quick peek at your Flirt App, which is blinking a bright yellow 93%. Yes! It’s on!
Believe it or not, that’s going to happen sooner than you think thanks to a new technology taking shape at Stanford University.
Computer scientist Rajesh Ranganath and his colleagues developed a flirtation-detection machine that — based on prosodic (meaning: structure of verse), dialogue, and lexical clues — can detect a speaker’s intent to flirt with up to 75 % accuracy.
In contrast, without the machine men were only 56.2 % accurate when assessing if their date was flirting with them, and women were only 62.2 % accurate. Results were uncovered during a research study(PDF) by testing the machine’s analysis against the self-reported intentions and perceptions of men and women on a speed date.
Courtesy of author Jena Pincott’s excellent blog, here are a few of the study’s main findings:
When flirting, men ask more questions, use more “you” and “we,” laugh more, and use more sexual, anger, and negative-emotional words. They also speak faster, with higher pitch, but with a softer voice.
When flirting, women use more “I” and less “we;” have an expanded pitch range, laugh more, use repair questions (Excuse me?) but not other kinds of questions; use more sexual terms; use far less appreciation terms (Wow, That’s true, Oh, great) and backchannels (Uh-huh, Yeah, Right, Oh, okay.); and use more words in general than men.
Both genders convey intended flirtation by laughing more, speaking faster, and using higher pitch.