This Site Uses Tweets To Analyze Your Personality
Last Updated April 13, 2016, 11:30 PM
ADVERTISEMENT
We all wonder how we come off online. Are we the cool customer we’ve always believed? Or do our coworkers email our tweets back and forth to each other for nefarious reasons?
Now this site, analyzewords.com, will tell you exactly how you appear to other people. The site works by analyzing 400 or so “junk words,” small indicators that nevertheless can say a lot about a person.
“Across dozens of studies, junk words have proven to be powerful markers of people’s psychological states,” the researchers write. “When individuals use the word I, for example, they are briefly paying attention to themselves. People experiencing high levels of physical or mental pain automatically orient towards themselves and begin using I-words at higher rates. I-use, then, can reflect signs of depression, stress or insecurity.”
The site was written by scientists working at Auckland Medical School in New Zealand and University of Texas at Austin. Their research shows that junk words are a highly accurate measurement of personality.
A recent New Yorker article highlighted the predictive effects of tweet analysis for heart disease mortality rates. While divining medical information from tweets seems insane, it worked when taken as a predictor for a large populations.
“Counties where residents’ tweets included words related to hostility, aggression, hate, and, fatigue—words such as ‘asshole,’ ‘jealous,’ and ‘bored’—had significantly higher rates of death from atherosclerotic heart disease, including heart attacks and strokes. Conversely, where people’s tweets reflected more positive emotions and engagement, heart disease was less common. The tweet-based model even had more predictive power than other models based on traditional demographic, socioeconomic, and health-risk factors.”
The analysis seems to work, especially when we ran them on our favorite celebs. Click ahead to check them out. (Use it on yourself or your friends here.)
ADVERTISEMENT