Comment permalink

Cornell Researchers Looked at Tweets to See When People Were Happy and Sad

Do your happy and sad Tweets reflect your true emotions?

 

The latest social networking study isn’t based on love as some of the past studies I’ve written about, but is based instead on emotions. Cornell University’s cross-cultural study looked at the text in Tweets of over two million different people from around the globe. The purpose of the study was to see if there was a connection between when people Tweeted about certain emotions. 

 

The researchers discovered that people feel more positive at certain times and feel more negative at certain times. That is, if there Tweets are any indication of the Tweeters are actually feeling at any given time of the day. 

 

All of the Tweets that the researchers from Cornell University looked at were written in English; through help with computer technology, the researchers searched specifically for different words and emoticons known to have both positive and negative associations. The researchers were looking to determine if there was an overall pattern of when people would post certain kinds of Tweets and tried to determiner if the Tweets represented either a positive or negative emotion. 

 

The results are stranger than you might expect; the researchers’ found that there are certain times when people are more positive in their Tweets. Some of the findings are not unexpected; most people’s Tweets reflected more negative moods than they would otherwise have at the start of the work week, but their Tweets would get more positive as the week went on. 

 

As for the time of day, it varied a little depending on whether the Tweeter was a “night owl” or a morning person.  

 

According to the New York Times:

 

The pair found that about 7 percent of the users qualified as “night owls,” showing peaks in upbeat-sounding messages around midnight and beyond, and about 16 percent were morning people, who showed such peaks very early in the day.

After accounting for these differences, the researchers determined that for the average user in each country, positive posts crested around breakfast time, from 6 a.m. to 9 a.m.; they fell off gradually until hitting a trough between 3 p.m. and 4 p.m., then drifted upward, rising more sharply after dinner.

It’s interesting to note that the researchers had to factor in the differences for the “night owls” and morning people amongst the Tweeters although the findings for each are approximately what you would expect. I’m wondering if anyone has conducted any similar research amongst Facebookers or even bloggers to see how if the writers’ tone changed at a variety of times during the day. 

When are your Tweets and Facebook status posts the most positive? Have you taken the time to activate your Facebook timeline to see how your Facebook posts were represented over time? 

I haven’t taken the time to check my Facebook status reports or Tweets to see if they follow a similar pattern to what the Cornell researchers found, but I’d definitely be interested to see if there was any correlation.