Be Better at Twitter: The Definitive, Data-Driven Guide


A study based on 43,000 responses to Tweets found precisely what people like — and loathe — about microblog posts.


If you could construct, algorithmically, the Most Annoying Tweet Imaginable, it might look something like this:
BREAKING: Last week I had a #sandwich that was SO HORRIBLE, it made me want to #scream. Seriously, why can’t they make better #sandwiches?

The Most Annoying Tweet Imaginable, in other words, would be overly long. It would contain stale information. It would #totally #overuse #hashtags. It would be excessively personal. It would be aggressively mundane. It would be whiny.

All this, at least, according to a new study, released today, that explores what we like in our tweets — and what we find really, really off-putting. “Who Gives a Tweet: Evaluating Microblog Content Value” is the culmination of a year’s worth of analysis conducted by the researchers Paul André of Carnegie Mellon, Michael Bernstein of MIT, and Kurt Luther of Georgia Tech as they set to find out what separates value from vagary in a Twitter post. Last year, the team created a site, Who Gives a Tweet — essentially, a Hot or Not for microcontent — that asked users to designate a selection of tweets according to the emotional responses they provoked (“positive,” “neutral,” “negative”). And then, intriguingly, to explain those responses in their own words. The team, with the help of Mechanical Turk, then analyzed the 43,000 crowdsourced responses they’d collected from the site, looking for patterns and takeaways that might help the rest of us to become better, more crowd-pleasing members of the Twittersphere.

Read the full post: (Click here to read more on The Atlantic.)

Leave a Reply

Required fields are marked *.