I recently did some analysis to see which dating apps/sites people were Tweeting about the most. Tinder won by a landslide, followed by OkCupid and Badoo.
Now I wanted to see what these Tweets were about. Using the open-source data analytics tool KNIME, I fed in the Tweets, did some data cleanup, and created word clouds to get a picture of the most common topics.
Let’s start with Tinder:
Some of the words had me scratching my head initially.. castle? Bots? But a little digging led to this retweeted story: “Tinder Hacked By Bots Promoting Castle Clash Game Downloads“.
Other words, like dating, singles, sexy, hot, and matches, all fit in with Tinder’s reputation.
I took a look at the data on swiping right (saying ‘yes’ to a match) and swiping left (saying ‘no’) and people were Tweeting about swiping right almost twice as much as swiping left.
Next up, OkCupid:
As I mentioned in my previous post, about 60% of the OkCupid posts had to do with OkCupid’s boycotting of Firefox because Mozilla’s president had donated to the anti-gay marriage Prop 8. That definitely skews the data! Another big story (for the words nightmare, steals, phone) had this headline: “Nightmare OkCupid Date Steals Girl’s Phone and Impersonates Her Online.” Interestingly, marriage made it into the word cloud (unlike in Tinder and eHarmony) but that seems also to be related to the Mozilla boycott!
Next up in number of Tweets was Badoo–but most of the data was in Spanish.
I decided to focus on the next one instead, eHarmony:
Apparently eHarmony had a commercial out that made a lot of people uncomfortable. As for “job,” it included various job postings at eHarmony (I did get rid of all the Tweets by the dating app’s Twitter account, but other people posted the same information).
995pm refers to a deal eHarmony was running at the time: $9.95 per month.
Other interesting words: exclusive, “findlove”, senior, and matchmaker.
What About Love?
“Love” was the 42nd most common word in Tinder’s Tweets, 108th for OkCupid (people were too busy Tweeting about the boycott!) and the 11th most common at eHarmony. I can’t say I’m surprised that people Tweeting about eHarmony are Tweeting the most about love!
The next thing I’d like to do with this data is sentiment analysis–that is, are people saying more negative or positive things about each of these sites? I’d also like to get some more data for OkCupid since the Mozilla boycott has passed.
You may have noticed that each word cloud contains the name of the dating site/app itself. I did remove the majority of those words (each Tweet has one so it’s not particularly relevant!) but a few stayed in because of the way the data was organized. I used KNIME’s Parts of Speech tagger, and interestingly it sometimes tagged the dating apps as a noun, and sometimes as a verb (depending on where in the sentence it appears). If I were to do this again, I’d remove those instances as well.