Where’s the love? Twitter analysis

The internet-era has brought forth a new age of sharing. We share photos, accomplishments, cat videos, trials, and tribulations. We also share a lot of what’s on our minds.

Previously, I used an analysis of tweets to explore trends in anger on twitter. Now, I turn to an examination of love. Looking at:

  • Love expressed by usage of the love and its multiple forms (e.g., love, loved, loving, etc.)
  • Love expressed by emotions ( ? ? ?‍❤️‍? ? ❤️ etc.)
  • Examine how word and emoticon expressions of love corroborate each other
  • Examine regional variations expressions of love


Analysis of 24 million geo-tagged tweets show that on average, 3.37% tweets are using forms of the word “love” (almost 5x more than hate and anger). Of course, there are other ways to express love in a tweet, and this is just a rough tool. On average, 4.5% of tweets use the love emoticons. The image shows the hot-spot analysis of regional differences in the distribution of tweets (words and emoticons). Fully red sections use love statistically significantly more in tweets, fully blue sections use love less in tweets. The map shows a few things:

  • There is significant regional variation in the use of love signifiers, and these regional difference represent stable and relatively large regions (not county by county)
  • There is significant correspondence between word and emoticon signifiers. That’s good news, both seem to indicate the same thing
  • Mostly, the hotspots for love are different than the hotspots for hate
  • Some parts of the country, such as extreme South Texas, use Love and Hate well above national norms

How big are those regional differences? In some cases, the differences are small. Some of the orange and red areas are only slightly above the nationwide average (4.00% vs. 3.37%). Sometimes the difference is stark. For example, portions of Mississippi (at 7%) are 3.5 times more likely to express love than portions of Washington (at 2.0%).

Why do these difference exist? I do not know. Perhaps there are some regional differences in expectations for civility, or different norms for if (or how) the same emotion is conveyed online. Perhaps people in different parts of the country are simply more loving than other parts. I did try lining up this map with some socio-economic indicators like crime-rate, unemployment rate, income distribution, and others. Again, I didn’t get very far.

If you have any ideas, let me know in the comments!

Leave a Reply

Your email address will not be published. Required fields are marked *