Tweeting While Eating: About

Tweeting While Eating: Comparing the Sentiments of U.S. Business Locations using Social Media

Main site

Background: In recent years, 'hedonometrics' has become an increasingly valuable scientific method for studying human behavior, and specifically gauging human happiness. This idea has been around since the 1880s, when Francis Edgeworth spoke of the "ideally perfect instrument, a psychophysical machine, continually registering the height of pleasure experienced by an individual". More recently, it has been used to measure population level happiness using messages posted online. For more inforation about the instrument used to measure sentiment, please visit the Hedonometer website. This project is a collaboration with the Computational Story Lab. Website designed by Peter Larsen, with assistance and guidance from Chris Danforth, Peter Dodds, Andy Reagan, and Morgan Frank.

Methods: Individuals using a mobile device application may opt-in to geolocate their message, in which case the exact latitude and longitude of the mobile phone is reported. The accuracy of this information is governed by the precision of the GPS instrument embedded in the phone, which can vary depending on the surrounding topography. As a result of these factors, we are able to approximately place each geolocated message inside a 10 meter circle on the surface of the Earth, within which the tweet was sent. Roughly 1% of the status updates received through Twitter's public API gardenhose feed are geolocated, resulting in a total of 37 million messages in 2011, collectively representing more than 180,000 English-speaking people. Only the geolocated tweets authored within 100 meters of an establishment were included. The geographic coordinates of all businesses in the continental U.S. were identified with a database of phone numbers and addresses, purchased from Yellow Page City Inc.

Publications: The instrument we use to measure happiness has been developed and described in a series of scientific papers including:

Temporal Patterns of Happiness and Information in a Global Social Network: Hedonometrics and Twitter : P. S. Dodds, K. D. Harris, I. M. Kloumann, C. A. Bliss, C. M. Danforth. 2011. Temporal Patterns of Happiness and Information in a Global-Scale Social Network: Hedonometrics and Twitter. PLoS ONE 6(12): e26752. doi:10.1371/journal.pone.0026752


The Geography of Happiness: Connecting Twitter Sentiment and Expression, Demographics, and Objective Characteristics of Place : L. Mitchell, K. D. Harris, M. R. Frank, P. S. Dodds, C. M. Danforth. 2013. The Geography of Happiness: Connecting Twitter sentiment and expression, demographics, and objective characteristics of place. PLoS ONE. 8(5): e64417. doi:10.1371/journal.pone.0064417

US Map

Happiness and the Patterns of Life: A Study of Geolocated Tweets: M. R. Frank, L. Mitchell, P. S. Dodds, C. M. Danforth. 2013. Happiness and the Patterns of Life: A Study of Geolocated Tweets. Scientific Reports. 3, No: 2625, doi:10.1038/srep02625

Two Charts
Bonus: As an additional example application of the technique explored in this website, we report here an interesting result. We collected tweets from individuals who geolocated a message from within McDonalds in the year 2011. For these individuals, we also collected messages they authored in the week prior and subsequent to their visit to the fast food restaurant. In the image below, we find that their expressed sentiment is at a minimum roughly 24 hours prior to their indulgence. Happiness increases thereafter for the rest of the week!
McDonald's Track