Tweets show that hardware stores evoke disgust, but hostels bring joy

A study of nearly 2 million tweets over a year suggests that people in San Francisco feel disgusted when they’re in hardware stores, and Londoners are happiest in hostels or motels


February 1, 2023

Tweets from people in San Francisco suggest they feel disgusted at hardware stores now only near real estate offices

Getty Images/Mascot

Your tweets can reveal when and where you are angry, disgusted, sad, or happy.

Panote Siriaraya of the Kyoto Institute of Technology, Japan, and his colleagues believed that tweets contain a “reach of information” about human behavior, analyzed the content of tweets posted in San Francisco and London from early September 2016 to late August 2017 .

Siriaraya says they used data from that time because Twitter removed precise location tagging from its posts in 2019. The researchers had also previously analyzed tweets posted between 2016 and 2017 for a previous study, which they reused.

The team drew a boundary around each city and analyzed every tweet posted within those geographic areas and not sent from apps like Foursquare, which automatically tweets when a user “checks in” with their app.

In total, the researchers analyzed 1.57 million tweets from people in London posted by 180,000 users and 390,000 tweets from San Francisco posted by 65,000 users. According to the researchers, these cities were chosen because they can be accurately tracked using OpenStreetMap, a tool that can pinpoint where tweets were sent.

An artificial intelligence known as a neural network classified the content of each tweet based on the emotion it expressed most.

The results indicated that tweets with an angry tone were most common among people in San Francisco on Wednesdays compared to Tuesdays for Londoners. According to the researchers, this could be explained by people feeling frustrated while getting through a work week.

Tweets posted over the weekend tended to show more positive emotions, such as happiness, compared to more common negative emotions, such as sadness, on weekdays, which is unsurprising, Siriaraya says.

In San Francisco, people were most likely to tweet disgusting posts when they were near real estate agents, followed by hardware stores. They also tended to be angrier at the city’s bridges. According to Siriaraya, this anger can be explained by the limited number of bridges in San Francisco, which causes traffic to build up as people enter and exit the city.

Anger was expressed at bus stops in London, which researchers say may stem from frustrations while waiting for public transport. The results suggest that people in London are happiest in tourist accommodation such as motels and hostels. Hotels and restaurants were associated with both anger and joy.

The research has been carried out on an unprecedented scale, says David Ellis of the University of Bath, UK. However, Ellis says he wished the researchers had reached out to some of those who tweeted to confirm that the neural network correctly classified the emotion behind their post.

Barry Smith from the University of London’s School of Advanced Study also has questions about the classification of the tweets. “One of the emotions they had was anticipation,” he says. “It’s funny because you can anticipate things with fear or anticipate things with pleasure.” In their study, the researchers classified anticipation as a positive emotion.

Smith also suggests that some of the locations are classified in a way that makes it difficult to tell what’s going on around the person posting. For example, tweets containing the word “wine” were associated with sadness in San Francisco and fear in London.

Siriaraya says the results and the insights that can be gleaned from them do not always reflect the complexities of human life and require further research.

Article modified on February 2, 2023

This copy has been updated to better describe the places in London that bring joy to people on Twitter.

More on these topics:

Leave a Reply

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