A study of over 1.5 million tweets over the course of a year found that San Francisco people disliked being in hardware stores, while Londoners reveled most in motels.
technology
February 1, 2023
According to tweets from people in San Francisco, they get annoyed at hardware stores. Getty Images/Mascot
Your tweets may reveal when and where you are angry, fed up, sad or happy.
Panote Silialaya of Kyoto Institute of Technology and his colleagues, who believe the tweets contain a “rich information” about human behavior, tweeted in San Francisco and London between early September 2016 and late August 2017. We analyzed the content of the posted tweets.
Syriaraya said it used data from this period because Twitter removed precise location tagging from posts in 2019. The researchers had already analyzed tweets posted between 2016 and 2017 for their previous study, which they reused.
Rather than being sent by apps such as Foursquare, which automatically tweet when a user “checks in” using the app, the team analyzes all tweets posted within these regions to find out more about each city. I drew a border around the
Overall, the researchers analyzed 1.57 million tweets posted by 180,000 users from Londoners and 390,000 tweets from San Francisco posted by 65,000 users. These cities were chosen, according to the researcher, because he can pinpoint them using OpenStreetMap, a tool that can pinpoint where a tweet was sent.
An artificial intelligence known as a neural network categorized each tweet according to the emotion it most expressed.
The results suggest that angry-toned tweets were most commonly posted on Wednesday among San Francisco residents, compared to Tuesdays among Londoners. Researchers say this could be explained by people feeling frustrated in getting through the work week.
It’s not surprising that tweets posted on weekends tend to express positive emotions, such as joy, while weekdays tend to express negative emotions, such as sadness.
In San Francisco, people tended to tweet disgusting posts as they approached real estate agents’ offices and get angry around the city’s bridges. Siriaraya said the anger could be explained by the limited number of bridges in San Francisco, which creates more traffic as people enter and exit the city.
Researchers found that anger was expressed at bus stops in London, possibly reflecting frustration while waiting for public transport.
The study is on an unprecedented scale, says David Ellis of the University of Bath, UK. But Ellis said the researchers wanted to reach out to people who tweeted to make sure the neural network correctly categorized the emotions behind the posts.
Barry Smith, of the University of London School of Advanced Studies, also has doubts about the classification of tweets. “One of the feelings he had was anticipation,” he says. “It’s funny because you can predict things with fear, and you can predict things with joy.” The researchers considered anticipation to be a positive emotion in their study.
Smith also suggests that some of the locations are categorized in a way that makes it difficult to discern what’s going on around the poster. For example, a tweet containing the word “wine” was associated with sadness in San Francisco and fear in London.
Sirialaya says the results and insights they provide do not necessarily reflect the complexities of human life and require further research.
More on these topics:
