What is it about?
A study of 1.53 billion tweets suggests the removing of “LOL” and other misleading words can improve well-being estimates and monitoring ability.
Photo by John-Mark Smith on Unsplash
Why is it important?
Social media posts can help us understand how people are adapting to and coping with the new normal. But our words are useful not just to understand what we – as individuals – think and feel. They’re also useful clues about the community we live in. Why is this so?
Read the Original
This page is a summary of: Estimating geographic subjective well-being from Twitter: A comparison of dictionary and data-driven language methods, Proceedings of the National Academy of Sciences, April 2020, Proceedings of the National Academy of Sciences, DOI: 10.1073/pnas.1906364117.
You can read the full text:
Data and language model
We've released the resources for this paper. Key highlights: county-level language features used for the analysis, and the best performing Life Satisfaction language model (trained on the Facebook data of survey respondents).
What do your tweets say about your happiness?
Article in Inverse magazine about our study
Improving the prediction of regional well-being from tweets
Featured Research in NUS News
Estimating geographic subjective well-being from Twitter: A comparison of dictionary and data-driven language methods
Open-access version of the study
Removing as few as three words ("lol", "love" and "good") from well-being measurements can improve regional estimates of well-being based on emotion measurements.
The following have contributed to this page