Harvard CGA joined forces with MIT SUL in 2021 to use social media data to study the effects of climate change on people’s well being. To achieve this objective, we developed the Twitter Sentiment Global Index  (TSGI) dataset, an open dataset for monitoring Subjective Well-Being (SWB) globally. By applying Natural Language Processing techniques to our archive of 10 billion geotagged tweets posted from 2010 to the present, we constructed a multi-year database that has daily global coverage and is updated monthly. This is the first time enrichment has been achieved on this large scale involving processing of about 10 billion tweets. We believe that this enrichment will be useful for a wide range of research applications involving the use of sentiment and geography on Twitter data. This dataset is cureently being used by the group to study global nonlinear effect of temperature on human sentiment. The scripts can be found on our Github here.

Questions/comments on this project can be send to Devika Kakkar.