SUL/Harvard CGA collaborative paper accepted to Scientific Data

The SUL paper, "Twitter Sentiment Geographical Index Dataset" has been accepted by the journal Scientific Data – a Nature Journal, and a peer-reviewed and open-access journal.

This paper is authored by Yuchen Chai (MIT DUSP/EECS master’s graduate, SUL researcher), Devika Kakkar (Harvard Center for Geographic Analysis, our collaborator), Juan Palacios and Siqi Zheng. It is a major research outcome of our “Global Sentiment” research theme over the past four years (Yichun and Jianghao are two key researchers on this theme also).

SUL collaborated with Harvard Center for Geographical Analysis (Harvard CGA) on the twitter data and natural language processing part. READ more in the Harvard IQSS article ->

"Twitter Sentiment Geographical Index Dataset" Abstract

Promoting well-being is one of the key targets of the Sustainable Development Goals at the United Nations. Many national and city governments worldwide are incorporating Subjective Well-Being (SWB) indicators into their agenda, to complement traditional objective development and economic metrics. In this study, we introduce the Twitter Sentiment Geographical Index (TSGI), a location-specific expressed sentiment database with SWB implications, derived through deep-learning-based natural language processing techniques applied to 4.3 billion geotagged tweets worldwide since 2019. Our open-source TSGI database represents the most extensive Twitter sentiment resource to date, encompassing multilingual sentiment measurements across 164 countries at the admin-2 (county/city) level and daily frequency. Based on the TSGI database, we have created a web platform allowing researchers to access the sentiment indices of selected regions that are continuously updated monthly.