Global Public Sentiment on Decentralized Finance: A Spatiotemporal Analysis of Geo-tagged Tweets from 150 Countries

TL;DR

The paper addresses the spatial distribution of public sentiment toward decentralized finance by analyzing over 150 million geo-tagged DeFi-related tweets from 2012–2022 across ~150 countries, integrated with GDP per capita and cryptocurrency regulation data. It employs Moran’s I, geographically weighted regression, Fisher's Z, K-means clustering, and LDA topic modeling to quantify regional variations, causal-like relationships, and thematic content. Key findings show GDP per capita becomes a significant predictor of DeFi tweet proportions after 2014, with stronger effects in higher-income regions and after major crypto market moves; three country clusters reveal distinct sentiment and topic profiles. The work advances computational social science in finance, offers policy-relevant insights for financial inclusion and regulation, and contributes open-science resources (data and code on GitHub and KNIME workflows) to support ongoing research.

Abstract

Blockchain technology and decentralized finance (DeFi) are reshaping global financial systems. Despite their impact, the spatial distribution of public sentiment and its economic and geopolitical determinants are often overlooked. This study analyzes over 150 million geo-tagged, DeFi-related tweets from 2012 to 2022, sourced from a larger dataset of 7.4 billion tweets. Using sentiment scores from a BERT-based multilingual classification model, we integrated these tweets with economic and geopolitical data to create a multimodal dataset. Employing techniques like sentiment analysis, spatial econometrics, clustering, and topic modeling, we uncovered significant global variations in DeFi engagement and sentiment. Our findings indicate that economic development significantly influences DeFi engagement, particularly after 2015. Geographically weighted regression analysis revealed GDP per capita as a key predictor of DeFi tweet proportions, with its impact growing following major increases in cryptocurrency values such as bitcoin. While wealthier nations are more actively engaged in DeFi discourse, the lowest-income countries often discuss DeFi in terms of financial security and sudden wealth. Conversely, middle-income countries relate DeFi to social and religious themes, whereas high-income countries view it mainly as a speculative instrument or entertainment. This research advances interdisciplinary studies in computational social science and finance and supports open science by making our dataset and code available on GitHub, and providing a non-code workflow on the KNIME platform. These contributions enable a broad range of scholars to explore DeFi adoption and sentiment, aiding policymakers, regulators, and developers in promoting financial inclusion and responsible DeFi engagement globally.

Figures (21)

• Figure 1: Proportions of tweets related to decentralized finance across countries. The figure illustrates the spatial distribution of tweets containing at least one decentralized finance-related keyword. Darker shades indicate a higher proportion of relevant tweets originating from that country, while lighter shades represent lower proportions.
• Figure 2: Sentiment scores of tweets related to decentralized finance across countries. The figure visualizes the average sentiment score of tweets containing at least one decentralized finance-related keyword. Higher sentiment scores (in darker shades) indicate a more positive sentiment, while lower scores (in lighter shades) reflect a more negative sentiment.
• Figure 3: Fisher's transformation of correlation coefficients across years. The figure illustrates the temporal evolution of the correlation between GDP per capita and the proportion of tweets containing keywords related to decentralized finance. The Fisher Z-transformed correlation coefficients provide a stabilized measure of correlation, accounting for variations in sample size across years. Positive values indicate a stronger association between GDP per capita and keyword prevalence, while negative values suggest an inverse relationship. The confidence intervals represent the statistical uncertainty in estimating these correlations over time.
• Figure 4: Global clustering of countries based on decentralized finance-related tweets, sentiment scores, and economic indicators. Countries are color-coded according to their assigned cluster, which reflects similarities in their level of engagement with decentralized finance, public sentiment, and economic development. The classification is derived using a K-means clustering algorithm on 145 countries.
• Figure 5: Scatter plot of GDP per capita, sentiment score, and proportion of tweets related to decentralized finance. Each point represents a country, positioned according to its GDP per capita and the proportion of relevant tweets, with color intensity reflecting sentiment score. The visualization highlights patterns in economic development, online engagement with decentralized finance, and public sentiment across different countries.