Comparing User Activity on X and Mastodon

2024-12-15

BigData Congress [Services Society]

AI Summary

This study investigates how federated architecture shapes user behavior by systematically comparing Japanese users’ activities on the centralized platform X (formerly Twitter) and the federated decentralized platform Mastodon (exemplified by the instance mstdn.jp). Using large-scale public Japanese-language datasets from both platforms, we apply statistical analysis, temporal modeling, and LDA topic modeling to examine differences in user engagement, interaction patterns, and topical distributions. Results reveal that X exhibits a pronounced reply-driven engagement pattern, whereas Mastodon users demonstrate more balanced posting behavior and greater temporal stability in participation. Moreover, structural topic divergence emerges across domains—particularly in politics and subcultural discourse—indicating platform-level ideological and cultural segmentation. This work provides the first empirical evidence of how federation influences micro-level social media behavior, offering critical insights into the socio-technical implications of decentralized architectures. It addresses a key gap in the empirical literature on federated social networks.

Technology Category

• Application Domains: Humanities & Computational Social Science
• Machine Learning: Distributed Machine Learning & Federated Learning
• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval

Application Category

• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Systems and Infrastructure for Web, Mobile and WoT: Decentralized Web and Fediverse systems
• Web Mining and Content Analysis: Topic discovery and tracking

Abstract

The "Fediverse", a federation of decentralized social media servers, has emerged after a decade in which centralized platforms like X (formerly Twitter) have dominated the landscape. The structure of a federation should affect user activity, as a user selects a server to access the Fediverse and posts are distributed along the structure. This paper reports on the differences in user activity between Twitter and Mastodon, a prominent example of decentralized social media. The target of the analysis is Japanese posts because both Twitter and Mastodon are actively used especially in Japan. Our findings include a larger number of replies on Twitter, more consistent user engagement on mstdn.jp, and different topic preferences on each server.

Problem

• Analyzes user activity differences between Twitter and Mastodon.
• Focuses on Japanese posts due to high usage in Japan.
• Examines reply frequency, engagement, and topic preferences.

Innovation

• Analyzes user activity on decentralized platforms
• Compares Twitter and Mastodon engagement metrics
• Focuses on Japanese user data for insights