User migration in blockchain-based online social networks through the lens of temporal node representation shift

User migration in online social networks represents a critical phenomenon that can reshape platform dynamics and lead to abrupt structural changes, often triggered by technical, social, or competitive factors. In the context of blockchain-based online social networks, migration events can be particularly disruptive when triggered by hard forks - fundamental splits in the underlying blockchain protocol that create two incompatible versions of the platform. However, understanding how users adapt their behavior before, during, and after such events remains a challenging research question. To address this challenge, we rely on the framework of graph representation learning, with a particular focus on Temporal Graph Neural Networks (TGNNs). In particular, we analyze how node representations returned by TGNNs evolve during the migration event and examine how representation shifts can mirror changes in users’ behavioral patterns and platform interactions. Our study focuses on Steemit, a blockchain-based social network that experienced a significant user migration following a hard fork in its supporting blockchain infrastructure. Our findings highlight that both the prediction performance and node representation are influenced by the occurrence of the migration event. We detect shifts in node representations that correspond to changes in individual user behavior throughout the event. Furthermore, group-centric analysis reveals changes in behavior and memberships among similar users during different transition periods. Additionally, we find a level of polarization in node representations caused by the migration event, which gradually diminishes over time, resulting in more evenly distributed dimensions of node representations months after the first migration. We compare our approach against two baselines based on network statistics and pre-trained LLM embeddings, showing that TGNNs better capture the distribution shift derived by the migration. To summarize, this work offers valuable insights into user behavior dynamics during platform migrations, demonstrating the effectiveness of temporal graph learning approaches in analyzing such transitions in an automated manner.