EVOLVE-X: Embedding Fusion and Language Prompting for User Evolution Forecasting on Social Media

2025-07-21

AI Summary

This paper addresses the challenge of modeling evolutionary user behavior in social media by proposing a cross-modal joint embedding framework that unifies the representation of dynamic social networks, shifting interaction patterns, and evolving activity trajectories—enabling downstream tasks such as friend recommendation and risk early warning. Methodologically, it innovatively integrates instruction-tuned large language models (LLaMA-3-Instruct, Mistral-7B-Instruct, Gemma-7B-IT) with lightweight language models (GPT-2, BERT, RoBERTa), leveraging prompt engineering to achieve semantic–structural dual-channel embedding alignment. Experimental results demonstrate that GPT-2 achieves the lowest perplexity (8.21) in cross-modal configurations, significantly outperforming BERT and RoBERTa. The proposed framework attains state-of-the-art performance in long-term behavioral forecasting, link generation, and anomalous activity detection, validating its effectiveness and generalizability for modeling users’ full lifecycle behavior.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: Language Grounding & Multi-modal NLP
• Cognitive Modeling & Cognitive Systems: Social Cognition And Interaction

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Social Networks and Social Media: Generative AI / large language models and their impact on social systems
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

Social media platforms serve as a significant medium for sharing personal emotions, daily activities, and various life events, ensuring individuals stay informed about the latest developments. From the initiation of an account, users progressively expand their circle of friends or followers, engaging actively by posting, commenting, and sharing content. Over time, user behavior on these platforms evolves, influenced by demographic attributes and the networks they form. In this study, we present a novel approach that leverages open-source models Llama-3-Instruct, Mistral-7B-Instruct, Gemma-7B-IT through prompt engineering, combined with GPT-2, BERT, and RoBERTa using a joint embedding technique, to analyze and predict the evolution of user behavior on social media over their lifetime. Our experiments demonstrate the potential of these models to forecast future stages of a user's social evolution, including network changes, future connections, and shifts in user activities. Experimental results highlight the effectiveness of our approach, with GPT-2 achieving the lowest perplexity (8.21) in a Cross-modal configuration, outperforming RoBERTa (9.11) and BERT, and underscoring the importance of leveraging Cross-modal configurations for superior performance. This approach addresses critical challenges in social media, such as friend recommendations and activity predictions, offering insights into the trajectory of user behavior. By anticipating future interactions and activities, this research aims to provide early warnings about potential negative outcomes, enabling users to make informed decisions and mitigate risks in the long term.

Problem

• Predicts user behavior evolution on social media.
• Forecasts future network changes and connections.
• Provides early warnings for negative outcomes.

Innovation

• Uses Llama-3, Mistral-7B, Gemma-7B with prompts
• Combines GPT-2, BERT, RoBERTa via joint embedding
• Cross-modal configs optimize user behavior prediction