Open Access

ARTICLE

Learning Temporal User Features for Repost Prediction with Large Language Models

Wu-Jiu Sun¹, Xiao Fan Liu^1,2,*

1 School of Computer Science and Engineering, Southeast University, Nanjing, 211189, China
2 Department of Media and Communication, City University of Hong Kong, Hong Kong, 999077, China

* Corresponding Author: Xiao Fan Liu. Email:

Computers, Materials & Continua 2025, 82(3), 4117-4136. https://doi.org/10.32604/cmc.2025.059528

Received 10 October 2024; Accepted 23 December 2024; Issue published 06 March 2025

Abstract

Predicting information dissemination on social media, specifically users’ reposting behavior, is crucial for applications such as advertising campaigns. Conventional methods use deep neural networks to make predictions based on features related to user topic interests and social preferences. However, these models frequently fail to account for the difficulties arising from limited training data and model size, which restrict their capacity to learn and capture the intricate patterns within microblogging data. To overcome this limitation, we introduce a novel model Adapt pre-trained Large Language model for Reposting Prediction (ALL-RP), which incorporates two key steps: (1) extracting features from post content and social interactions using a large language model with extensive parameters and trained on a vast corpus, and (2) performing semantic and temporal adaptation to transfer the large language model’s knowledge of natural language, vision, and graph structures to reposting prediction tasks. Specifically, the temporal adapter in the ALL-RP model captures multi-dimensional temporal information from evolving patterns of user topic interests and social preferences, thereby providing a more realistic reflection of user attributes. Additionally, to enhance the robustness of feature modeling, we introduce a variant of the temporal adapter that implements multiple temporal adaptations in parallel while maintaining structural simplicity. Experimental results on real-world datasets demonstrate that the ALL-RP model surpasses state-of-the-art models in predicting both individual user reposting behavior and group sharing behavior, with performance gains of 2.81% and 4.29%, respectively.

---

Keywords

---