Citation Trajectory Prediction

Citation trajectory prediction aims to forecast the future citation counts of scientific publications, helping researchers and institutions identify impactful work early on. Recent research focuses on leveraging advanced techniques like transformer-based models (e.g., BERT) and graph neural networks to incorporate textual content, publication metadata, and the dynamic relationships within academic networks into predictive models. These improved models are evaluated using metrics like Spearman's rank correlation and are increasingly applied to multi-domain datasets, enhancing their generalizability and utility for applications such as research funding allocation and technology forecasting.