Topic: graph convolutional networks

How Can AI Avoid Averaging Out Emotions? A New Sentiment Analysis Method Combining Language Models and Graph Neural Networks

At the ACL 2026 conference in San Diego, USA, researchers from our Department presented their paper entitled “PUEB-DimASR at SemEval-2026 Task 3: Escaping the Mean Regression Trap with Graph-Enhanced Transformers for Dimensional Aspect-Based Sentiment Regression“, prepared as part of the SemEval-2026 workshop. The paper was authored by Oskar Riewe-Perła and Prof. Agata Filipowska.