With the growth of textual data across online platforms, sentiment analysis is essential for deriving insights from user-generated content. While traditional approaches and deep learning models have shown promise, they often cannot capture complex relationships between entities. In this paper, we propose using Relational Graph Convolutional Networks (RGCNs) for sentiment analysis, which provide better interpretability by modeling dependencies between data points represented as intercon- nected nodes in a graph structure. We demonstrate our method’s effectiveness through pre-trained language models such as BERT and RoBERTa with RGCN architecture on product reviews from Amazon and Digikala datasets and analyze the resulting performance. Our experiments underscore the strength of RGCNs in capturing relational information for sentiment analysis tasks.
Khosravi, A. , Rahmati, Z. and Vefghi, A. (2025). Relational Graph Convolutional Networks for Sentiment Analysis. Computational Methods for Differential Equations, (), -. doi: 10.22034/cmde.2025.65816.3048
MLA
Khosravi, A. , , Rahmati, Z. , and Vefghi, A. . "Relational Graph Convolutional Networks for Sentiment Analysis", Computational Methods for Differential Equations, , , 2025, -. doi: 10.22034/cmde.2025.65816.3048
HARVARD
Khosravi, A., Rahmati, Z., Vefghi, A. (2025). 'Relational Graph Convolutional Networks for Sentiment Analysis', Computational Methods for Differential Equations, (), pp. -. doi: 10.22034/cmde.2025.65816.3048
CHICAGO
A. Khosravi , Z. Rahmati and A. Vefghi, "Relational Graph Convolutional Networks for Sentiment Analysis," Computational Methods for Differential Equations, (2025): -, doi: 10.22034/cmde.2025.65816.3048
VANCOUVER
Khosravi, A., Rahmati, Z., Vefghi, A. Relational Graph Convolutional Networks for Sentiment Analysis. Computational Methods for Differential Equations, 2025; (): -. doi: 10.22034/cmde.2025.65816.3048