آمار
| تعداد نشریات | 45 |
| تعداد شماره‌ها | 1,386 |
| تعداد مقالات | 17,000 |
| تعداد مشاهده مقاله | 54,687,117 |
| تعداد دریافت فایل اصل مقاله | 17,248,681 |
Relational Graph Convolutional Networks for Sentiment Analysis | ||
| Computational Methods for Differential Equations | ||
| مقالات آماده انتشار، پذیرفته شده، انتشار آنلاین از تاریخ 03 خرداد 1404 اصل مقاله (2.68 M) | ||
| نوع مقاله: Research Paper | ||
| شناسه دیجیتال (DOI): 10.22034/cmde.2025.65816.3048 | ||
| نویسندگان | ||
| Asal Khosravi؛ Zahed Rahmati* ؛ Ali Vefghi | ||
| Department of Mathematics and Computer Science, Amirkabir University of Technology, Tehran, Iran. | ||
| چکیده | ||
| 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. | ||
| کلیدواژه‌ها | ||
| Heterogeneous Graphs؛ Sentiment Analysis؛ Graph Neural Networks؛ Relational Graph Convolutional Networks؛ Pretrained Language Models | ||
|
آمار تعداد مشاهده مقاله: 44 تعداد دریافت فایل اصل مقاله: 24 |
||