<![CDATA[This research proposes an Enhanced TextCNN architecture, integrating a Gated Mechanism and Aspect Fusion to address challenges in automatic movie rating classification from user reviews, such as text complexity and the need to understand sentiment towards specific aspects (e.g., plot, acting). The proposed model incorporates Gated Linear Units (GLU) as an adaptive filter in the convolutional layers to suppress noise and enhance key features, alongside an aspect fusion layer that employs multi-head self-attention to explicitly extract and weight information relevant to specific movie aspects from the text, enabling context-aware classification. Experimental results on a dataset of 50,000 movie reviews show the model achieves an accuracy of 85.67% and a weighted F1 score of 85.55%, significantly outperforming the baseline TextCNN (78.34% accuracy) by a 7.33% improvement, while also demonstrating robustness across reviews of varying lengths and offering better computational efficiency compared to more complex models like BERT.]]>
Copyrights © 2025
