A domain knowledge infused gated network using integrated sentiment prediction framework for aspect-based sentiment analysis

Aspect-Based Sentiment Analysis (ABSA) targets sentiments on specific aspects in reviews, offering more granularity than overall sentiment analysis. Challenges in ABSA include handling implicit sentiments, varying expressions, linguistic nuances, and ensuring robust predictions across domains. Addressing these is crucial for extracting meaningful insights from customer reviews and enhancing products or services. Aiming at these concerns, this paper proposes an Enhanced Knowledge Infused Graph-Gated BERT (EKIG-GBERT) model for ABSA in customer-related program reviews. This innovative approach integrates a Dynamic Sentiment-specific Knowledge Graph (DSSKG) and Knowledge graph-enhanced BERT model with Gated Domain Graph Convolutional Network (KG-BERT-GDGCN) to capture intricate sentiment-aspect relationships. The methodology begins with data pre-processing, including tokenization and noise reduction, followed by domain-specific knowledge infusion via DSSKG. The approach leverages KG-BERT for advanced aspect extraction, enhancing the model's capacity to capture subtle emotional nuances in textual data. Aspect extraction is performed at multiple levels like term, category, implicit, entity, and attribute that leverages the KG-BERT model for comprehensive sentiment representation. Additionally, a structured graph seamlessly integrates affective information from DSSKG and KG-BERT, forming an affective adjacency matrix that encapsulates nuanced emotional connections among words in a sentence. The integrated sentiment prediction framework fuses features from DSSKG and KG-BERT using the GDGCN model. Processing through densely connected layers, dropout, and batch normalization ensures effective regularization, resulting in a robust model that leverages information from multiple sources for improved sentiment analysis. Experimental evaluations using four SemEval datasets (i.e., Rest14 task 4, Lap14 task 4, Res15 task 12, Res16 task 5) demonstrate that the EKIG-GBERT model significantly outperforms existing ABSA methods. The EKIG-GBERT model achieved an accuracy of 97.5% on the Rest14 task 4, 98.5% on Lap14 task 4, 94% on Res15 task 12, and 92% on Res16 task 5. Additionally, the confusion matrix analysis further confirmed its superior performance in distinguishing between various sentiment aspects. These results underscore the model's robustness and reliability in the ABSA prediction tasks.