Advancing Urdu NLP: Aspect-Based Sentiment Analysis with Graph Attention Networks
Kamran Aziz, Donghong Ji, Bobo Li, Fei Li, Jun Zhou · 2024
In this study, we unveil an innovative framework for aspect-based sentiment analysis specifically designed for Urdu news headlines. Our approach uniquely combines the power of Graph Attention Networks (GAT) with the multilingual BERT model to navigate the linguistic intricacies of Urdu, a language often overlooked in computational sentiment analysis. Central to our work is the development of a first-of-its-kind, manually annotated dataset for Urdu, meticulously crafted to reflect its diverse linguistic attributes. This dataset serves as a critical tool in enhancing our model’s accuracy and comprehensiveness. By merging the contextual capabilities of BERT with the relational insights provided by GAT, we have created a model that excels in extracting and classifying sentiments from Urdu news content. Our methodology not only involves extensive preprocessing of data, including tokenization, POS tagging, and lemmatization using Stanza, but also sets a new benchmark in aspect extraction and sentiment analysis for Urdu. This pioneering research contributes significantly to narrowing the gap in NLP resources for low-resource languages and facilitate regional language processing, offering valuable insights for linguists, media analysts, and NLP practitioners.