TRABSA: Interpretable Sentiment Analysis of Tweets using Attention-based BiLSTM and Twitter-RoBERTa

arXiv:2404.00297v1 Announce Type: cross
Abstract: Sentiment analysis is crucial for understanding public opinion and consumer behavior. Existing models face challenges with linguistic diversity, generalizability, and explainability. We propose TRABSA, a hybrid framework integrating transformer-based architectures, attention mechanisms, and BiLSTM networks to address this. Leveraging RoBERTa-trained on 124M tweets, we bridge gaps in sentiment analysis benchmarks, ensuring state-of-the-art accuracy. Augmenting datasets with tweets from 32 countries and US states, we compare six word-embedding techniques and three lexicon-based labeling techniques, selecting the …

abstract analysis architectures arxiv attention attention mechanisms behavior challenges consumer cs.cl cs.lg diversity explainability face framework hybrid networks opinion public roberta sentiment sentiment analysis transformer tweets twitter type understanding