GBRE-AHB: contextual understanding for cross-domain aspect categorization with adaptive hyperparameter tuning

The cross-domain aspect detection and categorization is a vital task in natural language processing, enabling the automated identification and categorization of aspects in textual data spanning diverse domains. Traditional methods face several complexities such as scalability, limited contextual understanding of words, data sparsity, and adaptation difficulty. So, a novel method named gated bidirectional recurrent encoder-based adaptive honey badger (GBRE-AHB) algorithm is proposed for cross-domain aspect detection and categorization. In this study, the bidirectional encoder representations for transformers (BERT) is utilized to capture contextual information from text and enable better aspect identification and categorization by understanding the context. The local optimization problems are identified and solved by determining an adaptive strategy. Also, the gated recurrent unit (GRU) is employed to sequence the text data and allow aspect detection by considering the sequence in which aspects appear within a document. The study is validated on the datasets, namely the IMDB dataset of 50 K movie reviews and the cell phone reviews sentiment analysis-body dataset. The efficiency is validated by various metrics that attained the ranges as F1-score (97.85%), specificity (97.83%), recall (97.82%), precision (97.94%), and accuracy (98.67%), respectively. The experimental results revealed that the proposed method for cross-domain aspect detection and categorization as well as improved the reliability as well as longevity of the model and determined the impacts applied in the categorization process.