An efficient LSTM based cross domain aspect based sentiment analysis (CD-ABSA)

Abstract

This research study focuses the cross-domain aspect-based sentiment analysis (CD-ABSA) for existing source domain annotation data. The CD-ABSA tries to use the valuable information in a source domain to extract aspect terms and evaluate their sentiment polarities in a target domain. It can considerably increase the usage of the source domain annotation resources while also reducing the workload of newer domain data annotation. one of the main components of the CD-ABSA is aspect extraction. In this paper, we utilized the most common topic modelling techniques: LDA and LSA to extract aspects from the reviews as it does not require labelled data. The topics are extracted from the education domain of the Course and Teacher Performance Evaluation (CTPE) dataset. In this paper, we also evaluated the different hyper-parameters on the CD-ABSA model and selected the best and optimal combination. The proposed methodology train on domain-dependent and independent word embedding that achieves CD-ABSA, in particularly end-to-end fashion. The experiment carries out on Academica dataset, which consists of students’ comments/feedback and SemEval-2014 dataset, which includes laptops and restaurants reviews. The evaluation metrics such as (precision, recall, F1 score and validation Accuracy) is considered while judging the LSTM classifier performance for CD-ABSA as a result.