Sentiment Analysis of Drug Reviews using Transfer Learning
Punith NS, Krishna Raketla · 2021 Third International Conference on Inventive Research in Computing Applications (ICIRCA) · 2021
With more and more people expressing their opinions on the web, Effective and Accurate Sentiment Analysis of the data is a burgeoning research area in the field of Machine Learning and Natural Language Processing. The proposed research study has built the multiple deep learning-based classification systems. Neural Network based Models with ELMO Word Embeddings as an input are built and compared with various Transformers-based classification such as BERT, XLNET and other variants of the BERT Model. Using the Drug Reviews Dataset which was collated by crawling through online pharmaceuticals review websites, where various pre-trained word embedding models are compared along with transformers and Deep Neural Network Architectures.