Fine-grained Sentiment Classification using BERT

EasyChair Preprint 1762

Abstract

Sentiment classification is an important process in understanding people's perception towards a product, service, or topic. Many natural language processing models have been proposed to solve the sentiment classification problem. However, most of them have focused on binary sentiment classification. In this paper, we use a promising deep learning model called BERT to solve the fine-grained sentiment classification task. Experiments show that our model outperforms other popular models for this task without sophisticated architecture. We also demonstrate the effectiveness of transfer learning in natural language processing in the process.

Keyphrases: Fine-grained sentiment classification, Natural Language Processing, Sentiment Classifier, Transfer Learning, computational linguistic, language model, machine learning, neural network, pretrained bert model, pretraining, sentiment classification, stanford sentiment treebank, word embedding, word vector

@booklet{EasyChair:1762,
  author    = {Manish Munikar and Sushil Shakya and Aakash Shrestha},
  title     = {Fine-grained Sentiment Classification using BERT},
  howpublished = {EasyChair Preprint 1762},
  year      = {EasyChair, 2019}}