BiDAF model in sentiment analysis task

Abstract

Sentiment analysis is a critical job in natural language processing. Controlling and evaluating customer feedback on their goods is a task that companies are especially interested in. For reading comprehension problems including attention processes, the BiDAF model is developed. Attention processes have recently been expanded and effectively used for natural language processing problems. In this study, we use the BiDAF model to perform sentiment analysis on Amazon product evaluations at the sentence level. The BiDAF model is a multilayered processing model that reflects context at multiple levels and uses the BiLSTM model. Furthermore, we investigate the sentence's attention weight distribution using the attention mechanism. With a recall measure, the model achieves an accuracy of up to 99.9%. We discovered that the attention weights of important phrases are equivalent to, if not higher than, the attention weights of sentiment words in the sentence.

Keywords

• natural language processing
• lstm
• deep learning
• machine learning
• bidaf