A Review of Different Word Embeddings for Sentiment Classification using Deep Learning

TL;DR

This paper reviews various word embedding techniques used in deep learning models for sentiment classification, comparing their effectiveness on Amazon reviews with two sentiment classes, Happy and Unhappy.

Contribution

It provides a comparative analysis of different word embedding strategies and discusses their impact on sentiment classification accuracy.

Findings

Certain embeddings outperform others in accuracy

Embedding choice affects model performance significantly

Insights on optimal embedding strategies for sentiment analysis

Abstract

The web is loaded with textual content, and Natural Language Processing is a standout amongst the most vital fields in Machine Learning. But when data is huge simple Machine Learning algorithms are not able to handle it and that is when Deep Learning comes into play which based on Neural Networks. However since neural networks cannot process raw text, we have to change over them through some diverse strategies of word embedding. This paper demonstrates those distinctive word embedding strategies implemented on an Amazon Review Dataset, which has two sentiments to be classified: Happy and Unhappy based on numerous customer reviews. Moreover we demonstrate the distinction in accuracy with a discourse about which word embedding to apply when.