Topic Based Sentiment Analysis Using Deep Learning

TL;DR

This paper presents a deep learning approach for topic-based sentiment analysis on Twitter data, involving custom word embeddings and a two-phase process to improve sentiment prediction accuracy conditioned on topics.

Contribution

It introduces a novel two-tier method using custom word embeddings for more accurate topic-conditioned sentiment analysis in social media data.

Findings

Custom embeddings outperform state-of-the-art in standard classifiers

The approach identifies influential words for each topic

Enhanced sentiment prediction accuracy for Twitter data

Abstract

In this paper , we tackle Sentiment Analysis conditioned on a Topic in Twitter data using Deep Learning . We propose a 2-tier approach : In the first phase we create our own Word Embeddings and see that they do perform better than state-of-the-art embeddings when used with standard classifiers. We then perform inference on these embeddings to learn more about a word with respect to all the topics being considered, and also the top n-influencing words for each topic. In the second phase we use these embeddings to predict the sentiment of the tweet with respect to a given topic, and all other topics under discussion.