Twitter sentiment analysis with deep learning technique for self-driving cars
Authors
Sinha, Ashish
Issue Date
2019
Degree
MSc in Data Analytics
MSc
MSc
Publisher
Dublin Business School
Rights holder
Rights
Items in eSource are protected by copyright. Previously published items are made available in accordance with the copyright policy of the publisher/copyright holder.
Abstract
Social media is an evolving platform for influencers, decision-makers and the common people to express their opinions. Social listening has changed the approach of brands when it comes to promoting and determining the market value of their product. Sentiment analysis has become a vital tool to understand the flow of the market via social media. Twitter is one of the leading platforms in this context. With its massive user base and significant amount of data, it has proved to be a goldmine for such a task. In this paper, we will explore and study how deep learning techniques impact the classification and gain insight on the sentiment of Self-Driving Cars. It combines word embedding and deep neural network to accomplish the task. The outcome is a multi-class sentiment classification. Based on the result, we can determine that the model achieved an accuracy of 70% and efficiently answered our research questions.