Comparative study of traditional and deep learning algorithms on social media using sentiment analysis
No Thumbnail Available
Authors
Vedagiri, Greeshma
Issue Date
2022
Degree
MSc in Data Analytics
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
In recent years, there has been a significant increase in social media content. This study focuses on sentiment analysis of Twitter data. This research has been done to improve the accuracy of the sentiment analysis varying from various machine learning models to deep neural network models. Deep learning has recently demonstrated enormous success in the field of sentiment classification. The traditional models implemented include Logistic Regression, Naïve Bayes, Gradient Boost, Support vector machine and Random Forest and the deep learning models include CNN and RNN LSTM. A general-purpose deep learning ANN outperforms the traditional algorithms. The highest performance is achieved with the specialised LSTM deep learning classifier. The primary goal of this research is to highlight the capabilities of state-of-the-art deep learning architectures in building sentiment classifiers for Twitter data.