Text Analysis of Russia and Ukraine War

-, Alex Greenmount James (2023) Text Analysis of Russia and Ukraine War. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (1MB) | Preview
Preview	PDF (Configuration manual) Download (921kB) | Preview

Abstract

Sentiment analysis has a wide scope on various industrial applications. It has been used on applications including the user feedback support and product surveying. This project focuses on the various machine learning techniques used for sentiment analysis like Artificial Neural Network (ANN) and Random Forest (RF). The project starts with a collection of tweets based on the Ukraine and Russia war pattern using various hashtags and keywords. The collected data is being preprocessed to remove the unwanted hashtags and characters. The processed data is being tokenized and fed to the sentiment analysis tool under the Natural Language Toolkit (NLTK). The library will extract the features and achieve the polarity score and subjectivity of the tweets. The tweets are then arranged with the scores and polarity and fed for the neural networking and machine learning models created. For the machine learning libraries sklearn, keras, pandas, numpy, nltk etc are utilized. The machine learning algorithms used are Random Forest and ANN with Term Frequency-Inverse Document Frequency (TF-IDF). The data results are being compared with the NLTK reference. The data fed through the TF-IDF is given to both Random Forest and ANN systems. The results show that the ANN can have a better correlation with respect to the NLTK analysis. The ANN had a 10-percentage increase in the prediction capability compared to the Random Forest machine learning.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Bradford, Michael UNSPECIFIED
Subjects:	J Political Science > JZ International relations Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science P Language and Literature > P Philology. Linguistics > Computational linguistics. Natural language processing Z Bibliography. Library Science. Information Resources > ZA Information resources > ZA4150 Computer Network Resources > The Internet > World Wide Web > Websites > Online social networks T Technology > TK Electrical engineering. Electronics. Nuclear engineering > Telecommunications > The Internet > World Wide Web > Websites > Online social networks
Divisions:	School of Computing > Master of Science in Data Analytics
Depositing User:	Tamara Malone
Date Deposited:	12 May 2023 17:02
Last Modified:	12 May 2023 17:02
URI:	https://norma.ncirl.ie/id/eprint/6560

Actions (login required)

View Item