Predicting Optimal Cryptocurrency using Social Media Sentimental Analysis

Sahal, Ravi (2023) Predicting Optimal Cryptocurrency using Social Media Sentimental Analysis. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (1MB) | Preview
Preview	PDF (Configuration manual) Download (3MB) | Preview

Abstract

Interest in cryptocurrencies has grown significantly recently on social media. Particular focus has been placed on these sorts of price adjustments. Behavioral sciences and associated academic publications have shown a significant correlation between social media and changes in cryptocurrency pricing. Smaller cryptocurrencies are particularly affected since mentions made on Twitter may have a big impact on them. Many machine learning and deep learning models were employed in recent research on cryptocurrencies to predict or anticipate the price of the coin after conducting sentiment classification. This analysis may help investors choose the best cryptocurrency. This research objective is to provide a system model for identifying the most profitable cryptocurrencies by examining data from social media platforms like Twitter. Several aspect-based sentiment models are constructed depending on the gaps that have been found. The model integrated recurrent neural network such as basic RNN and biLSTM(Bidirectional Long Short-Term Memory) with embeddings from language model (ELMo) embedding to conduct contextually-based emotional analysis on the data. As a consequence, The accuracy of the biLSTM model was 86.30% and it worked effectively when combined with the ELMo.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Mulwa, Catherine UNSPECIFIED
Subjects:	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 H Social Sciences > HG Finance > Money > Currency 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:	25 May 2023 14:27
Last Modified:	25 May 2023 14:27
URI:	https://norma.ncirl.ie/id/eprint/6643

Actions (login required)

View Item