The Impact of Social Media on the Prices of the Top Five Memecoins

Alghazi, Mohammed (2022) The Impact of Social Media on the Prices of the Top Five Memecoins. Undergraduate thesis, Dublin, National College of Ireland.

Preview

PDF (Bachelor of Science) Download (3MB) | Preview

Abstract

As of writing this report, Cryptocurrencies are talked about everywhere, we see ads, posts, read articles, and posts on social media that tell us to invest in this coin or that coin but in reality, what do we really know?

This project aims to analysis Tweets sent out from high-profile users who constantly tweet about low cap Crypto Memecoins such as SHIBA INU, DOGELON, DOGECOIN, MONACOIN, SAMPYEDCOIN. The introduction of the project explains the background, aims, and technology used. The project report briefly explains the complexity of the data and how each dataset was obtained, why the datasets obtained are suitable for the project, and how the datasets complement each other including the characteristics of the dataset, and visualisation tools used. The next phase is choosing the methodology and from early on in the planning phase the KDD methodology was the chosen methodology as the dataset was organised in the phases complementing the KDD methodology. These phases include the Selection of our data, pre-processing and data cleansing methods used, data transformation, data mining, and machine learning including LSTM which is used to predict the future prices of the coins mentioned above, and finally evaluation process. The following project report will contain a brief description of the analysis conducted and how the dataset extracted from the various APIs was used for pre-processing and data cleansing steps involved for implementations, data characteristics, and predictive analysis. Exploratory data analysis on why these certain methods were chosen for example why was the closing price attributes of each coin used for predictive analysis. The results will be explained in the results section of the report and will include all outputs, figures, graphs, and plots.

LSTM also known as Long-Short-Term Memory will be used to predict the prices of the so-called ‘Memecoins’ and will be using data obtained from the NLTK VADER Sentimental analysis polarity score to merge the data obtained from the Yahoo web scraper extraction of the mentioned crypto coins prices individually. Keras, TensorFlow, and Tenserboard were used for forecasting and data visualisation and UI interface, and various Python libraries such as Plotly for plots and graphs, NLTK for data cleansing, data pre-processing, and NLTK VADER were used for Sentiment analysis. All these libraries combined were used to produce a smooth development of the project.

Item Type:	Thesis (Undergraduate)
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science Q Science > QA Mathematics > Computer software T Technology > T Technology (General) > Information Technology > Computer software 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 > Bachelor of Science (Honours) in Computing
Depositing User:	Clara Chan
Date Deposited:	10 Aug 2022 12:09
Last Modified:	10 Aug 2022 16:45
URI:	https://norma.ncirl.ie/id/eprint/5712

Actions (login required)

View Item