Prediction of Bitcoin prices using Twitter Data and Natural Language Processing

dc.contributor.author

Wong, Eugene Lu Xian

dc.date.accessioned

2021-12-17T02:10:00Z

dc.date.available

2021-12-17T02:10:00Z

dc.date.issued

2021-12-16

dc.date.updated

2021-12-17T02:09:59Z

dc.description.abstract

The influence of social media platforms like Twitter had long been perceived as a bellwether of Bitcoin Prices. This paper aims to investigate if the tweets can be modeled using two different approaches, namely, the Naïve Bayes and LSTM models, to compute the sentiment scores in order to predict the Bitcoin price signal. Through the experiments conducted, the LSTM model indicates some degree of predictive advantage compared to the Naïve Bayes model.

dc.identifier.uri

https://hdl.handle.net/10161/24081

dc.subject

NLP

dc.subject

Natural Language Processing

dc.subject

LSTM

dc.subject

Naïve Bayes

dc.subject

Deep Learning

dc.subject

Discriminative Models

dc.subject

Generative Models

dc.title

Prediction of Bitcoin prices using Twitter Data and Natural Language Processing

dc.type

Report

duke.contributor.orcid

Wong, Eugene Lu Xian|0000-0003-2074-7374

pubs.organisational-group

Student

pubs.organisational-group

Duke

pubs.publication-status

Submitted

Files

Original bundle

Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
Prediction of Bitcoin prices using Twitter Data and Natural Language Processing.pdf
Size:
1.51 MB
Format:
Adobe Portable Document Format
Description:
Submitted version