Institutional Repository of Vilnius University
Twitter žinučių emocinės nuotaikos įtakos Bitcoin kainai analizė /
Abstract
dc:descriptionThis study examines the relationship between Twitter sentiment and Bitcoin prices, aiming to determine whether there is a significant correlation that could be used to predict price changes. Using Pearson, Kendall, and Spearman cross-correlation methods, the analysis revealed correlations of varying strength between the data sets, but no relationship was strong enough to establish a clear link between Twitter sentiment and Bitcoin prices. When investigating the impact of lag and the correlation between the derivatives of the data sets, no strong or significant correlations were found. Data normalization and the examination of derivatives of cryptocurrency prices and sentiment scores also did not yield unequivocal results. While some minor correlations were observed, the overall trend did not show a reliable or consistent relationship between the two data sets. The study acknowledges potential limitations in methodology and scope, and suggests further research with a larger data set and additional sentiment analysis techniques. In conclusion, the study found a minor correlation between Twitter sentiment and Bitcoin prices, but it was not significant enough to make a definitive conclusion or use for predictive purposes.
Degree
thesis:*- Grantor dc:publisher
- Institutional Repository of Vilnius University
- Year dc:date
- 2023
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Jonaitis, Karolis,
Rights
dc:rights- Statement dc:rights
-
- info:eu-repo/semantics/openAccess
- Language dc:language
- lit
Identifiers
dc:identifier.*- Repository record dc:identifier
- https://repository.vu.lt/VU:ELABAETD192842715&prefLang=en_US