Institutional Repository of Vilnius University
Socialinio tinklo „Facebook" puslapių populiarumo vertinimo tyrimas, paremtas mašininio mokymosi metodais /
Abstract
dc:descriptionThis paper presents a study of the popularity of Facebook pages. The popularity was assessed by analyzing the content strategies of the pages. Content strategies were analyzed based on the duration of the published videos, the subject matter of the content being created, publication time and day of the week. The analysis was conducted by investigating three Facebook pages that published over 8,000 videos. Topic modeling, statistical hypothesis testing and video clustering were performed in this study. Topic modeling was performed using Latent Dirichlet Allocation, the Kruskal-Wallis and Dunn tests were used to test the hypotheses and videos clustering was performed using K-means and hierarchical clustering methods. Carrying out topic modeling, 5 topics were formed, which allowed to better understand published content. After analyzing the data, the strategies of the published content were examined, the statistical hypotheses were tested and the strategies features of the published content of the pages were identified.
Degree
thesis:*- Grantor dc:publisher
- Institutional Repository of Vilnius University
- Year dc:date
- 2022
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Eirošius, Dominykas,
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:ELABAETD146237944&prefLang=en_US