Please use this identifier to cite or link to this item: https://dl.ucsc.cmb.ac.lk/jspui/handle/123456789/4528
Full metadata record
DC FieldValueLanguage
dc.contributor.authorDe Silva, T.H.M.-
dc.date.accessioned2021-08-11T09:01:34Z-
dc.date.available2021-08-11T09:01:34Z-
dc.date.issued2021-08-11-
dc.identifier.urihttp://dl.ucsc.cmb.ac.lk/jspui/handle/123456789/4528-
dc.description.abstractSocial information has emerged as a key component that drives growth in modern day society. The emergence of Web 2.0 and the global connectivity it brought has caused massive changes in news-reporting and journalism landscapes. Micro-blogging platforms play a key role in global news propagation today. There is a growing need to filter the noise and extract only credible or useful information from the unprecedented volume of data disseminated through these platforms every day. While there is a number of studies carried out on determining credibility of user generated content, there is no one accepted credibility analysis solution. The solutions presented in the past are also difficult to be used in real world applications owing to complexities. In this study, a new methodology for solving the issue of filtering credible information online through analysis of source credibility is proposed. Firstly, a thorough literature review on existing credibility assessment techniques and analysis approaches is conducted. Three user credibility ranking models which follow three slightly different approaches to rank users are proposed and implemented by using data acquired from Twitter social platform. Throughout a detailed study, it is shown that the analysis of perceived credibility of content authors — established through either human input or by assessing the available metadata — is helpful to identify highly credible users within these platforms. The findings from this study show that by preemptively identifying credible users in a network through network analysis methods, it is possible to curb misinformation on micro-blogging platforms.en_US
dc.language.isoenen_US
dc.titleA Network Analysis Based Credibility Ranking Model to Combat Misinformation on Twitteren_US
dc.typeThesisen_US
Appears in Collections:2020

Files in This Item:
File Description SizeFormat 
2017 MCS 022.pdf1.71 MBAdobe PDFView/Open


Items in UCSC Digital Library are protected by copyright, with all rights reserved, unless otherwise indicated.