Please use this identifier to cite or link to this item: https://rda.sliit.lk/handle/123456789/1545
Full metadata record
DC FieldValueLanguage
dc.contributor.authorSomasinghe, K.I.-
dc.date.accessioned2022-03-10T06:04:13Z-
dc.date.available2022-03-10T06:04:13Z-
dc.date.issued2021-09-
dc.identifier.urihttp://rda.sliit.lk/handle/123456789/1545-
dc.descriptionSupervisor: Mr. Prasanna S. Haddelaen_US
dc.description.abstractGeneration and spread of fake news have drastically increased with the growth of technology and advancement of online media platforms. Today, rather than using traditional resources to get information, most people rely on the internet and it has become a part of every individual’s life since this is a one of the simplest methods to acquire information on almost everything. This internet based media has become a source of sharing news and these sources are used by companies, political parties as well as social influencers etc. Fake news changes the perception of the viewers and diverts them from the reality. By analyzing fake news in Sinhala Language related to COVID-19 which is a disastrous situation to not only Sri Lanka but the whole world it would be a great advantage to notify people regarding fake news and the resources they use to spread fake news and reduce unethical sharing of news, to protect the authenticity of news that reaches people and the authenticity of the journalism field. This research presents an approach to analyze the effect of polarity in the sentiment of the news data and analyze how it affects towards fake news in Sinhala language using textual data. The proposed model uses natural language processing techniques such as sentiment analysis and machine learning algorithms such as Logistic Regression, Support Vector Machine, Naive Bayes.en_US
dc.language.isoenen_US
dc.titleSentiment Based Approach to Analyse Fake News Related to COVID 19 in Sri Lankaen_US
dc.typeThesisen_US
Appears in Collections:MSc 2021
MSc in IS

Files in This Item:
File Description SizeFormat 
Thesis Document - (K.I. Somasinghe_MS19816500).pdf
  Until 2050-12-31
16.49 MBAdobe PDFView/Open Request a copy
Thesis Document - (K.I. Somasinghe_MS19816500)_intro.pdf16.48 MBAdobe PDFView/Open


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.