Sentiment classification of Sinhala content in social media

dc.contributor.authorJayasuriya, Pradeep
dc.contributor.authorEkanayake, Sarith
dc.contributor.authorMunasinghe, Ranjiva
dc.contributor.authorKumarasinghe, Bihara
dc.contributor.authorWeerasinghe, Isuru
dc.contributor.authorThelijjagoda, Samantha
dc.date.accessioned2021-07-05T16:59:39Z
dc.date.available2021-07-05T16:59:39Z
dc.date.issued2020
dc.description.abstractIn this study, we focus on the classification of Sinhala social media sentiments into positive and negative classes for a particular domain (sports). We have employed machine learning algorithms and lexicon-based sentiment classification methods. We also consider a hybrid approach by constructing an ensemble classifier in which we combine Machine Learning and Lexicon based methods. For individual methods, machine learning algorithms performed best in terms of accuracy. The ensemble classifier was able to improve performance further.en_US
dc.identifier.citationJayasuriya, Pradeep, Ekanayake, Sarith, Munasinghe, Ranjiva, Kumarasinghe, Bihara , Weerasinghe, Isuru and Thelijjagoda, Samantha (2020). Sentiment classification of Sinhala content in social media. In : International Research Conference on Smart Computing and Systems Engineering, 2020. Department of Industrial Management, Faculty of Science, University of Kelaniya, Sri Lanka, p.136.en_US
dc.identifier.urihttp://repository.kln.ac.lk/handle/123456789/23086
dc.publisherDepartment of Industrial Management, Faculty of Science, University of Kelaniya, Sri Lankaen_US
dc.subjectMachine Learning, Natural Language Processing, Sentiment Analysis, Social Media, Supervised Learningen_US
dc.titleSentiment classification of Sinhala content in social mediaen_US

Files

Original bundle

Now showing 1 - 1 of 1
Thumbnail Image
Name:
21.pdf
Size:
899.73 KB
Format:
Adobe Portable Document Format
Description:

License bundle

Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.71 KB
Format:
Item-specific license agreed upon to submission
Description: