Analisis Sentiment Akun Selebgram Berdasarkan Komentar Pengikut Menggunakan Metode Support Vector Machine (SVM)

Baskoro, Anggito Suryo (2023) Analisis Sentiment Akun Selebgram Berdasarkan Komentar Pengikut Menggunakan Metode Support Vector Machine (SVM). Undergraduate thesis, Politeknik Negeri Jember.

	Text (Abstract) Abstrak (Inggris).pdf - Submitted Version Available under License Creative Commons Attribution Share Alike. Download (329kB)
	Text (BAB I Pendahuluan) BAB I PENDAHULUAN.pdf - Submitted Version Available under License Creative Commons Attribution Share Alike. Download (461kB)
	Text (Daftar Pustaka) Daftar Pustaka.pdf - Submitted Version Available under License Creative Commons Attribution Share Alike. Download (298kB)
	Text (Tugas Akhir) Skripsi-Full(Tertanda tangan)_Non Lampiran.pdf Restricted to Registered users only Download (3MB) | Request a copy

Abstract

Instagram is a social media platform that provides communication services, both image, video, and text communication that provides a variety of personal and public information. As a communication medium, Instagram is used as a place to promote products and services through actors who have talent in the entertainment field called celebgrams. However, on the Instagram platform there are also celebgrams who are current because of their fame or virality. So that there are some celebgrams who are not good personalities and cannot be used as partners in doing business. Therefore, the author makes research related to sentiment analysis using Support Vector Machine in order to distinguish which celebgrams have positive sentiments and which ones have negative sentiments. In this study, researchers used 2500 datasets as training data and test data. The data is labeled to become training data. Based on the training data, classification is carried out using the Support Vector Machine (SVM) method and testing of the testing data is carried out. Based on the results of research conducted with confusion matrix testing, the highest accuracy was obtained in the 9:1 data comparison with an accuracy of 79.8%, while the classification with the comparison of training and test data 8:2 achieved an accuracy of 79.6%, for data comparison 7:3 achieved an accuracy level of 77% and data comparison with 6:4 reached 76%. It can be concluded that this research depends on the dataset and data division, so the level of accuracy in reading the test data is quite influential. For further research, additional methods such as lexicon-based features and confusion matrix are needed to increase the accuracy of the research. Keywords : Classification, Data Mining, Instagram, Support Vector Machine (SVM), Text Mining.

Actions (login required)

View Item