Analisis Kinerja Support Vector Machine dalam Mengidentifikasi Komentar Perundungan pada Jejaring Sosial

Autor:	Wanayumini Wanayumini, Zakarias Situmorang, Ade Clinton Sitepu
Rok vydání:	2021
Předmět:	Training set Computer science business.industry Confusion matrix Filter (signal processing) Machine learning computer.software_genre Test (assessment) Support vector machine Social media Artificial intelligence business computer Test data
Zdroj:	JURNAL MEDIA INFORMATIKA BUDIDARMA. 5:475
ISSN:	2548-8368 2614-5278
DOI:	10.30865/mib.v5i2.2923
Popis:	Cyberbullying is the same as bullying but it is done through media technology. Bullying has often occurred along with the development of social media technology in society. Some technique are needed to filter out bully comments because it will indirectly affect the psychological condition of the reader, morover it is aimed at the person concerned. By using data mining techniques, the system is expected to be able to classify information circulating in the community. This research uses the Support Vector Machine (SVM) classification because the algorithm is good at performing the classification process. Research using about 1000 dataset comments. Data are grouped manually first into the labels "bully" and "not bully" then the data divide into training data and test data. To test the system capability, data is analyzed using confusion matrix. The results showed that the SVM Algorithm was able to classify with an level of accuracy 87.75%, 89% precision and 91% Recal. The SVM algorithm is able to formulate training data with level of accuracy 98.3%
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_________::0d21fc3392a972411c186671bd1de68b https://doi.org/10.30865/mib.v5i2.2923 Zobrazit plný text záznamu