Comparison of Tiktok User Sentiment Analysis Accuracy with Naïve Bayes and Support Vector Machine
Journal: International Journal of Advanced Trends in Computer Science and Engineering (IJATCSE) (Vol.12, No. 1)Publication Date: 2023-01-12
Authors : Parasian D.P Silitonga Mitra Hasibuan Z Situmorang Desinta Purba;
Page : 11-15
Keywords : Sentiment Analysis; TikTok; Naïve Bayes; Support Vector Machine; Twitter.;
Abstract
This study aims to compare the accuracy of the sentiment analysis of TikTok application users using the Naïve Bayes algorithm and the Support Vector Machine. The data set in this study comes from comments from Tiktok users on Twitter social media. Comparison of the accuracy of sentiment analysis in this study was carried out through three tests. The first test was conducted on 848 tweets, the second test used 957 tweet data, and the third test used 1,925 tweet data. Testing is done by dividing the data by 70% for training data and 30% for test data. The results showed that the accuracy of the Naive algorithm was 89.35% and 94.08% using the Support Vector Machine algorithm.
Other Latest Articles
- Network Management and Design for an Animation and Creative Studio
- Predicting the Assessment Course Performance of Criminology Students Using Data Mining
- The potential of Zai pit technology and Integrated soil fertility management to enhance crop productivity in semi-arid regions of Sub-Sahara Africa: A review
- Application of advanced molecular to select the variety of Bitter gourd (Momordica charantia .L) in Can Tho
- Analysis of Nitrogen and Phosphorus Content of Seaweed Codium sp. in Super Intensive Shrimp Pond Liquid Waste
Last modified: 2023-02-10 14:11:13