Multi-aspect Sentiment Analysis of Tiktok Application Usage Using FasText Feature Expansion and CNN Method

Among the many social media platforms that have emerged, TikTok is a platform has most significant number of subscribers compared to other platforms. However, not all reviews given by users are good and often found with slang real meaning, therefore sentiment analysis needed for these problems. These will later be analyzed according predetermined aspects, namely feature business content aspects based on written Google Play Store, using data crawling techniques pass preprocessing weighting stages. The method used Term Frequency-Inverse Document Frequency (TF-IDF). Then, process use Convolutional Neural Network (CNN) method, expansion carried out determine what words interrelated certain words. purpose this research analyze fastText expansion. highest accuracy result 87.74%.