| Abstrak/Abstract |
Social media's tendency for instant reactions can be harnessed by companies and organizations to gather feedback. Nevertheless, effectively analyzing vast amounts of social media data poses a challenge. This issue can be addressed through the use of sentiment analysis technology. In this study, a sentiment analysis model is developed, employing Support Vector Machine (SVM) and Term Frequency-Inverse Document Frequency (TF-IDF) algorithms. The study aims to investigate the impact of feature engineering on TF-IDF, by incorporating statistical features into the SVM model's sentiment analysis performance. The experimental results reveal that the prediction model utilizing the conventional TFIDF approach achieves an SVM model with an F-measure score of 84.55%. Through the implementation of feature engineering, by adding max, min, and sum features, the model's performance shows a noticeable improvement, with an increase of 0.65% in the F-measure score difference. Consequently, the proposed feature engineering method positively enhances the capability of the SVM-based sentiment analysis model. To facilitate the acquisition of sentiment analysis results through user interfaces, the trained SVM model is integrated into a web-based sentiment analysis application. By doing so, the findings of this study contribute to streamlining the process of obtaining sentiment analysis results from social media data. |
