<![CDATA[In the evolving digital era, social media, particularly TikTok, has become a pivotal platform for information sharing and communication, including by educational institutions such as Universitas Pelita Harapan (UPH). The use of TikTok at UPH has generated diverse comments that require effective management, prompting this research to develop sentiment by using the K-Nearest Neighbor (KNN) algorithm. This study aims to address two main issues: analyzing the accuracy of the K-Nearest Neighbor algorithm in sentiment of comment sentences and measuring the performance of the K-Nearest Neighbor algorithm in calculating analysis results on comment sentences. This research employs the KNN method with a dataset of 1213 entries from 2021 to 2023 containing keywords related to UPH from TikTok platform content. The study is managed and conducted on Google Colab using the Python programming language. Based on the results of training and testing data, an accuracy of 91% is obtained, with precision at 93%, recall at 91%, and an f-1 score of 92%. From the performance of the KNN algorithm, it can be concluded that the KNN method can classify sentiment in comments]]>
Copyrights © 2024
