Analisis sentimen komentar Universitas Pelita Harapan pada TikTok menggunakan metode K-Nearest Neighbor

Wijaya, Robert (2024) Analisis sentimen komentar Universitas Pelita Harapan pada TikTok menggunakan metode K-Nearest Neighbor. Bachelor thesis, Universitas Peliita Harapan.

Preview	Text (Title) Title.pdf Available under License Creative Commons Attribution Non-commercial Share Alike. Download (29kB) | Preview
Preview	Text (Abstract) Abstract.pdf Available under License Creative Commons Attribution Non-commercial Share Alike. Download (321kB) | Preview
Preview	Text (ToC) ToC.pdf Available under License Creative Commons Attribution Non-commercial Share Alike. Download (749kB) | Preview
Preview	Text (Chapter1) Chapter1.pdf Available under License Creative Commons Attribution Non-commercial Share Alike. Download (839kB) | Preview
	Text (Chapter2) Chapter2.pdf Restricted to Registered users only Available under License Creative Commons Attribution Non-commercial Share Alike. Download (1MB)
	Text (Chapter3) Chapter3.pdf Restricted to Registered users only Available under License Creative Commons Attribution Non-commercial Share Alike. Download (2MB)
	Text (Chapter4) Chapter4.pdf Restricted to Registered users only Available under License Creative Commons Attribution Non-commercial Share Alike. Download (1MB)
	Text (Chapter5) Chapter5.pdf Restricted to Registered users only Available under License Creative Commons Attribution Non-commercial Share Alike. Download (181kB)
Preview	Text (Bibliography) Bibliography.pdf Available under License Creative Commons Attribution Non-commercial Share Alike. Download (583kB) | Preview
	Text (Appendices) Appendices.pdf Restricted to Repository staff only Available under License Creative Commons Attribution Non-commercial Share Alike. Download (5MB)

Abstract

Di era digital yang sedang berkembang, media sosial, khususnya TikTok, telah menjadi platform penting untuk berbagi informasi dan komunikasi, termasuk oleh institusi pendidikan seperti Universitas Pelita Harapan (UPH). Penggunaan TikTok di UPH menghasilkan beragam komentar yang memerlukan pengelolaan efektif, mendorong penelitian ini untuk mengembangkan analisis sentimen menggunakan algoritma K-Nearest Neighbor (KNN). Penelitian ini bertujuan untuk mengatasi dua masalah utama: menganalisa tingkat akurasi penggunaan algoritma K-Nearest Neighbor dalam analisis sentimen terhadap kalimat komentar dan mengukur kinerja algoritma K-Nearest Neighbor dalam menghitung hasil validasi pada kalimat komentar. Penelitian ini menggunakan metode KNN dengan dataset berjumlah 1213 data dari tahun 2021 sampai 2023 yang memiliki kata kunci terkait UPH dari konten platform TikTok. Penelitian ini dikelola dan dilakukan di Google Colab dengan bahasa pemrograman python. Berdasarkan hasil data training dan data testing didapatkan accuracy sebesar 91% dengan precision sebesar 93%, recall sebesar 91% dan f-1 score sebesar 92%. Dari hasil performa algoritma KNN, dapat disimpulkan metode KNN dapat mengklasifikasikan sentimen komentar. / 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 analysis 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 analysis of comment sentences and measuring the performance of the K-Nearest Neighbor algorithm in calculating validation 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.

Actions (login required)

View Item