Penerapan Analisis Sentimen pada Pengguna Twitter Menggunakan Metode K-Nearest Neighbor

Authors

  • Akhmad Deviyanto
  • Muhammad Didik Rohmad Wahyudi Informatics Engineering Department, Faculty of Science and Technology, State Islamic University (UIN) Sunan Kalijaga, Yogyakarta

DOI:

https://doi.org/10.14421/jiska.2018.31-01

Abstract

Abstract

This research is made to implement the KNN (K-Nearest Neighbor) algorithm for sentiment analysis Twitter about Jakarta Governor Election 2017. The object is 2000 data tweets in Indonesia collected from Twitter during Januari 2017 using Python package called Twitterscraper. The methode used in sentiment analysis system is KNN with TF-IDF term weighting and Cosine similarity measure. As the test result, the highest accuracy is 67,2% when k=5, the highest precision is 56,94% with k=5, and the highest recall 78,24% with k=15.

Keywords : K – Nearest Neighbor, Twitterscraper, TF-IDF, Cosine Similarity

 

Penelitian ini dibuat untuk mengimplementasikan algoritma KNN (K - Nearest Neighbor) dalam analisis sentimen pengguna Twitter tentang topik Pilkada DKI 2017. Data tweet yang digunakan adalah sebanyak 2000 data tweet berbahasa Indonesia yang dikumpulkan selama bulan Januari 2017 menggunakan package Python bernama Twitterscraper. Menggunakan algoritma KNN dengan pembobotan kata TF-IDF dan fungsi Cosine Similarity, akan dilakukan pengklasifikasian nilai sentimen ke dalam dua kelas : positif dan negatif. Dari hasil pengujian diketahui bahwa nilai akurasi terbesar adalah 67,2% ketika k=5, presisi tertinggi 56,94% ketika k=5, dan recall 78,24% dengan k=15.

Kata Kunci : K – Nearest Neighbor, Twitterscraper, TF-IDF, Cosine Similarity

Downloads

Published

2018-12-10

How to Cite

Deviyanto, A., & Wahyudi, M. D. R. (2018). Penerapan Analisis Sentimen pada Pengguna Twitter Menggunakan Metode K-Nearest Neighbor. JISKA (Jurnal Informatika Sunan Kalijaga), 3(1), 1–13. https://doi.org/10.14421/jiska.2018.31-01

Issue

Vol. 3 No. 1 (2018): Mei 2018

Section

Articles

License

Authors who publish with this journal agree to the following terms as stated in http://creativecommons.org/licenses/by-nc/4.0


a. Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.

b. Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.

c. Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work.