Klasifikasi Sentimen Masyarakat Terhadap Pemerintah Terkait Penerapan Kebijakan New Normal Menggunakan Metode K-Nearest Neighbor
نویسندگان
چکیده
Abstrak - Instagram memiliki berbagai macam pengguna tanpa terkecuali pemerintah, akun instagram pemerintah sendiri fungsi sebagai salah satu media informasi bagi masyarakat untuk mengetahui berita terbaru. Pemerintah telah melakukan upaya mengurangi dan memutus rantai penyebaran virus covid-19, langkah yang diambil dalam menghadapi covid-19 dengan menerapkan kebijakan New Normal. Tujuan penulis dari penelitian ini adalah menghitung akurasi metode K-Nearest Neighbor pada klasifikasikan sentimen opini terkait penerapan new normal. Penelitian dilakukan melalui beberapa tahapan yaitu pengumpulan data dikelola pemerintah. Setelah itudata tersebut proses preprocessing. Lalu membuat model menggunakan word embedding FastText. Selanjutnya feature engineering improve menghasilkan fitur terbaik. Dataset berjumlah 4717 terbagi 1456 kelas pro, 1662 netral, 1599 kontra. Pengujian confusion matrix cara menguji latih uji sebanyak 3 kali perbandingan 90:10 nilai sebesar 60,169% k-40 80:20 60,16%, sedangkan terendah terdapat 70:30 58,12%.Kata kunci: Normal, Instagram, Klasifikasi, Sentimen, Abstract has various kinds of users without the exception government, government's own account a function as medium information for public to find out latest news. The government made efforts reduce and break chain spread COVID-19 virus, one steps taken by in dealing with implementing Normal policy. author's aim this study is calculate accuracy method classifying sentiments from opinion regarding implementation normal This research was conducted through several stages, namely collecting accounts managed government. After that, preprocessed. Then create using use produce best features. dataset amounted which divided into pro class data, neutral contra data. test carried testing training times comparison 90:10, value 60.169% at ratio 80:20, 60.16%, while lowest there that 58.12%.Keywords: Classification, Sentiment,
منابع مشابه
Aplikasi belajar membaca iqro' berbasis mobile
Abstrak Kemajuan Ilmu Pengetahuan dan Teknologi (IPTEK) hendaklah diikuti dengan Iman dan Takwa (IMTAK), sangat disayangkan, jika masih banyak masyarakat yang belum bisa membaca huruf hijaiyah yang merupakan dasar dari Al-Qur’an. Masyarakat sekarang telah disibukkan dengan berbagai aktipitas sehingga mereka sulit untuk belajar dengan Ustad atau Ustadza mengenai huruf hijaiyah. Untuk mengatasi m...
متن کاملDrought Monitoring and Prediction using K-Nearest Neighbor Algorithm
Drought is a climate phenomenon which might occur in any climate condition and all regions on the earth. Effective drought management depends on the application of appropriate drought indices. Drought indices are variables which are used to detect and characterize drought conditions. In this study, it was tried to predict drought occurrence, based on the standard precipitation index (SPI), usin...
متن کاملFast Approximate Nearest-Neighbor Search with k-Nearest Neighbor Graph
We introduce a new nearest neighbor search algorithm. The algorithm builds a nearest neighbor graph in an offline phase and when queried with a new point, performs hill-climbing starting from a randomly sampled node of the graph. We provide theoretical guarantees for the accuracy and the computational complexity and empirically show the effectiveness of this algorithm.
متن کاملUnsupervised K-Nearest Neighbor Regression
In many scientific disciplines structures in highdimensional data have to be found, e.g., in stellar spectra, in genome data, or in face recognition tasks. In this work we present a novel approach to non-linear dimensionality reduction. It is based on fitting K-nearest neighbor regression to the unsupervised regression framework for learning of low-dimensional manifolds. Similar to related appr...
متن کاملA New Distance-weighted k-nearest Neighbor Classifier
In this paper, we develop a novel Distance-weighted k -nearest Neighbor rule (DWKNN), using the dual distance-weighted function. The proposed DWKNN is motivated by the sensitivity problem of the selection of the neighborhood size k that exists in k -nearest Neighbor rule (KNN), with the aim of improving classification performance. The experiment results on twelve real data sets demonstrate that...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Jurnal nasional komputasi dan teknologi informasi
سال: 2022
ISSN: ['2620-8342', '2621-3052']
DOI: https://doi.org/10.32672/jnkti.v5i3.4455