Analisis Sentimen pada Ulasan pengguna Aplikasi Bibit Dan Bareksa dengan Algoritma KNN

Putra, Aluisius Dwiki Adhi; Juanita, Safitri

doi:10.35957/jatisi.v8i2.962

Cited by 32 publications

(34 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Other studies conducted by Hidayat & Syafrullah (2017) [5] and Darwis et al (2021) [6] revealed that Naïve Bayes can be effectively used for sentiment analysis, yielding high accuracy results. Additionally, Putra & Juanita's research (2021) [7] achieved an accuracy of above 85% for user sentiment towards two different applications.…”

Section: Introductionmentioning

confidence: 93%

Hoax News Analysis for the Indonesian National Capital Relocation Public Policy with the Support Vector Machine and Random Forest Algorithms

et al. 2023

View full text Add to dashboard Cite

The decision of the Indonesian government to relocate the nation's capital outside Java to the North Penajam Paser Regency has sparked controversy and misinformation on social media platforms. While sentiment analysis studies have been conducted on this topic, no research has yet analyzed the issue of hoaxes related to the relocation of the national capital. This study aims to fill this gap by analyzing hoaxes related to the relocation of the Indonesian national capital on Twitter. The study utilizes data crawling, filtering with Hoax Booster Tools (HBT) ASE, data labeling, preprocessing, and TF-IDF weighting. The data is then classified using Support Vector Machine (SVM) and Random Forest (RF) algorithms, and the results of both algorithms are compared. The study found that 85% of tweets had a positive sentiment and 15% had a negative sentiment. Furthermore, the SVM algorithm outperformed the RF algorithm with an accuracy of 95.24% compared to 86.90%. This study contributes to the understanding of the hoax issues related to the relocation of the Indonesian state capital and provides recommendations for government policies to address community concerns.

show abstract

Section: Introductionmentioning

confidence: 93%

Hoax News Analysis for the Indonesian National Capital Relocation Public Policy with the Support Vector Machine and Random Forest Algorithms

et al. 2023

View full text Add to dashboard Cite

show abstract

“…K-nn dilakukan dengan mencari kelompok k objek dalam data training yang paling dekat (mirip) dengan objek pada data baru atau data testing. Ada banyak cara untuk mengukur jarak kedekatan antara data baru dengan data lama (data training), diantaranya euclidean distance dan manhattan distance (city block distance), yang paling sering digunakan adalah euclidean distance [15]- [17]: 2 (1)…”

Section: Algoritma K-nearest Neighborunclassified

Penerapan Algoritma K-Nearest Neighbor Untuk Klasifikasi Warga Penerima Bantuan Sosial

Pahrudin

Harianto

2022

bits

View full text Add to dashboard Cite

Social Assistance (BanSos) is a government program intended for lower-middle families. Social assistance is assistance given to the community, especially the lower middle class, which is not continuous and selective. Many types of social assistance are provided by the government with the aim of prospering and helping the community's economy. However, the problem that occurs is that there are still many people who receive social assistance that are not people who deserve to receive social assistance, while the lower middle class who should receive social assistance are neglected and do not receive the social assistance. It should be for the distributor or the kelurahan to form groups for residents who are entitled to receive social assistance. The process of grouping the recipients of social assistance can be done by processing the data of residents who have the right to receive the social assistance. The data processing can be done by using data mining. One of the algorithms that can be used to solve problems in data mining is the K-Nearest Neighbor algorithm. After carrying out the overall process with a value of K = 5, it was found that the new data from residents was declared eligible to receive social assistance

show abstract

“…Penelitian lainnya yang dilakukan oleh Aluisius Dwiki Adhi Putra dan Safitri Juanita pada tahun 2021 dengan hasil penelitian didapatkan modelling dari proses pengujian algoritma didapatkan tingkat akurasi sebesar 91,91% [25]. Ditahun yang sama juga dilakukan penelitian oleh Nanda Satria Halim Pratama, dkk dengan hasil penelitian yaitu penerapan dengan data mining dan algoritma k-nearest neighbor dimana tingkat akurasi hasil pengujian didapatkan sebesar 71% [26].…”

Section: Pendahuluanunclassified

Penerapan Data Mining Untuk Prediksi Perkiraan Hujan dengan Menggunakan Algoritma K-Nearest Neighbor

Nursobah

Lailiyah

Harpad

et al. 2022

bits

View full text Add to dashboard Cite

Rain is a condition where water droplets fall from clouds to the earth. In life, the presence of rain is highly anticipated, rain can help people who have a profession as farmers. Rain that occurs on a large scale will really provide obstacles for the community, in addition to hampering activities or activities especially those carried out on outdoor rain can also cause disaster for the community in the form of flooding. Estimating rain for the community is very important, knowing whether it will rain or not can make it easier for the community to anticipate the possibilities that may occur due to rain. However, in the process of delivering forecasts, there is often an uneven distribution of information and delays in conveying information to the public regarding whether or not rain will occur. The community should be able to independently predict whether or not rain will occur. Data processing should be done properly and correctly. Data mining is a way that can be done to assist in data processing. In this study, the settlement process will be carried out using the K-Nearest Neighbor (K-NN) algorithm. The results obtained show that the data testing decision is NO. In other words, data mining and the K-Nearest Neighbor algorithm can help the problem solving process

show abstract

Analisis Sentimen pada Ulasan pengguna Aplikasi Bibit Dan Bareksa dengan Algoritma KNN

Cited by 32 publications

References 6 publications

Hoax News Analysis for the Indonesian National Capital Relocation Public Policy with the Support Vector Machine and Random Forest Algorithms

Hoax News Analysis for the Indonesian National Capital Relocation Public Policy with the Support Vector Machine and Random Forest Algorithms

Penerapan Algoritma K-Nearest Neighbor Untuk Klasifikasi Warga Penerima Bantuan Sosial

Penerapan Data Mining Untuk Prediksi Perkiraan Hujan dengan Menggunakan Algoritma K-Nearest Neighbor

Contact Info

Product

Resources

About