Muflih, Hilmy Zhafran
Unknown Affiliation

Published : 3 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 3 Documents
Search

Penerapan Business Intelligence Untuk Analisis Kematian di Indonesia Tahun 2000-2022 Abdillah, Allif Rizki; Muflih, Hilmy Zhafran; Pranata, Ananda Bagas; Hasan, Firman Noor
Jurnal Informatika Vol 10, No 2 (2023): October 2023
Publisher : Universitas Bina Sarana Informatika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31294/inf.v10i2.16569

Abstract

Kematian terus menerus terjadi dan sebagai manusia biasa kematian tidak dapat dihindari. Seiring berjalannya waktu, jenis kematian juga semakin bertambah khususnya di Indonesia, faktor kematian yang disebabkan oleh bencana alam, bencana non-alam atau penyakit dan bencana sosial yang di dalamnya memuat jenis-jenis penyebab kematian juga semakin bertambah jenis kematian yang baru. Seperti kemarin Indonesia mendapatkan jenis kematian baru yaitu covid-19 yang menelan ratusan ribu korban jiwa. Tujuan dari penelitian ini untuk mengidentifikasi serta menganalisa penyebab kematian yang ada di Indonesia dengan rentang tahun 2000 sampai tahun 2022. Peneliti memperoleh dataset untuk penelitian ini dari situs www.kaggle.com untuk dibuat data visualisasinya dengan mengimplementasikan Business Intelligence menggunakan platform Tableau dalam pembuatan visualisasinya. Hasil dari penelitian ini adalah laporan berupa dashboard yang di dalamnya memuat Total kematian berdasarkan kategori, total kematian beserta jenis kematiannya, total kematian per tahun dari tahun 2000 sampai tahun 2022, dll. Sehingga dapat memudahkan proses pengambilan keputusan. Kesimpulan dari penelitian ini yaitu terdapat 777.076 korban yang meninggal karena bencana non alam atau penyakit, terdapat 185.290 korban yang meninggal akibat bencana alam dan 261 korban yang meninggal akibat bencana sosial. Total kematian di Indonesia pada rentang tahun 2000 sampai tahun 2022 sejumlah 962.627. Death keeps happening and as an ordinary human being death cannot be avoided. Over time, the types of death have also increased, especially in Indonesia, the factor of death caused by natural disasters, non-natural disasters or diseases and social disasters which contain the types of causes of death. Like yesterday, Indonesia got a new type of death, namely Covid-19 which claimed hundreds of thousands of lives. The purpose of this research is to identify and analyze the causes of death in Indonesia from 2000 to 2022. Researchers obtained the dataset for this study from the website www.kaggle.com to make data visualization by implementing Business Intelligence using the Tableau platform in making the visualization. The results of this study are reports in the form of dashboards which contain total deaths by category, total deaths and types of deaths, total deaths per year from 2000 to 2022, etc. So that it can facilitate the decision-making process. The conclusion of this study is that there were 777,076 victims who died due to non-natural disasters or diseases, there were 185,290 victims who died as a result of natural disasters and 261 victims who died as a result of social disasters. The total number of deaths in Indonesia between 2000 and 2022 is 962,627.
Analisis Sentimen Terhadap Pelayanan TransJakarta Berdasarkan Tweets Menggunakan Metode Naïve Bayes Classifier Muflih, Hilmy Zhafran; Hasan, Firman Noor
KLIK: Kajian Ilmiah Informatika dan Komputer Vol. 4 No. 6 (2024): Juni 2024
Publisher : STMIK Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/klik.v4i6.1927

Abstract

The high use of private transportation in Indonesia, especially in the Jakarta area, causes several impacts, one of which is traffic jams. This congestion condition can be reduced by public transportation. It is hoped that public transportation can now reduce the level of congestion in Jakarta. One of the public transportation in Jakarta is TransJakarta. TransJakarta is a form of transportation that can carry a relatively large number of passengers and TransJakarta offers various facilities to users, such as the availability of priority seating, stops that are quite comfortable, comfortable conditions on the bus plus low prices so that it gets various responses from users who led researchers to conduct research on the views of TransJakarta users regarding TransJakarta services, whether TransJakarta users' responses were positive or negative. The purpose of this research is to understand whether users are satisfied or not with the services provided by TransJakarta. The method used in the research is the Naïve Bayes Classifier algorithm which is used to carry out the sentiment analysis process regarding TransJakarta services with the help of the RapidMiner application. The data collected by researchers was 773 tweet data obtained via social media X to be used as a dataset. The results of sentiment analysis from the Naïve Bayes Classifier algorithm obtained 80.6% or 623 negative sentiments and 19.4% or 150 positive sentiments from 773 datasets. The results of the confusion matrix evaluation obtained an accuracy value of 73.96%.
ANALISIS SENTIMEN TERHADAP ULASAN PENGGUNAAN SHOPEE MELALUI TWEET PADA TWITTER MENGGUNAKAN ALGORITMA NAÏVE BAYES Muflih, Hilmy Zhafran; Al Assyam, Hafizh Dhery; Pangestu, Faisal Akbar; Kamayani, Mia
Jurnal Teknik Informatika dan Komputer Vol. 2 No. 2 (2023): Jurnal Teknik Informatika dan Komputer
Publisher : Universitas Muhammadiyah Prof. DR. HAMKA

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22236/jutikom.v2i2.12199

Abstract

The increasing use of the internet among the public is because it is a means to carry out various activities, one of which is buying and selling online or known as e-commerce. One of the largest e-commerce in Indonesia is Shopee. Shopee offers various features for its users. The large number of shopee users results in the large number of responses given to shopee, so the researcher wants to carry out a sentiment analysis process regarding user responses to shopee, whether the response of shopee users is negative or positive. The responses or opinions of Shopee users are taken from tweets in the Twitter application. Tweets typed and written and published by Twitter users about shopee. In this study, researchers used the RapidMiner application to collect tweets data from Twitter users and to apply the Naïve Bayes algorithm. The researcher collected 200 data regarding shopee from Twitter. The results obtained from sentiment analysis using the Naïve Bayes algorithm get 78% negative sentiment and 22% positive sentiment from 200 datasets. The process of testing the Naïve Bayes algorithm using the confusion matrix obtains an accuracy value of 77.50%.