Claim Missing Document
Check
Articles

Found 24 Documents
Search

Perancangan Program Penilaian Peserta Pusdiklat Pada BPSDM Kemendagri Jakarta Oktaviani, Anggi; Muthia, Dinda Ayu; Susanti, Melan; Sujatmiko, Fredericus Panji
Sinkron : jurnal dan penelitian teknik informatika Vol. 3 No. 1 (2018): SinkrOn Volume 3 Nomor 1, Periode Oktober 2018
Publisher : Politeknik Ganesha Medan

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (437.112 KB)

Abstract

Badan Pengembangan Sumber Daya Manusia (BPSDM) Kemendagri bertugas untuk mengembangakan sumber daya manusia supaya dapat mempelancar pelaksanaan tugas yang diberikan oleh pemerintah dan dapat memberikan pelayanan kepada masyarakat. Maka dari itu BPSDM Kemendagri banyak melakukan kegiatan Pelaksanan Pendidikan dan Pelatihan (DIKLAT) untuk aparatur pemerintah sesuai dengan undang-undang. Dalam instansi BPSDM Kemendagri, Diklat merupakan sarana yang diberikan untuk mengembangkan kompetensi yang dimiliki aparatur pemerintah. Dalam proses Diklat terdapat penilaian yang harus diberikan oleh pengajar, akan tetapi dalam proses penginputan nilai yang dilakukan oleh staff masih mengunakan Microsoft Excel dan jika peserta ingin melihat nilai sementara, peserta harus mendatangi staf. Tujuan dari penelitian ini adalah membuat web penilaian peserta pusdiklat, agar mempermudah peserta dalam mencari informasi nilai sementara dan dapat membantu meringankan kinerja staf dalam menginput nilai peserta agar lebih efektif dan efisien
Perancangan Program Penilaian Peserta Pusdiklat Pada BPSDM Kemendagri Jakarta Oktaviani, Anggi; Muthia, Dinda Ayu; Susanti, Melan; Sujatmiko, Fredericus Panji
Sinkron : jurnal dan penelitian teknik informatika Vol. 3 No. 1 (2018): SinkrOn Volume 3 Nomor 1, Periode Oktober 2018
Publisher : Politeknik Ganesha Medan

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (428.599 KB)

Abstract

Badan Pengembangan Sumber Daya Manusia (BPSDM) Kemendagri bertugas untuk mengembangakan sumber daya manusia supaya dapat mempelancar pelaksanaan tugas yang diberikan oleh pemerintah dan dapat memberikan pelayanan kepada masyarakat. Maka dari itu BPSDM Kemendagri banyak melakukan kegiatan Pelaksanan Pendidikan dan Pelatihan (DIKLAT) untuk aparatur pemerintah sesuai dengan undang-undang. Dalam instansi BPSDM Kemendagri, Diklat merupakan sarana yang diberikan untuk mengembangkan kompetensi yang dimiliki aparatur pemerintah. Dalam proses Diklat terdapat penilaian yang harus diberikan oleh pengajar, akan tetapi dalam proses penginputan nilai yang dilakukan oleh staff masih mengunakan Microsoft Excel dan jika peserta ingin melihat nilai sementara, peserta harus mendatangi staf. Tujuan dari penelitian ini adalah untuk mengetahui apakah metode waterfall dapat menyelesaikan masalah mengenai pembuatan web penilaian peserta pusdiklat. Sehingga mempermudah peserta dalam mencari informasi nilai sementara dan dapat membantu meringankan kinerja staf dalam menginput nilai peserta agar lebih efektif dan efisien
Online Student Admission Application at SMK Al-Basyariah Bojong Gede Muthia, Dinda Ayu; Ramadhani, Andini; Kurniawan, Adi; Irfansyah, Raka
Sinkron : jurnal dan penelitian teknik informatika Vol. 3 No. 2 (2019): SinkrOn Volume 3 Number 2, April 2019
Publisher : Politeknik Ganesha Medan

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (376.302 KB) | DOI: 10.33395/sinkron.v3i2.10034

Abstract

Acceptance of new students is one of the processes that exist in educational institutions every year, the number of prospective students who register causes the new student admission committee cannot manage everything properly so that it is less effective in handling it. In this study, the new student admission system used by Al-Basyariah Vocational School Bojong Gede still uses the system manually, which still uses paper records, so that minimal damage and even data loss occurs. Making a new student registration information system is expected to facilitate new prospective students in registering by saving time and costs compared to coming directly to school and with the information system of new student admissions, it is expected to help and simplify the processing of students in this school.
Opinion Mining Pada Review Produk Kecantikan Menggunakan Algoritma Naïve Bayes Ayu Muthia, Dinda
Jurnal Sistem Informasi Vol 7 No 1 (2018)
Publisher : STMIK ANTAR BANGSA

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (710.595 KB)

Abstract

Abstract— In recent years many sentiment analysis and opinion mining applications have been developed to analyze opinions, feelings and attitudes about products, brands, and news, etc. These applications mine opinions from different sources like online forums and news sites and from movie, product and hotel reviews. The Naïve Bayes algorithm is a popular machine learning technique for opinion mining, as it is very simple, efficient and performs well on many domains. However, Naïve Bayes has a deficiency that is very sensitive to features that are too numerous, resulting in low classification accuracy. Therefore, this research used Genetic Algorithm feature selection method to improve the accuracy of Naïve Bayes. This study produces text classification in the form of positive or negative from beauty product reviews. Measurements based on Naive Bayes accuracy before and after the addition of feature selection methods. The evaluation was performed using 10 fold cross validation. Measurement accuracy is measured with confusion matrix and ROC curve. The results showed an increase in the accuracy of Naïve Bayes from 65.50% to 83%.Intisari— Dalam beberapa tahun terakhir banyak analisis sentimen dan aplikasi opinion mining telah dikembangkan untuk menganalisis pendapat, perasaan dan sikap tentang produk, merek, dan berita, dan sejenisnya. Aplikasi ini menambang pendapat dari berbagai sumber seperti forum online dan situs berita dan dari ulasan film, produk dan hotel. Algoritma Naïve Bayes adalah teknik machine learning yang populer untuk opinion mining, karena sangat sederhana, efisien dan memiliki performa yang baik pada banyak domain. Namun, Naïve Bayes memiliki kekurangan yaitu sangat sensitif pada fitur yang terlalu banyak, yang mengakibatkan akurasi klasifikasi menjadi rendah. Oleh karena itu, dalam penelitian ini digunakan metode pemilihan fitur Genetic Algorithm agar bisa meningkatkan akurasi Naïve Bayes. Penelitian ini menghasilkan klasifikasi teks dalam bentuk positif atau negatif dari review produk kecantikan. Pengukuran berdasarkan akurasi Naive Bayes sebelum dan sesudah penambahan metode pemilihan fitur. Evaluasi dilakukan menggunakan 10 fold cross validation. Pengukuran akurasi diukur dengan confusion matrix dan kurva ROC. Hasil penelitian menunjukkan peningkatan akurasi Naïve Bayes dari 65.50% menjadi 83%.Kata Kunci— Algoritma, Naive Bayes, Review, Opinion Mining
OPINION MINING PADA REVIEW BUKU MENGGUNAKAN ALGORITMA NAÏVE BAYES Dinda Ayu Muthia
JURNAL TEKNIK KOMPUTER AMIK BSI Vol 2, No 1 (2016): Jurnal Teknik Komputer AMIK BSI
Publisher : Universitas Bina Sarana Informatika

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1058.864 KB) | DOI: 10.31294/jtk.v2i1.357

Abstract

Abstract — In the era of widespread use of the internet today, thenumber of consumers who wrote the opinion and experience ofonline continues to increase. Read the review as a whole can betime consuming, however, if only a few reviews that read, then theevaluation will be biased. Sentiment analysis aims to address thisproblem by automatically classifying user review be positive ornegative opinion. Naïve Bayes classifier is a popular machinelearning techniques for text classification, because it is very simple,efficient and has a good performance in many domains. However,Naïve Bayes has the disadvantage that is very sensitive to featuretoo much, resulting in a classification accuracy becomes low.Therefore, in this study used the integration method of featureselection, namely Information gain and Genetic algorithm in orderto improve the accuracy of Naïve Bayes classifier. This researchresulted in the classification of the text in the form of positive ornegative review of the book. Measurement is based on the accuracyof Naive Bayes before and after the addition of feature selectionmethods. The evaluation was done using a 10 fold cross validation.While the measurement accuracy is measured by confusion matrixand ROC curves. The results showed an increase in the accuracy ofNaïve Bayes from 78.50% to 84.50%.
ONLINE COURSE REGISTRATION APPLICATION AT EDEN EVERYDAY ENGLISH BOGOR Dinda Ayu Muthia; Yetrivo Efendy
Jurnal Teknoinfo Vol 15, No 2 (2021): Juli
Publisher : Universitas Teknokrat Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33365/jti.v15i2.832

Abstract

The course is one of the education provided outside formal (non-formal) schools to develop personal abilities and skills. Eden Everyday English Course Institute is an Institution located in Bogor. In this institution, the registration process for students is done manually by filling in the registration form provided by the admin. Eden Everyday English Course Institute is one of the courses where the number of applicants increases every year, this causes the administration department cannot manage everything properly and feels overwhelmed so that it is not effective. With the increase in the number of students registering each year, it would be better if a web-based registration system was created, so that it could simultaneously serve as a medium for promoting the course institution. The purpose of this research is to create a web-based application to help the process of registration for new students in Eden Everyday English Course Institute using the waterfall method. Many studies, especially in the field of information system development, use the Waterfall method. This online course registration application is effective and efficient because it is supported by an integrated system. This application improves the quality of information and the efficiency of the implementation of online course registration.
ANALISIS SENTIMEN PADA REVIEW BUKU MENGGUNAKAN ALGORITMA NAÏVE BAYES Dinda Ayu Muthia
Paradigma Vol 16, No 1 (2014): Periode Maret
Publisher : LPPM Universitas Bina Sarana Informatika

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (606.56 KB) | DOI: 10.31294/p.v16i1.723

Abstract

Nowadays consumers are increasingly making their opinions and experiences online. Reading those reviews are time-consuming, but, if only few reviews were read, the evaluation would be biased. Sentiment analysis aims to solve this problem by automatically classifying user reviews into positive or negative opinions. Naive Bayes classifier is a popular machine learning technique for text classification, because it is so simple, efficient and it has a great performance in many domains. However, it has a lack that it is highly sensitive to the high number of feature. Therefore, in this research the concatenation of feature selection methods is used, that is Information gain and Genetic algorithm that could increase the accuracy of Naive Bayes classifier.This research turns out text classification in the form of positive or negative from book reviews. The measurement is based on the accuracy of Naive Bayes before and after adding the feature selection method. Evaluation was performed using 10 fold cross validation. Whereas the measurement of accuracy was measured by using confusion matrix and ROC curve. The result of this research is the improvement of accuracy of Naive Bayes from 75.50% to 84.50%.
PERANCANGAN SISTEM INFORMASI PEMESANAN TIKET PESAWAT DOMESTIK BERBASIS WEB PADA CV JENIKA GROUP DEPOK Adelia Guskani; Dinda Ayu Muthia
Akrab Juara : Jurnal Ilmu-ilmu Sosial Vol 7 No 1 (2022): Februari
Publisher : Yayasan Azam Kemajuan Rantau Anak Bengkalis

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58487/akrabjuara.v7i1.1759

Abstract

Based on the Tiket.com survey in the third quarter of 2020, there was a three-fold increase in transactions that occurred in hotel booking services and flight bookings. This increase is considered very fast in the midst of the Covid-19 pandemic due to the encouragement of people to take vacations in the midst of the pandemic. To be able to compensate for the increase that occurred, tour and travel companies are required to be able to optimize services by computerizing the flight ticket booking system. Therefore, the author intends to create a website for booking domestic airline tickets for CV JENIKA GROUP Depok. The author uses a method that has proven its effectiveness in designing an information system, namely the Waterfall method. Based on the results of the study, it can be concluded that the design of this web-based domestic flight ticket booking program can provide convenience and comfort for admins and customers of CV JENIKA GROUP and can further expand marketing reach.
ANALISIS SENTIMEN PADA REVIEW RESTORAN DENGAN TEKS BAHASA INDONESIA MENGUNAKAN ALGORITMA NAIVE BAYES Dinda Ayu Muthia
JITK (Jurnal Ilmu Pengetahuan dan Teknologi Komputer) Vol 2 No 2 (2017): JITK Issue February 2017
Publisher : LPPM Nusa Mandiri

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1126.028 KB)

Abstract

In the era of the web as it is now, some information is now flowing through the network. Because of the variety of web content includes subjective opinion and objective information, it is now common for people to gather information about products and services they want to buy. However, because there is quite a lot of information in text form without any numerical scale, it is difficult to classify the evaluation of information efficiently without reading the complete text. Sentiment analysis aims to address this problem by automatically classifying user review be a positive or negative opinion. Naïve Bayes classifier is a popular machine learning techniques for text classification because it is very simple, efficient and performs well in many domains. However, Naïve Bayes has the disadvantage that is very sensitive to feature too much, resulting in a classification accuracy becomes low. Therefore, this study used the method of selecting features, namely Genetic algorithm in order to improve the accuracy of Naïve Bayes classifier. This research resulted in the classification of the text in the form of a positive or negative review of the restaurant. Measurement is based on the accuracy of Naive Bayes before and after the addition of feature selection methods. The evaluation was done using a 10 fold cross-validation. While the measurement accuracy is measured by confusion matrix and ROC curves. The results showed an increase in the accuracy of Naïve Bayes from 86.50% to 90.50%.
Opinion Mining Pada Review Produk Kecantikan Menggunakan Algoritma Naïve Bayes Dinda Ayu Muthia
Jurnal Sistem Informasi Vol 7 No 1 (2018): JSI Periode Februari 2018
Publisher : LPPM STMIK ANTAR BANGSA

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (710.595 KB) | DOI: 10.51998/jsi.v7i1.203

Abstract

Abstract— In recent years many sentiment analysis and opinion mining applications have been developed to analyze opinions, feelings and attitudes about products, brands, and news, etc. These applications mine opinions from different sources like online forums and news sites and from movie, product and hotel reviews. The Naïve Bayes algorithm is a popular machine learning technique for opinion mining, as it is very simple, efficient and performs well on many domains. However, Naïve Bayes has a deficiency that is very sensitive to features that are too numerous, resulting in low classification accuracy. Therefore, this research used Genetic Algorithm feature selection method to improve the accuracy of Naïve Bayes. This study produces text classification in the form of positive or negative from beauty product reviews. Measurements based on Naive Bayes accuracy before and after the addition of feature selection methods. The evaluation was performed using 10 fold cross validation. Measurement accuracy is measured with confusion matrix and ROC curve. The results showed an increase in the accuracy of Naïve Bayes from 65.50% to 83%.Intisari— Dalam beberapa tahun terakhir banyak analisis sentimen dan aplikasi opinion mining telah dikembangkan untuk menganalisis pendapat, perasaan dan sikap tentang produk, merek, dan berita, dan sejenisnya. Aplikasi ini menambang pendapat dari berbagai sumber seperti forum online dan situs berita dan dari ulasan film, produk dan hotel. Algoritma Naïve Bayes adalah teknik machine learning yang populer untuk opinion mining, karena sangat sederhana, efisien dan memiliki performa yang baik pada banyak domain. Namun, Naïve Bayes memiliki kekurangan yaitu sangat sensitif pada fitur yang terlalu banyak, yang mengakibatkan akurasi klasifikasi menjadi rendah. Oleh karena itu, dalam penelitian ini digunakan metode pemilihan fitur Genetic Algorithm agar bisa meningkatkan akurasi Naïve Bayes. Penelitian ini menghasilkan klasifikasi teks dalam bentuk positif atau negatif dari review produk kecantikan. Pengukuran berdasarkan akurasi Naive Bayes sebelum dan sesudah penambahan metode pemilihan fitur. Evaluasi dilakukan menggunakan 10 fold cross validation. Pengukuran akurasi diukur dengan confusion matrix dan kurva ROC. Hasil penelitian menunjukkan peningkatan akurasi Naïve Bayes dari 65.50% menjadi 83%.Kata Kunci— Algoritma, Naive Bayes, Review, Opinion Mining