Claim Missing Document
Check
Articles

Found 10 Documents
Search

Recommendation for Classification of News Categories Using Support Vector Machine Algorithm with SVD Nofenky .; Dionisia Bhisetya Rarasati
Ultimatics : Jurnal Teknik Informatika Vol 13 No 2 (2021): Ultimatics : Jurnal Teknik Informatika
Publisher : Faculty of Engineering and Informatics, Universitas Multimedia Nusantara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31937/ti.v13i2.1854

Abstract

Online news is a digital information media currently has a very easy and flexible updating process. The News Document grouping process is implemented in several stages, including Text Mining which includes Text Pre-processing which includes Tokenizing, Stopword removal, Stemming, Word Merging, TF-IDF and Confusion Matrix. Of the several techniques in Text Mining, the most frequently used for News Document classification is the Support Vector Machine (SVM). SVM has the advantage of being able to identify separate hyperplane that maximizes the margin between two or more different classes. The selection of features in SVM significantly affects the classification accuracy results. Therefore, in this study a combination of feature selection methods is used, namely Singular Value Decomposition in order to increase accuracy and reduce the Classifier Time Support Vector Machine. This research resulted in text classification in the form of categories Entertainment, Health, Politics and Technology. Based on the Support Vector Machines Algorithm, an accuracy rate of 81% was obtained with 360 Data Training and 120 Data Testing, after adding the Singular Value Decomposition feature with a K- Rank value of 50%, a significant increase in accuracy was obtained with an accuracy value of 94% and The time of Algorithm process is faster.
A Grouping of Song-Lyric Themes Using K-Means Clustering Dionisia Bhisetya Rarasati
JISA(Jurnal Informatika dan Sains) Vol 3, No 2 (2020): JISA(Jurnal Informatika dan Sains)
Publisher : Universitas Trilogi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31326/jisa.v3i2.658

Abstract

One of the automatic way of theme grouping that can be used is K-Means Clustering. In this research, the song theme is taken from the text of song lyrics. The aim of this study is developing a system that can automatically group the song lyric theme and know the accuracy level of the grouping. The process stage is started with the data processing or text processing called as text mining. In text mining, there are some processes. First, the text operation. The text operation consists of tokenizing, stopword, steeming, and word weighting then can be processed using K-Means clustering. In clustering process, it consists of initial centroid initialization uses Variance Initialization, next counts the centroid distance on the data using Euclidean distance until get the proper grouping accurately. The accuracy counting uses confusion matrix. The next step to see the suitability system that has been made, new data is added which then is processed by a system. After that, it can decide the new data is classified into one specific theme. From the research that has been conducted as case study in Masdha Radio Yogyakarta, total data available 400 and divided into four clusters. The clusters consist of love cluster, friendship cluster, religion cluster, and fighting cluster. The result of research song lyric grouping based on the theme works well with 93.25% accuracy for the unique word frequency numbers 121 maximum and unique word 0 minimum.Keywords – K-Means clustering, Text Operation, Variance Initialization, Confusion Matrix.
Sentiment Analysis of 2024 Presidential Candidates Election Using SVM Algorithm Alfonso, Michael; Rarasati, Dionisia Bhisetya
JISA(Jurnal Informatika dan Sains) Vol 6, No 2 (2023): JISA(Jurnal Informatika dan Sains)
Publisher : Universitas Trilogi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31326/jisa.v6i2.1714

Abstract

Elections for presidential candidates are held every 5 years with various candidates, especially on Twitter, arguments about political matters often occur that many Twitter users participate in discussions about the election for presidential candidate. Therefore, this study focuses on sentiment analysis to infer user responses to the presidential election and validate it by looking for a correlation between electability survey results and Twitter sentiment data using Pearson Correlation. In sentiment analysis model, the 10-Fold Cross Validation method is used to find the best model from a dataset with a division of training data and test data with 90:10 split. Then the alphabetic data will be converted into numeric data using the TF-IDF weighting method. To validate the best model, Confusion Matrix is used to get the best f1-score. The model is using Support vector machine algorithm with the Gaussian RBF (Radial Basis Function) kernel. The results of the analysis are compared with the results of the news portal electability survey which contains the 3 candidates using Pearson Correlation. This study produces the best fold for each data on each presidential candidate with the f1-score to find the best model for each fold. In the Peason Correlation result, the higher positive sentiment of each presidential candidate, the higher electability survey data. For further research, research can be discuss about hyper tuning parameters and using other kernels on Support vector machine algorithm.
IMPLEMENTASI METODE FUZZY TSUKAMOTO DALAM MENENTUKAN SUPPLY BBM PADA PERTASHOP Citra, Calvin Christopher; Mulyana, Teady Matius Surya; Agung, Halim; Rarasati, Dionisia Bhisetya; Sipayung, Evasaria Magdalena
SKANIKA: Sistem Komputer dan Teknik Informatika Vol 5 No 2 (2022): Jurnal SKANIKA Juli 2022
Publisher : Universitas Budi Luhur

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1419.156 KB) | DOI: 10.36080/skanika.v5i2.2946

Abstract

Kebutuhan Bahan Bakar Mesin dari masyarakat terus meningkat, hal ini juga terjadi bagi masyarakat pinggir kota.Untuk memenuhi kebutuhan Bahan Bakar Mesin yang ada dipinggir kota, maka Pertamina memberikan sebuah program bagi masyarakat untuk mendirikan SPBU mini dengan modal yang kecil, program ini dinamakan dengan Pertashop. Pertashop akan melakukan Pasokan satu bulan satu kali ke pihak pertamina. Namun dalam proses seupply proses perhitungan masih sering kurang tepat sehingga membuat pertashop mengalami kekurangan stok. Untuk mengatasi hal tersebut yang dapat dilakukan adalah dengan menentukkan Pasokan yang dibutuhkan pada sebuah SPBU atau Pertashop pada periode selanjutnya. Logika Fuzzy yang dipilih sebagai metode untuk menentukan Pasokan pada Pertashop agar mengurangi terjadinya kehabisan stok. Metode yang dipilih dalam menentukan Pasokan pada pertashop adalah Logika Fuzzy. Logika fuzzy memiliki Sistem Interferensi Fuzzy yang memberikan sebuah aturan dalam logika Fuzzy. Sistem Interferensi Fuzzy terdapat 3 metode yaitu, Tsukamoto, Mamdani, dan Sugeno. Pada penelitian ini menggunakan metode Fuzzy Tsukamoto Hasil penelitian didapatkan bahwa dengan tingkat akurasi metode fuzzy sebesar 87% menggunakan metode MAPE, dapat dinyatakan bahwa metode fuzzy Tsukamoto berhasil dalam menghitung Pasokan yang harus dilakukan pihak pertashop setiap bulannya agar tidak terjadi kekurangan stok.
Sentiment Analysis of Sirekap Application Review Using Logistic Regression Algorithm Hagi, Audi; Rarasati, Dionisia Bhisetya
Jurnal Informatika Vol 11, No 2 (2024): October
Publisher : Universitas Bina Sarana Informatika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31294/inf.v11i2.22066

Abstract

General Elections (Pemilu) is one of the crucial moments in democracy to elect representatives of the people. The General Elections Commission (KPU) launched the Sirekap application as an aid in the election process. This application allows polling station officers (KPPS) to record the vote count electronically. However, there have been some complaints and feedback from the public regarding the Sirekap application. To understand public sentiment towards the Sirekap application, this study was conducted by analyzing user reviews on the Google Play Store. The Logistic Regression algorithm is used to classify review sentiment into positive and negative. The analysis process involves data preprocessing, z-score normalization, dividing the data set into 80% training data and 20% test data, weighting words using the TF-IDF method, training the model using the Logistic Regression algorithm, and testing the model with a confusion matrix. The results of the analysis show that the Logistic Regression algorithm is effective in classifying the sentiment of the Sirekap application reviews with an accuracy of 91%. The precision score for the positive and negative classes are 90% and 92%, respectively. The recall score for the positive and negative classes are 94% and 87%, respectively. The f1-score for the positive and negative classes are 92% and 90%, respectively. The results of this sentiment analysis can also be used by the KPU to understand the level of user satisfaction and improve the quality of the Sirekap application for the 2024 Regional Head Elections (Pilkada).
Stock Price Prediction on IDX30 Index using Long Short-Term Memory Algorithm William, Ken; Rarasati, Dionisia Bhisetya
Jurnal Informatika Vol 11, No 2 (2024): October
Publisher : Universitas Bina Sarana Informatika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31294/inf.v11i2.22156

Abstract

The capital market plays a significant role in a country's economy, facilitating corporate financing and providing investment opportunities for the public. One popular investment instrument is stocks, yet many investors struggle to make profitable investment decisions due to a lack of understanding of stock investments. Therefore, predicting stock prices can be a way to determine the future value of a stock. This research aims to address this issue by applying the Long Short-Term Memory (LSTM) algorithm to predict stock prices on the IDX30 index. LSTM is capable of processing sequential data, such as stock price data, complexly because it can store information over long periods. The testing is conducted using various parameters in layers, epochs, and time steps to obtain the best prediction model. The LSTM architecture used consists of four layers: the LSTM layer with 128 neurons, dropout and dense layers with 64 neurons, and an additional dense layer that converts the output from the previous layer into prediction results. This study demonstrates that the LSTM algorithm can accurately predict stock prices based on evaluation metrics such as Mean Absolute Percentage Error (MAPE) and Root Mean Square Error (RMSE). The best results for PT Bank Central Asia Tbk show a MAPE of 1.14% and RMSE of 137.71, PT Bank Rakyat Indonesia Tbk shows a MAPE of 1.58% and RMSE of 87.4, and PT Bank Mandiri Tbk shows a MAPE of 1.64% and RMSE of 88.26.
Analisis Sentimen Aplikasi Polri Super App Menggunakan Algoritma Random Forest Fransisco, Vicky; Rarasati, Dionisia Bhisetya
Jurnal Ilmiah Sains dan Teknologi Vol 8 No 2 (2024): Jurnal Ilmiah Sains dan Teknologi
Publisher : Teknik Informatika Fakultas Ilmu Komputer

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47080/saintek.v8i2.3383

Abstract

Polri Super App merupakan aplikasi mobile terintegrasi yang dapat melakukan banyak hal yang berkaitan dengan kepolisian. Pelayanan kepolisian mencakup berbagai aspek yang sangat penting dalam kehidupan bermasyarakat, seperti menangani kasus kriminal, mengatur lalu lintas, mengawasi kegiatan masyarakat, dan lainnya. Seiring dengan penerapan dan meningkatnya penggunaan aplikasi ini, muncul berbagai tanggapan berupa ulasan dari pengguna aplikasi. Untuk dapat memahami tingkat kepuasan dan ekspektasi dari pengguna aplikasi, analisis sentiment dari pengguna aplikasi diperlukan. Dengan menganalisis ulasan dari pengguna aplikasi, maka didapatkan sentimen masyarakat yang diharapkan dapat berguna bagi penyelenggara layanan Polri Super App agar dapat terus meningkatkan kualitas dan layanan aplikasi. Algoritma Random Forest digunakan untuk melakukan klasifikasi terhadap ulasan aplikasi. Hasil pengujian menggunakan confusion matrix menunjukkan bahwa model yang dibentuk memiliki nilai akurasi sebesar 95,87%.
Pengembangan Sistem Inventory dan Sistem Pengiriman Barang untuk Memajukan Usaha PT. ABC Wilson, Arthur; Rarasati, Dionisia Bhisetya
Jurnal Ilmiah Sains dan Teknologi Vol 8 No 2 (2024): Jurnal Ilmiah Sains dan Teknologi
Publisher : Teknik Informatika Fakultas Ilmu Komputer

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47080/saintek.v8i2.3396

Abstract

In a company, there are always inbound and outbound goods. To record and track the movement of these goods efficiently, a system is needed. Manual writing is no longer feasible due to the high volume and rapid movement of goods, increasing the likelihood of errors. Therefore, an inventory system that automatically records the movement of goods is necessary to minimize human errors. There are systems for both inbound and outbound goods. All goods entering and leaving the company must be recorded for reporting purposes. For sales and shipment of goods, a shipment system is essential to make deliveries more efficient, timely, and cost-effective. The inventory system aims to record the movement of goods. Additionally, the shipment system cannot track the current status of shipments. The goal of this research is to develop inventory and shipment systems that can assist PT ABC's operations and facilitate its growth.
Klasifikasi Penyakit Paru-Paru Dengan Citra X-Ray Menggunakan Metode Convolutional Neural Network Kusuma, Daniel; Rarasati, Dionisia Bhisetya
Jurnal Ilmiah Sains dan Teknologi Vol. 9 No. 2 (2025): Jurnal Ilmiah Sains dan Teknologi
Publisher : Teknik Informatika Fakultas Ilmu Komputer

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.5555/23mj8c35

Abstract

This research explores the utilization of Convolutional Neural Network (CNN) methods to classify lung diseases, including COVID-19, Tuberculosis, and Pneumonia. The focus is on developing a CNN model for lung disease classification using a dataset that has undergone augmentation. Data augmentation is performed through various transformations such as rotation, horizontal_flip, vertical_flip, shear_range, and zoom_range. The dataset is divided into 70% for training, 20% for validation, and 10% for testing, totaling 2200 data points. The results indicate that the constructed model successfully achieved an accuracy of 96.49% in the training process and 95% on the testing data. This research demonstrates the potential of CNN in classifying lung diseases quite effectively after model training.
Analisis Sentimen Pengguna Aplikasi Byond by BSI Menggunakan Algoritma Naïve Bayes Wijaya, Ian Frederick; Rarasati, Dionisia Bhisetya
Ranah Research : Journal of Multidisciplinary Research and Development Vol. 7 No. 6 (2025): Ranah Research : Journal Of Multidisciplinary Research and Development
Publisher : Dinasti Research

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.38035/rrj.v7i6.1808

Abstract

Penelitian ini bertujuan untuk menganalisis sentimen pengguna terhadap aplikasi Byond by BSI yang dikembangkan oleh Bank Syariah Indonesia. Analisis dilakukan dengan mengklasifikasikan ulasan pengguna dari Google Play Store ke dalam kategori positif atau negatif menggunakan algoritma Naïve Bayes dengan pendekatan pembobotan fitur TF-IDF. Data dikumpulkan melalui teknik web scraping, menghasilkan 26.547 ulasan yang kemudian diproses melalui tahapan preprocessing seperti case folding, filtering, normalisasi, tokenisasi, penghapusan stop words, dan stemming. Model klasifikasi dievaluasi menggunakan dua skenario pembagian data: 80:20 dan 70:30. Hasil penelitian menunjukkan bahwa pada skenario 80:20, model mencapai akurasi sebesar 89%, sedangkan pada skenario 70:30 mencapai 88%. Evaluasi dilakukan menggunakan confusion matrix yang mencakup metrik akurasi, precision, recall, dan F1-score. Analisis lebih lanjut mengungkap bahwa pengguna cenderung memberikan sentimen positif terhadap desain antarmuka dan kemudahan navigasi, sementara sentimen negatif banyak diarahkan pada performa teknis seperti lambat dan sering error. Dengan demikian, metode Naïve Bayes yang dipadukan dengan TF-IDF terbukti efektif dalam mengklasifikasikan sentimen ulasan aplikasi mobile banking. Temuan ini dapat menjadi dasar bagi pengembang dan manajemen Bank Syariah Indonesia dalam merancang strategi peningkatan kualitas layanan dan pengalaman pengguna aplikasi Byond by BSI.