Article Per Year (5 Year)
p-Index From 2021 - 2026
2.502
P-Index
This Author published in this journals
All Journal Jurnal Pilar Nusa Mandiri IJIS - Indonesian Journal On Information System JSiI (Jurnal Sistem Informasi) J-SAKTI (Jurnal Sains Komputer dan Informatika) JURNAL TEKNOLOGI INFORMASI J-SAKTI (Jurnal Sains Komputer dan Informatika) J-Intech (Journal of Information and Technology) Jurnal Ilmu Komputer Innovative: Journal Of Social Science Research Inspiration: Jurnal Teknologi Informasi dan Komunikasi Informatics and Software Engineering (ISE) Journal of Innovation and Computer Science
Saputra, Dedi Dwi
Unknown Affiliation
Humanities Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Energy Engineering Law, Crime, Criminology & Criminal Justice Library & Information Science Public Health Other

Published : 16 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 16 Documents
Search

 1   2 
Optimasi Sentimen Analisis Informatif dan Tidak Informatif dari Tweet di BMKG Menggunakan Algoritma Naive Bayes dan Metode Teknik Pengambilan Sampel Minoritas Sintetis Hidayatulloh, Muhammad Yusuf; Sunanto, Anto; Armansyah, A; Gevin, Muhammad Farrell Afelino; Saputra, Dedi Dwi
J-SAKTI (Jurnal Sains Komputer dan Informatika) Vol 7, No 1 (2023): EDISI MARET
Publisher : STIKOM Tunas Bangsa Pematangsiantar

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30645/j-sakti.v7i1.565

Abstract

The emergence of computer-based and mobile-based social networks seems to have received high attention from the public. Evidenced by the increasing number of social networks that appear. Friendster, Facebook, Twitter, Linkd In and many others. Twitter is one of the social media used to find information, Twitter users generally report every activity. They are even more helped by the existence of increasingly sophisticated cellphones. The system created in this study to optimize the analysis of informative and uninformative sentiment using a rapid miner application with the Naïve Bayes, Naïve Bayes + Adaboost, SVM, and SVM PSO methods using data taken from twitter @infoBMKG. The research method used is the collection of tweet data from twitter taken by the Crawling method. The data taken is tweets in Indonesian with a total of 1,000 tweets from the @infoBMKG twitter account. The results of the nave Bayes algorithm test carried out in this study were to measure the performance of accuracy, precision, recall, AUC from the results of the training and submission of datasets that had gone through the data preprocessing process. From the results of the research that has been done, it is proven that the optimization of informative and uninformative sentiment analysis from tweets on BMKG's twitter gets good results using the Support Machine Vector method with higher Accuracy, Recall, and AUC values than other methods.
Analisis Sentimen Analisis Sentimen Terhadap Twitter Direktorat Jenderal Bea dan Cukai Menggunakan komparasi Algoritma Naïve Bayes dan Support Vector Machine Saputra, Dedi Dwi; Fahlapi, Riza; Kuntoro, Antonius Yadi; Hermanto, Hermanto; Asra, Taufik
J-INTECH (Journal of Information and Technology) Vol 12 No 02 (2024): J-Intech : Journal of Information and Technology
Publisher : LPPM STIKI MALANG

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32664/j-intech.v12i02.1274

Abstract

Direktorat Jenderal Bea & Cukai (DJBC) is a government agency in charge of guarding and serving export and import activities in Indonesia since its establishment in 1946 which is expected by the community as the front guard in protecting the community in this field, but in recent times there have been many cases involving the institution of the Directorate General of Customs & Excise which make this institution can affect the view of the performance of this institution. With the description of the problem above, it is very interesting to conduct research on public views using tweets from twitter @bravobeacukai and @beacukaiRI which are owned and processed by Direktorat Jenderal Bea & Cukai as a place to channel public opinions and views on this institution. This research uses the Smote method with Naïve Bayes and compared with Support vector machine methods for these results to compare the level of accuracy. The results of this study found that using the Smote method with Naïve Bayes obtained an Accuracy value of 78.95%, Precision 74.01%, Recall 89.41%, and AUC 0.650 while for the Smote method with Support vector machine is worth 73.35% Accuracy, Precision 67.88%, Recall 88.95%, and AUC 0.853. Based on the research results, the smote method with Naïve Bayes has the greatest results and is effective with the dataset studied.
Classification of Software Defect Prediction for Bisnissyariah.co.id Media Portal using Machine Learning Technology Ismaya, Fikri; Gata, Windu; Kusuma, Muhammad Romadhona; Saputra, Dedi Dwi; Kurniawan, Sigit
Journal of Innovation and Computer Science Vol. 1 No. 2 (2025): Journal of Innovation and Computer Science
Publisher : Yayasan Mitra Peduli Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.57053/jics.v1i2.96

Abstract

This research was conducted to develop software defect prediction using a dataset from Bisnissyariah, a forum website with up-to-date news related to Islamic business. The study employed a straightforward research design to ensure easy comprehension for the readers. Machine learning models, including Random Forest, Gradient Boosting, and Support Vector Machine, were utilized in this research—the application of these models aimed to evaluate and compare the accuracy of software defect predictions. The research findings indicated that the Random Forest model outperformed the others, achieving an accuracy rate of 96.7%. This result shows the high effectiveness of the Random Forest model in predicting software defects based on data from Bisnissyariah. In addition, these findings significantly impact the development of more reliable and high-quality software, particularly in Islamic business. This research makes a valuable contribution to enhancing our understanding of software defect prediction using data from sources like Bisnissyariah.
Perancangan UI/UX Design Warung Pintar Berbasis Android Menggunakan Metode Design Thinking (Studi Kasus: Warung 16) Kuntoro, Antonius Yadi; Fahlapi, Riza; Saputra, Dedi Dwi; Hermanto, Hermanto; Sukmawati, Alfiani; Asra, Taufik
Jurnal Ilmu Komputer (JUIK) Vol 5, No 2 (2025): JUNE 2025
Publisher : Universitas Muhammadiyah Gorontalo

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31314/juik.v5i2.4168

Abstract

Perkembangan teknologi informasi yang pesat telah menjangkau berbagai kalangan, termasuk instansi swasta, negeri, wirausahawan, pebisnis, sekolah, hingga perguruan tinggi. Teknologi informasi tidak hanya mempermudah pencarian informasi, tetapi juga mendukung kelancaran bisnis, termasuk aktivitas penjualan. Peran User Interface (UI) dan User Experience (UX) menjadi krusial dalam pengembangan aplikasi untuk memastikan kenyamanan dan kemudahan pengguna. Aplikasi mobile memungkinkan pengguna mengakses informasi, media sosial, dan marketplace online dengan mudah. Warung 16, toko retail di Bogor, melayani pembelian langsung dan delivery via WhatsApp. Namun, metode WhatsApp memiliki kendala seperti ketiadaan informasi stok real-time dan proses pemesanan manual. Penelitian ini merancang UI/UX aplikasi untuk mempermudah pembeli dalam proses pembelian dan akses informasi produk di Warung 16. Desain ini bertujuan meningkatkan efisiensi, mengurangi kesalahan manual, dan menawarkan pengalaman pengguna yang optimal. Melalui pendekatan Design Thinking pada aplikasi warung 16 yang diuji dengan motede System Usability Scale (SUS) terhadap 112 responden menggunakan kuesioner mendapatkan hasil sebesar 91,2 yang menunjukkan bahwa desain memenuhi persyaratan dengan baik dalam uji kegunaan.
Sentiment Analysis of Rising Fuel Prices on Social Media Twitter using the Naïve Algorithm Bayes Classifiers And AdaBoost Hendriyadi, Imam; Putri, Angela Febrianti; Rahmawati, Rahmawati; Saputra, Dedi Dwi
Informatics and Software Engineering Vol. 1 No. 1 (2023): June 2023
Publisher : SAN Scientific

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58777/ise.v1i1.55

Abstract

The government issued a policy of increasing the price of Indonesian fuel oil (BBM) in September 2022. This policy resulted from the war in Europe between Russia and Ukraine, which caused a surge in world oil prices because many respondents complained about the increase in fuel. This condition has caused much controversy or opinion among the public on social media, especially Twitter. With this phenomenon, sentiment analysis uses the Naïve Bayes classifiers algorithms to see how the public responds to government policies. The classification used in this sentiment analysis is Complaint or Not Complaint. Sentiment analysis of fuel rise on Twitter using Naïve Bayes classifier algorithm and AdaBoost Naïve Bayes classifier algorithm is applied to get the best classification By using hashtag tweets The increase in the price of fuel oil (BBM) which was taken 1000 tweets to be Used US a dataset. Data preprocessing consists of Text, Status, removal annotations, Remove hashtags, Remove urls, regexp, Indonesian stemming, and Indonesian stopword removal. The analysis results obtained an accuracy value of 70.69%, precision of 70.49%, recall of 71.45%, and AUC of 0.729 (good classification).   Pemerintah mengeluarkan kebijakan menaikkan harga bahan bakar minyak (BBM) Indonesia pada September 2022. Kebijakan ini adalah hasil dari perang di Eropa antara Rusia dan Ukraina hal ini menyebabkan lonjakan harga minyak dunia karena banyak responden masyarakat yang mengeluhkan atas kenaikan BBM. Hal ini banyak menimbulkan kontroversi ataupun opini pada kalangan masyarakat di social media khususnya twitter. Dengan adanya fenomena tersebut, untuk melihat bagaimana tanggapan masyarakat terhadap kebijakan pemerintah maka dilakukan analisis sentimen menggunakan algoritma naïve bayes classifier. Klasifikasi yang digunakan pada analisis sentimen ini adalah Complaint atau Not complaint. Analisis sentimen kenaikan bahan bakar pada twitter menggunakan algoritma naive bayes classifier dan adaboost, algoritma naïve bayes classifier ini diterapkan untuk mendapatkan klasifikasi terbaik. Dengan menggunakan hashtag tweets Kenaikan harga bahan bakar minyak (BBM) yang diambil 1000 tweet untuk di jadikan dataset. Preprocessing data terdiri dari Text, Status, Remove annotations, Remove hastag, Remove url, Regexp, Indonesian stemming, Indonesian stopword removal. Hasil analisis tersebut didapatkan nilai accuracy 70,69%, precision 70,49%, recall 71,45%, dan AUC yang didapat sebesar 0,729 (good classification).
Optimasi Feature Selection Text Mining: Stemming dan Stopword untuk Sentimen Analisis Aplikasi SatuSehat Wardhani, Diky; Astuti, Rika; Saputra, Dedi Dwi
Innovative: Journal Of Social Science Research Vol. 4 No. 1 (2024): Innovative: Journal Of Social Science Research
Publisher : Universitas Pahlawan Tuanku Tambusai

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31004/innovative.v4i1.8759

Abstract

Aplikasi SatuSehat merupakan hasil pengembangan dan transformasi dari Peduli Lindungi yang dilakukan oleh KEMENKES (kementerian kesehatan) dengan tujuan untuk mencatat data kesehatan masyarakat. Dengan berubahnya aplikasi Peduli Lindungi menjadi SatuSehat, beragam ulasan di layangkan oleh pengguna aplikasi ini di PlayStore. Penelitian ini dilakukan untuk membandingkan dan mengoptimasikan Feature Selection pada Text Mining untuk mendapatkan hasil yang paling optimal dari kedua fitur tersebut. 2000 data set didapatkan dengan metode Scrapping pada ulasan PlayStore. Lalu data tersebut diterapkan metode SMOTE dan Pre-Processing dengan Feature Selection, Stemming dan Stopword sehingga kedua fitur dapat dibandingkan dan dicari hasil yang optimal. Hasil penelitian ini maka bisa diperoleh hasil saat menggunakan Feature Selection steaming hasilnya akurasinya mendapatkan 93,43% dan presisi mendapatkan 88,42% sedangkan saat menggunakan feature selection stopword hasil yang didapatkan adalah nilai akurasinya mendapatkan 89,19% dan presisi mendapatkan 82,23%, dan jika menggunkan stopword dan stemming dilakukan secara bersamaan maka hasilnya nilai akurasinya mendapatkan 92,56% dan presisi mendapatkan 95,46%. Dan hasil teroptimal diperoleh paling optimal saat menggunakan stemming dan stopword digunakan secara bersamaan.
Co-Authors Abdullah, M Arief Agustinus, Matius Akhsanal, M. Antonius Yadi Kuntoro Ariyanto, Angga Armansyah, A Awang, Nana Deni Hermawan Dewi, Anggi Riantika Fahlapi, Riza Fakhrezi, Moch Alvi Fatoni, Raden Mirza Kurnia Gata, Windu Gevin, Muhammad Farrell Afelino Hartati, H Hendriyadi, Imam Hermanto Hermanto Hidayatulloh, Muhammad Yusuf Indah Purnamasari Ismaya, Fikri juwita sari Krisnadi, Eka Kharisma Kusuma, Muhammad Romadhona Kusumayudha, Mochammad Rizky Maulana, Fajrullah Ma’arif, Helmi Muchamad Bachram Shidiq Panggabean, Supriadi Pratiwi, Risca Lusiana Putra, Andreyana Pratama Putri, Angela Febrianti Rahmawati, Rahmawati Rika Astuti Siddik, Dimas Zappar Sigit Kurniawan Siti Fauziah Sri Diana Sukmawati, Alfiani Sulistyo, Romy Triadi Sunanto, Anto Sururi, Dede Miftah Taufik Asra Telaumbanua, Emrina Wahyudi, Zailani Wardhani, Diky Wibowo, Gigih Hasoko yuda pratama