Article Per Year (5 Year)
p-Index From 2020 - 2025
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 
KOMPARASI METODE FEATURE SELECTION TEXT MINING PADA PERMASALAHAN KLASIFIKASI KELUHAN PELANGGAN INDUSTRI TELEKOMUNIKASI MENGGUNAKAN SMOTE DAN NAÏVE BAYES Fauziah, Siti; Saputra, Dedi Dwi; Pratiwi, Risca Lusiana; Kusumayudha, Mochammad Rizky
IJIS - Indonesian Journal On Information System Vol 8, No 2 (2023): SEPTEMBER
Publisher : POLITEKNIK SAINS DAN TEKNOLOGI WIRATAMA MALUKU UTARA

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36549/ijis.v8i2.289

Abstract

Twitter merupakan salah satu media sosial yang populer di Indonesia. Tidak hanya masyarakat biasa yang menggunakan media sosial ini, banyak juga perusahaan yang memanfaatkan Twitter sebagai sarana promosi dan pendekatan kepada para pelanggannya. Termasuk Tri Indonesia yang mempunyai official akun di Twitter, salah satunya adalah @3CareIndonesia. Para pengguna Tri Indonesia memanfaatkan akun official ini sebagai sarana berbagi opini tentang pengalaman menggunakan provider ini dalam bentuk komentar di Twitter @3CareIndonesia. Penelitian ini dilakukan untuk mengukur seberapa akurat algoritma SMOTE dan Naïve Bayes dalam mengetahui sentimen pada komentar para pelanggan Tri Indonesia lalu mengkategorikannya kedalam komplain dan bukan komplain dengan megunakan algoritma Naïve Bayes. Proses pengambilan data menggunakan metode crawling data menggunakan aplikasi Rapidminer. Kemudian dari data yang didapat dilakukan preprocessing tingkat 1 menggunakan Gataframework dan preprocessing tingkat 2 menggunakan Rapidminer. Hasil dari penelitian ini  menunjukan bahwa kombinasi dari SMOTE dan Naïve Bayes dapat menghasilkan pemodelan yang cukup baik dengan nilai accuracy sebesar 81.85%, precision sebesar 80.44%, recall sebesar 83.10% dan AUC sebesar 0.817.Kata Kunci: Rapidminer, Naïve Bayes, Gataframework, Twitter, Sentiment Analysis
SENTIMEN ANALISIS TERHADAP PUAN MAHARANI SEBAGAI KANDIDAT CALON PRESIDEN 2024 BERDASARKAN OPINI TWITTER MENGGUNAKAN METODE NAIVE BAYES DAN ADABOOST Dewi, Anggi Riantika; Diana, Sri; Fakhrezi, Moch Alvi; Awang, Nana; Ma’arif, Helmi; Saputra, Dedi Dwi
Jurnal Sistem Informasi Vol 10 No 1 (2023)
Publisher : Universitas Serang Raya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30656/jsii.v10i1.5785

Abstract

Indonesia merupakan negara yang menganut sistem demokrasi, hal ini ditandai dengan diselenggarakannya pemilihan umum presiden dan wakil presiden. Publik sangat antusias dengan pencalonan presiden 2024, tidak hanya di dunia nyata, bahkan di dunia maya seperti Twitter pun masyarakat sangat antusias. Jumlah pengguna Twitter bisa digunakan untuk mengetahui sentimen masyarakat terkait pencalonan presiden 2024, untuk menentukan sentimen positif dan negatif sebuah tweet bisa dilakukan secara manual, namun jika dilihat dari jumlah penggunanya, opini yang dihasilkan juga besar. . Oleh karena itu diperlukan suatu mesin yang dapat menganalisis tweet dan mengklasifikasikan tweet menjadi sentimen positif dan negatif secara otomatis. Dalam penelitian ini, penulis melakukan analisis sentimen terhadap tanggapan warganet di media sosial Twitter terhadap ketua DPR Puan Maharani yang akan mencalonkan diri pada pemilihan wakil presiden Indonesia tahun 2024. Penelitian ini menggunakan metode klasifikasi algoritma Naïve Bayes dengan dan AdaBoost untuk mengklasifikasikan perspektif opini publik Twitter terkait pencalonan presiden Puan Maharani. Akurasi yang dihasilkan dari penelitian ini adalah Naïve Bayes 70.50% dan AdaBoost 68.40%. Kata Kunci: AdaBoost, Naïve Bayes, Pemilihan Umum, Puan Maharani, Sentiment Analysis, Twitter.
Time Effort Prediction Of Agile Software Development Using Machine Learning Techniques Muchamad Bachram Shidiq; Gata, Windu; Kurniawan, Sigit; Saputra, Dedi Dwi; Panggabean, Supriadi
Inspiration: Jurnal Teknologi Informasi dan Komunikasi Vol. 13 No. 2 (2023): Inspiration: Jurnal Teknologi Informasi dan Komunikasi
Publisher : Pusat Penelitian dan Pengabdian Pada Masyarakat Sekolah Tinggi Manajemen Informatika dan Komputer AKBA Makassar

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35585/inspir.v13i2.57

Abstract

To run a software development project, an effective and efficient project management mechanism is needed to coordinate the activities carried out. The agile method was developed because there are several weaknesses in the classic method that can interfere with the course of the software development process according to user desires.  However, in applying agile methods, time effort estimation cannot be done properly. This can cause project managers to have difficulty preparing resources in software development in scrum projects. For this reason, this research aims to predict the time effort of agile software development using Machine Learning techniques, namely the Decision Tree, Random Forest, Gradient Boosting, and AdaBoost algorithms, as well as the use of feature selection in the form of RRelieff and Principal Component Analysis (PCA) to improve prediction accuracy. The best-performing algorithm uses Gradient Boosting k-fold validation with PCA with an MSE value of 2.895, RMSE 1.701, MAE 0.898, and R2 0.951.
Komparasi Algoritma Klasifikasi Text Mining Untuk Analisa Sentimen Pada Akun Twitter Tokopediacare Sururi, Dede Miftah; Wibowo, Gigih Hasoko; Sulistyo, Romy Triadi; Fatoni, Raden Mirza Kurnia; Telaumbanua, Emrina; Saputra, Dedi Dwi
JURNAL TEKNOLOGI INFORMASI Vol 8, No 1 (2022): Jurnal Teknologi Informasi
Publisher : Universitas Respati Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52643/jti.v8i1.2271

Abstract

Perkembangan teknologi yang begitu pesat tidak terelakkan lagi. Media sosial kini menjadi sarana media komunikasi yang paling mudah digunakan orang banyak. Dengan media sosial, banyak penilaian sentimen yang dapat diteliti. Salah satunya Twitter. Dengan twitter, pengguna dapat melakukan review sebuah produk berdasarkan pengalaman yang mereka alami. Tokopedia misalnya, platform e-commerce dengan jutaan akun pembeli tentunya seringkali mendapatkan respon positif atau negatif. Melalui twitter, tokopedia menyediakan layanan konsumen dengan akun @TokopediaCare. Analisa sentimen terhadap review pengguna tokopedia pada akun tersebut memberikan indikator yang berguna untuk berbagai tujuan yang dapat ditemukan dalam komentar, umpan balik ataupun kritik. Data kicauan yang telah dikumpulkan dari twitter diolah terlebih dahulu dipecah menjadi kata sehingga dapat memudahkan dalam mengklasifikasi jenis kata. Penelitian ini menggunakan algoritma Synthetic Minority Oversampling Technique (SMOTE), Naïve Bayes, Adaptive Boosting (AdaBoost), Support Vector Machine (SVM) dan  Support Vector Machine Particle Swarm Optimization (SVM PSO) yang pengujiannya akan membandingkan dari campuran metode tersebut untuk mengetahui metode mana yang paling ideal dalam menentukan sentimen analisa pada kicauan twitter tokopedia. Dengan pengolahan hasil uji menggabungkan Synthetic Minority Oversampling Technique (SMOTE) dan Support Vector Machine Particle Swarm Optimization (SVM PSO) menghasilkan nilai terbaik yaitu Accuracy 76,05%, Precision 77,23%, Recall 74.14% dan AUC 0,826.
SENTIMENT ANALYSIS ON THE TWITTER PSSI PERFORMANCE USING TEXT MINING WITH THE NAÏVE BAYES ALGORITHM Maulana, Fajrullah; Abdullah, M Arief; Sari, Juwita; Siddik, Dimas Zappar; Agustinus, Matius; Saputra, Dedi Dwi
Jurnal Pilar Nusa Mandiri Vol 18 No 2 (2022): Pilar Nusa Mandiri : Journal of Computing and Information System Publishing Peri
Publisher : LPPM Universitas Nusa Mandiri

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33480/pilar.v18i2.3938

Abstract

Social media has developed rapidly today, so social media is no longer just a place to interact and socialize but also to express opinions or criticize a particular party or institution. After the incident at the Malang Kanjuruhan stadium in October 2022, many netizens criticized the performance of PSSI as Indonesia's number one organization that oversees football competitions in Indonesia. For this reason, sentiment analysis was carried out on the official PSSI account on Twitter to assess the performance of PSSI by grouping them as Satisfied and Unsatisfied using the Naïve Bayes Classifier. Sentiment analysis took tweets from the official PSSI account and as many as 1000 comments to be used as a dataset. Then preprocessing is carried out in the GATA Framework using the Annotation Removal, Remove Hashtag, Transformation Remove URL, Regexp, Indonesian Steaming, and Indonesian Stopword Removal methods. The results obtained were 82.82% for accuracy, 78.69% for precision, 90.33% for recall, and 0.866 for AUC. With these results, the value obtained is at a good classification level.
Text Mining untuk Sentimen Analisis dengan Metode Naïve Bayes, SMOTE, N-Gram dan AdaBoost Pada Twitter CommuterLine Putra, Andreyana Pratama; Pratama, Yuda; Krisnadi, Eka Kharisma; Purnamasari, Indah; Saputra, Dedi Dwi
J-SAKTI (Jurnal Sains Komputer dan Informatika) Vol 6, No 2 (2022): EDISI SEPTEMBER
Publisher : STIKOM Tunas Bangsa Pematangsiantar

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30645/j-sakti.v6i2.506

Abstract

In the current era, the development of information technology and social media is growing rapidly so that it can provide updated information and various kinds of public opinion. Many internet users in Indonesia use social media for various purposes, such as seeking information and expressing opinions through social media. One of the social media that is widely used by internet users in Indonesia is Twitter. Twitter users can provide information in the form of comments, criticisms, or suggestions for Comutterline services more quickly and easily. Sentiment analysis can help provide an overview of public perception by grouping opinions into positive and negative categories for Commuterline services. Conducting sentiment analysis based on comments or Tweets from the community on Twitter Commuterline to determine the performance of the Naïve Bayes Classifier algorithm, Synthetic Minority Over-sampling Technique (SMOTE), AdaBoost, and N-Gram so that machine learning implementation can help identify public opinion conveyed through Twitter automatically into positive and negative categories. The use of the Naïve Bayes Classifier, Synthetic Minority Over-sampling Technique (SMOTE), AdaBoost, and N-Gram methods which are considered better to generate predictions on tweets sent by CommuterLine users
Optimasi Analisis Sentimen Pada Twitter Olshop Tokopedia Menggunakan Textmining Dengan Algoritma Naïve Bayes & Adaboost Hartati, H; Hermawan, Deni; Akhsanal, M.; Wahyudi, Zailani; Ariyanto, Angga; Saputra, Dedi Dwi
J-SAKTI (Jurnal Sains Komputer dan Informatika) Vol 6, No 2 (2022): EDISI SEPTEMBER
Publisher : STIKOM Tunas Bangsa Pematangsiantar

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30645/j-sakti.v6i2.493

Abstract

Sentiment Analysis or commonly called Opinion Mining is the process of understanding, extracting and processing textual data automatically to obtain sentiment information contained in a sentence of opinion or opinion on a problem or object by someone, whether it tends to have a positive or negative opinion. This study aims to classify tweet data into 2 classifications, namely positive and negative. In this study, Indonesian text is used on Twitter social media in the form of tweets related to Tokopedia. Public opinion contained in the tweet can be used as material to find out whether tweets on Twitter, especially on Tokopedia, are classified as positive or negative. The data used consists of 1,000 tweet data. This dataset comes from the tweets of Tokopedia customers written on the Tokopedia twitter account. In text mining techniques, “transform case”, “tokenize”, “token filter by length”, “stemming” are used to build classifications. Gataframework is used to help during the preprocessing and cleansing process. RapidMiner is used to help create sentiment analysis in comparing three different classification methods, on Tokopedia's tweet data. The method used to compare in this research is the Naïve Bayes algorithm and the Naïve Bayes algorithm which is added with the Synthetic Minority Over-sampling Technique (SMOTE) feature and the Naïve Bayes algorithm is added with the Synthetic Minority Over-sampling Technique (SMOTE) feature which is optimized with Adboost. . The Naïve Bayes algorithm added with the Synthetic Minority Over-sampling Technique (SMOTE) feature, which was optimized with Adboost, got the best score. With 94.95% accuracy, 90.86% precision, 100.00% recall and 0.950 AUC
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.
Text Mining untuk Sentimen Analisis dengan Metode Naïve Bayes, SMOTE, N-Gram dan AdaBoost Pada Twitter CommuterLine Putra, Andreyana Pratama; Pratama, Yuda; Krisnadi, Eka Kharisma; Purnamasari, Indah; Saputra, Dedi Dwi
J-SAKTI (Jurnal Sains Komputer dan Informatika) Vol 6, No 2 (2022): EDISI SEPTEMBER
Publisher : STIKOM Tunas Bangsa Pematangsiantar

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30645/j-sakti.v6i2.506

Abstract

In the current era, the development of information technology and social media is growing rapidly so that it can provide updated information and various kinds of public opinion. Many internet users in Indonesia use social media for various purposes, such as seeking information and expressing opinions through social media. One of the social media that is widely used by internet users in Indonesia is Twitter. Twitter users can provide information in the form of comments, criticisms, or suggestions for Comutterline services more quickly and easily. Sentiment analysis can help provide an overview of public perception by grouping opinions into positive and negative categories for Commuterline services. Conducting sentiment analysis based on comments or Tweets from the community on Twitter Commuterline to determine the performance of the Naïve Bayes Classifier algorithm, Synthetic Minority Over-sampling Technique (SMOTE), AdaBoost, and N-Gram so that machine learning implementation can help identify public opinion conveyed through Twitter automatically into positive and negative categories. The use of the Naïve Bayes Classifier, Synthetic Minority Over-sampling Technique (SMOTE), AdaBoost, and N-Gram methods which are considered better to generate predictions on tweets sent by CommuterLine users
Optimasi Analisis Sentimen Pada Twitter Olshop Tokopedia Menggunakan Textmining Dengan Algoritma Naïve Bayes & Adaboost Hartati, H; Hermawan, Deni; Akhsanal, M.; Wahyudi, Zailani; Ariyanto, Angga; Saputra, Dedi Dwi
J-SAKTI (Jurnal Sains Komputer dan Informatika) Vol 6, No 2 (2022): EDISI SEPTEMBER
Publisher : STIKOM Tunas Bangsa Pematangsiantar

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30645/j-sakti.v6i2.493

Abstract

Sentiment Analysis or commonly called Opinion Mining is the process of understanding, extracting and processing textual data automatically to obtain sentiment information contained in a sentence of opinion or opinion on a problem or object by someone, whether it tends to have a positive or negative opinion. This study aims to classify tweet data into 2 classifications, namely positive and negative. In this study, Indonesian text is used on Twitter social media in the form of tweets related to Tokopedia. Public opinion contained in the tweet can be used as material to find out whether tweets on Twitter, especially on Tokopedia, are classified as positive or negative. The data used consists of 1,000 tweet data. This dataset comes from the tweets of Tokopedia customers written on the Tokopedia twitter account. In text mining techniques, “transform case”, “tokenize”, “token filter by length”, “stemming” are used to build classifications. Gataframework is used to help during the preprocessing and cleansing process. RapidMiner is used to help create sentiment analysis in comparing three different classification methods, on Tokopedia's tweet data. The method used to compare in this research is the Naïve Bayes algorithm and the Naïve Bayes algorithm which is added with the Synthetic Minority Over-sampling Technique (SMOTE) feature and the Naïve Bayes algorithm is added with the Synthetic Minority Over-sampling Technique (SMOTE) feature which is optimized with Adboost. . The Naïve Bayes algorithm added with the Synthetic Minority Over-sampling Technique (SMOTE) feature, which was optimized with Adboost, got the best score. With 94.95% accuracy, 90.86% precision, 100.00% recall and 0.950 AUC
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