Article Per Year (5 Year)
p-Index From 2020 - 2025
1.037
P-Index
This Author published in this journals
All Journal Techno Nusa Mandiri : Journal of Computing and Information Technology Inspiration: Jurnal Teknologi Informasi dan Komunikasi Jurnal Manuhara: Pusat Penelitian Ilmu Manajemen Dan Bisnis
Dedi Dwi Saputra
Unknown Affiliation
Computer Science & IT Decision Sciences, Operations Research & Management Economics, Econometrics & Finance

Published : 5 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 5 Documents
Search

 1 
SENTIMENT ANALYSIS ON TWITTER SOCIAL MEDIA ACCOUNTS: SHOPEECARE USING NAIVE BAYES, ADABOOST, AND SVM(EVOLUTION) ALGORITHM COMPARATIVE METHODS Rizky Nugraha Pratama; Ghina Amanda Kamila; Kresna Lazani T; Ilham Fauzi; Muhammad Reynaldo Oktaviano; Dedi Dwi Saputra
Jurnal Techno Nusa Mandiri Vol 19 No 1 (2022): Techno Nusa Mandiri : Journal of Computing and Information Technology Period of
Publisher : Lembaga Penelitian dan Pengabdian Pada Masyarakat

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33480/techno.v19i1.3086

Abstract

The growth of Indonesian e-commerce is increasing along with the growth of internet use in Indonesia. In 2015, there were 92 million internet users in Indonesia. One of the popular online shopping platforms in Indonesia is Shopee. One of the services to see the response and reporting of problems from users, including shopeecare. shopeecare was created on the social media platform twitter to help facilitate communication between customers. with the amount of customer enthusiasm in tweeting and Retweeting existing content, we decided to research about Sentiment analysis on twitter social media accounts: Shopeecare uses the SMOTE NB, ADboost, and SVM comparison methods. From the data, the comparison results from the test experiments used the Smote + Naive Bayes, Smote + Naive Bayes + Adaboost, and Smote + SVM models. It is known that the Accuracy, Precision, AUC values of the Smote + SVM algorithm are higher than other algorithms, namely Accuracy 76.24%, Precision 75.65%, AUC 0.822. From the results of the algorithm comparison, it shows that the algorithm in determining the sentiment of the complaint and not complaint analysis is better than other algorithms.
COMPARING ALGORITHM FOR SENTIMENT ANALYSIS IN HEALTHCARE AND SOCIAL SECURITY AGENCY (BPJS KESEHATAN) ASYHARUDIN ASYHARUDIN; Novi Kusumawati; Ulfah Maspupah; Destia Sari R.F.; Amir Hamzah; Duwik Lukito; Dedi Dwi Saputra
Jurnal Techno Nusa Mandiri Vol 19 No 1 (2022): Techno Nusa Mandiri : Journal of Computing and Information Technology Period of
Publisher : Lembaga Penelitian dan Pengabdian Pada Masyarakat

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33480/techno.v19i1.3167

Abstract

Twitter is a social media that can be used to express opinions and exchange information quickly with individuals and institutions such as the Healthcare and Social Security Agency (BPJS Kesehatan). Every word that a Twitter user utters has meaning and stellar emotion. This meaning can be reached through the process of sentiment analysis. Sentiment analysis is the process of understanding and classifying emotions such as positive or negative or complaining or not complaining. This study classifies tweet data related to BPJS Health services into two classifications, namely complain and no complain. Using 1,000 data from Twitter written on the BPJS Kesehatan Twitter account. In text mining, to build a classification, the transform case, tokenize, token filter by length, stemming and stopword techniques are used. Gataframework is used to assist the preprocessing and cleansing process. Rapidminer was used to create sentiment analysis in comparing three different classification methods of the Twitter data. The method used is the Nave Bayes algorithm and the Naïve Bayes algorithm with the addition of a Synthetic Minority Over-sampling Technique (SMOTE) feature and the Naïve Bayes algorithm with an SMOTE feature that is optimized with Adaboost. The Naïve Bayes algorithm is added with the SMOTE feature which is optimized with Adaboost to get the best value with an accuracy value of 69.11%, precision 69.93%, recall 68.89% and AUC 0.770
Software Defect Prediction For Quality Evaluation Using Learning Techniques Ensemble Stacking Kusuma, Muhammad Romadhona; Windu Gata; Sigit Kurniawan; Dedi Dwi Saputra; Supriadi Panggabean
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.v13i2.58

Abstract

This research aims to improve the software quality and effectiveness of zakat management by the National Amil Zakat Agency (BAZNAS) through the development of a software defect prediction model (SDPM). We used machine learning techniques and ensemble stacking approach on the "Masjid Tower" dataset containing 228 records and 34 attributes. The preprocessing process involved label encoding, feature selection with Pearson correlation, standard normalization, and the use of SMOTE to handle data imbalance. We performed hyperparameter tuning with grid search CV on Machine Learning algorithms such as Ada Boost and Gradient Boosting. The results showed that the ensemble stacking approach with a combination of Gradient Boosting, Ada Boost, Decision Tree, Bayesian Ridge, and LightGBM meta learner algorithms provided high accuracy with R2 score reaching 0.97, MAE of 0.037, and MSE of 0.006. This finding proves that the ensemble stacking approach is able to overcome the problem of software defects with accurate prediction results, provide useful guidance in the management of zakat and other software applications, and has the potential to improve software quality and the effectiveness of BAZNAS in managing zakat.
Indonesian Government Revenue Prediction Using Long Short-Term Memory Mahmud; Windu Gata; Hafifah Bella Novitasari; Sigit Kurniawan; Dedi Dwi Saputra
Inspiration: Jurnal Teknologi Informasi dan Komunikasi Vol. 14 No. 1 (2024): 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.v14i1.67

Abstract

Government revenue plays an important role in achieving national development goals. In the context of optimal state treasury management, accurate forecasts of government revenue are needed so that cash can be utilized optimally for the coming period. This study examines the appropriate method for predicting government revenue based on historical data from 2013 to 2022. It proposes applying the Long Short-Term Memory (LSTM) model for this purpose. Experiments show that the LSTM model, using two hidden layers and the right hyperparameters, can produce a Mean Absolute Percentage Error (MAPE) of 11.14% and a Root Mean Square Error (RMSE) of 15.43%. These results are better than those obtained using conventional modeling techniques such as Autoregressive Integrated Moving Average (ARIMA) and Seasonal Autoregressive Integrated Moving Average (SARIMA). The findings indicate that the LSTM model offers superior predictive accuracy and can significantly improve the management of government finances. By implementing this advanced predictive model, policymakers can make more informed decisions, enhancing the efficiency of resource allocation and contributing to the overall economic stability of the nation.
Studi Pengaruh Kemudahan Akses Aplikasi dan Kualitas Layanan terhadap Kepuasan Pelanggan Shopee Food Ani Nuriska Safitri; Mawalda Azharah; Khiyarana Fayziyah; Nadia Septia Aisyah; Antonius Yadi kuntoro; Riza Fahlapi; Dedi Dwi Saputra; Hermanto Hermanto; Taufik Asra
Jurnal Manuhara : Pusat Penelitian Ilmu Manajemen dan Bisnis Vol. 3 No. 3 (2025): Jurnal Manuhara: Pusat Penelitian Ilmu Manajemen dan Bisnis
Publisher : Asosiasi Riset Ilmu Manajemen Kewirausahaan dan Bisnis Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.61132/manuhara.v3i3.1926

Abstract

The development of information and communication technology in Indonesia has driven the rapid growth of app-based food delivery services, such as ShopeeFood. The ease of using the application and the quality of service are key factors influencing user satisfaction in utilizing this service. This study aims to analyze the influence of application ease of use and service quality on ShopeeFood user satisfaction in Depok. A quantitative approach was used, with primary data collected through questionnaires distributed to 100 respondents. The data was processed using SPSS by conducting data quality tests, classical assumption tests, t-tests, and F-tests. Based on the research findings, it was concluded that both application ease of use and service quality have a significant influence on user satisfaction, both individually (partially) and jointly (simultaneously). The t-value for ease of use was 6.576 and for service quality was 4.929, both exceeding the t-table value of 1.984 with a significance level of 0.000. Simultaneously, the F-value of 37.967 also indicates a significant influence.
Co-Authors Ani Nuriska Safitri Antonius Yadi Kuntoro ASYHARUDIN ASYHARUDIN Destia Sari R.F. Duwik Lukito Gata, Windu Ghina Amanda Kamila Hafifah Bella Novitasari Hermanto Hermanto I Gusti Bagus Wiksuana Ilham Fauzi Khiyarana Fayziyah Kresna Lazani T Kusuma, Muhammad Romadhona Mawalda Azharah Muhammad Reynaldo Oktaviano Nadia Septia Aisyah Novi Kusumawati Riza Fahlapi Rizky Nugraha Pratama Sigit Kurniawan Siti Helmyati Supriadi Panggabean Taufik Asra Ulfah Maspupah