Claim Missing Document
Check
Articles

Found 17 Documents
Search

Unilever’s Customer Data Management Information System in Medan City and Approaches to Android Smartphone and IoT Flexibility Purba, Windania
Internet of Things and Artificial Intelligence Journal Vol. 1 No. 3 (2021): Volume 1 Issue 3, 2021 [August]
Publisher : Association for Scientific Computing, Electronics, and Engineering (ASCEE)

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (943.269 KB) | DOI: 10.31763/iota.v1i3.497

Abstract

A web application is a type of application that uses browser technology to run an application accessed via a mobile network. In this case, the web application can also assist in collecting customer data, especially those carried out by Unilever companies, where the system is quite efficient and accurate in collecting customer data. This system also makes it easier for companies engaged in data collection. In this case, the employees can easily record every customer and see the number of products used and selling well in the market. This is where the Unilever company will know how many products will continue to be produced and marketed. Furthermore. This paper discusses the development plan for this W.E.B. application towards Smartphone mode and development towards the Internet of Things for flexibility when accessing and getting data in real-time.
COMPARATIVE ANALYSIS OF PSO AND FIREFLY OPTIMIZATION FOR VIOLENCE REPORT CLASSIFICATION Wijaya, Ryo; Juanta, Palma; Simson, Erick; Ricky, Ricky; Purba, Windania
JIKO (Jurnal Informatika dan Komputer) Vol 8, No 2 (2025)
Publisher : Universitas Khairun

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33387/jiko.v8i2.9721

Abstract

Cases of violence against children and women continue to increase, but the handling of reports is often hampered by the large volume of incoming reports and the lengthy manual classification process. This study aims to address these issues by developing a method for automatically classifying reports of violence using the Support Vector Machine (SVM) algorithm optimized with Particle Swarm Optimization (PSO) and Firefly algorithms. The main objective is to group types of violence accurately to facilitate faster and more effective identification and handling. The research dataset consists of 500 reports obtained from Kaggle, with stages including text pre-processing, implementation of optimization algorithms, and evaluation based on accuracy, precision, recall, and misclassification error. The experiments were conducted using Python on the Google Colab platform. The results showed that PSO-SVM achieved an accuracy of 87.00% and a recall of 80.42%, outperforming Firefly-SVM which achieved an accuracy of 86.00% and a recall of 78.75%. Although Firefly-SVM demonstrated slightly higher precision (92.63%) compared to PSO-SVM (91.53%), PSO-SVM had a lower misclassification error (13.00% compared to 14.00%). These findings indicate that PSO-SVM is more effective for applications requiring better case detection, while Firefly-SVM is more suitable for applications prioritizing precision in positive predictions.
PERBANDINGAN ALGORITMA NAIVE BAYES & K-NEAREST NEIGHBORS (KNN) DALAM ANALISIS SENTIMEN ULASAN PRODUK TOKOPEDIA Purba, Windania; Turnip, Charles Fransisco; Malau, Josua Heksa Parti; Halawa, Berkat Editar Jaya
Jurnal Teknik Informasi dan Komputer (Tekinkom) Vol 8 No 1 (2025)
Publisher : Politeknik Bisnis Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37600/tekinkom.v8i1.1983

Abstract

This study conducts a comparative performance analysis of two widely utilized classification algorithms, Naive Bayes and K-Nearest Neighbors (KNN), in the context of customer satisfaction analysis based on product reviews from the Tokopedia e-commerce platform. Customer-generated reviews serve as a critical factor in shaping product reputation and perceived quality, while also influencing the purchasing behavior of prospective buyers.The methodology encompasses data collection of product reviews from Tokopedia, followed by a comprehensive preprocessing pipeline, including text cleaning, tokenization, and stemming. The processed reviews are then categorized into two sentiment classes-positive and negative-employing both Naive Bayes and KNN algorithms.The performance of these algorithms is evaluated using standard classification metrics: accuracy,recall,F1-score dan precision. Empirical results demonstrate that Naive Bayes yields superior accuracy in classifying product sentiments compared to KNN.This research offers practical insights for e-commerce businesses in selecting suitable machine learning techniques for sentiment analysis to better understand customer feedback and enhance satisfaction. Moreover, the study contributes to the academic discourse by highlighting the strengths and limitations of each algorithm, and provides recommendations for future research in developing effective sentiment classification frameworks for customer satisfaction measurement.
ANALISIS SENTIMEN TERHADAP MOBIL LISTRIK MENGGUNAKAN METODE BERT DAN NER Purba, Windania; Panjaitan, Syahdani; Dahlim, Alvin; Ambarita, Bless Alget; Zendrato, Febriaman
Jurnal Teknik Informasi dan Komputer (Tekinkom) Vol 8 No 1 (2025)
Publisher : Politeknik Bisnis Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37600/tekinkom.v8i1.1984

Abstract

Air pollution from fossil fuel-powered vehicles poses serious health risks. To reduce greenhouse gas emissions, electric vehicles (EVs) have emerged as a greener alternative. However, EV adoption in Indonesia still struggles, mainly due to low public acceptance. This study analyzes Indonesian public sentiment toward EVs and the key factors influencing it, using Natural Language Processing (NLP) with BERT for sentiment classification and Named Entity Recognition (NER) for identifying important entities. The BERT model performed well, with 71.71% accuracy, 83.56% precision, 71.71% recall, 75.59% F1-score, and a misclassification error of 28.29%, outperforming Naïve Bayes and LSTM. Sentiment analysis found that 48.45% of the public expressed negative sentiment, 30.60% neutral, and only 20.95% positive. NER identified influential factors including public events, opinions, company reputation, product quality, pricing, and location.These findings offer important insights for policymakers and industry players in designing strategies to boost EV adoption in Indonesia.
PERBANDINGAN ALGORITMA NAIVE BAYES DAN K-NEAREST NEIGHBORS DALAM ANALISIS SENTIMEN ULASAN PRODUK TOKOPEDIA Purba, Windania; Panjaitan, Markus Sahat Maruli; Dawner, Elgin; Lumbantoruan, Marselina Dahlia H.
Jurnal Teknik Informasi dan Komputer (Tekinkom) Vol 8 No 1 (2025)
Publisher : Politeknik Bisnis Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37600/tekinkom.v8i1.1985

Abstract

This study aims to classify public opinions on educational issues expressed through the social media platform Twitter using the Naïve Bayes Classifier algorithm. This method was chosen due to its capability to categorize text data into positive, negative, and neutral sentiment categories based on the assumption of attribute independence. The data used consists of a collection of tweets relevant to the topic of education, which were analyzed through the stages of preprocessing, feature extraction, classification, and model evaluation. The results of the study indicate that the model is able to classify opinions with an accuracy of 73% based on the Confusion Matrix. Further analysis shows a precision of 85% for the positive category, 79% for negative, and 88% for neutral, while the recall for the positive category reached 77%. These findings suggest that the Naïve Bayes algorithm is fairly effective in processing public opinion from social media and can serve as a reference for understanding public perceptions regarding educational issues.
The Design of a Website-Based Motorcycle Installment Bill Check Application at Indah Motor KM.5 Purba, Windania; Sihombing, Irsan Jaya; Sidabutar, Ayu Elpriyani; Siahaan, Nur Ainun
Journal of Computer Networks, Architecture and High Performance Computing Vol. 3 No. 2 (2021): Journal of Computer Networks, Architecture and High Performance Computing, July
Publisher : Information Technology and Science (ITScience)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47709/cnahpc.v3i2.1010

Abstract

Looking at current developments, many activities have implemented the capabilities and advantages of technology in them so that the operational costs, time and energy needed can be found. This technological development also develops this technology also creates needs in the community and even new needs. Along with the need for credit is one alternative carried out by the community and business entities to obtain something with the aim of meeting their needs. This credit or installment activity also does not rule out the possibility of being applied to this type of motorcycle sales business, because in reality the need for motorcycles is currently important and has a high level of demand so that some motorcycle sales provide a payment system for motorcycles that are designed to improve performance. and quality of service, the community needs flexibility to speed up payment for motorbikes that are being sold in installments. From the research that has been done as mentioned above, the author intends to carry out development in terms of installment implementation into a website-based application, so the author takes the title "Designing a Website-Based Motorcycle Installment Bill Check Application at Indah Motor Km.5". From the problems that occur, the researcher intends to simplify credit or installment problems into a website that can make it easier for admins to process and solve problems that apply in the community.
Pelatihan dan Pengolahan Kemiri Di Desa Haranggaol Purba, Windania; Sari, Roza Maya
Jurnal Mitra Prima Vol. 1 No. 1 (2019): Jurnal Mitra Prima
Publisher : Mitra prima

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Desa Haranggaol merupakan salah satu sentra penghasil bawang merah terbesar yang berada di, kabupaten Simalungun, provinsi Sumatra Utara, Indonesia., Tujuan dari kegiatan pengabdian ini adalah memberikan pelatihan tentang pengolahan bawang merah menjadi produk siap konsumsi dengan BACRIS sebagai Mitra Industri. Materi kegiatan yang diberikan yaitu tentang pengolahan dan pemrosesan bawang merah menjadi produk siap konsumsi serta cara pemasaran produk siap konsumsi melalui e-commerse. Kegiatan pengabdian kepada Masyarakat (PKM) yaitu meliputi (1) observasi; (2) sosialisasi; (3) pelatihan dan praktik bawang merah menjadi produk siap konsumsi; (4) pemasaran (5) monitoring. Kegiatan ini bermanfaat untuk meningkatkan penghasilan petani bawang merah, hal ini karena bawang merah menjadi produk bawang goreng berkualitas tinggi dengan harga jual yang stabil, sehingga petani bawang merah tidak akan merugi jika hasil panen yang dihasilkan memiliki kualitas yang rendah.