cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Safriadi
Contact Email
safriadi@pnl.ac.id
Phone
+6285262485087
Journal Mail Official
jaise@pnl.ac.id
Editorial Address
Jl. Banda Aceh-Medan Km. 280,3, Buketrata, Mesjid Punteut, Blang Mangat, Kota Lhokseumawe, 24301
Location
Kota lhokseumawe,
Aceh
INDONESIA
Journal Of Artificial Intelligence And Software Engineering
Published by Politeknik Negeri Lhokseumawe
ISSN : 2797054X     EISSN : 2777001X     DOI : http://dx.doi.org/10.30811/jaise
Core Subject : Science,
Computer Science & IT
Artificial Intelligence Natural Language Processing Computer Vision Robotics and Navigation Systems Decision Support System Implementation of Algorithms Expert System Data Mining Enterprise Architecture Design & Management Software & Networking Engineering IoT
Arjuna Subject : Ilmu Komputer (semua kategori) - Aplikasi Ilmu Komputer
Articles 44 Documents
 1   2   3   4   5 
Search results for , issue "Vol 5, No 3 (2025): September" : 44 Documents clear
Sentiment Analysis of Fans Toward Brand Merchandise Releases Using Support Vector Machine (SVM) Munaiseche, Christian Imanuel; Nurchim, Nurchim; Cipto Utomo, Bangun Prajadi
Journal of Artificial Intelligence and Software Engineering Vol 5, No 3 (2025): September
Publisher : Politeknik Negeri Lhokseumawe

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30811/jaise.v5i3.7264

Abstract

The release of merchandise by idol groups often sparks various emotional reactions among fans, particularly on social media platforms. This study investigates fan sentiment regarding the birthday merchandise release by JKT48 members on the X (Twitter) platform using the Support Vector Machine (SVM) algorithm. A total of 1,062 comments were collected using the Tweet Harvest tool and manually categorized into three sentiment classes: positive, neutral, and negative. The collected data underwent several pre-processing stages, including case folding, data cleansing, tokenization, and stopword removal. The text data were then transformed into numerical features using the Term Frequency-Inverse Document Frequency (TF-IDF) method. To address the class imbalance issue, the Synthetic Minority Over-sampling Technique (SMOTE) was applied. Experimental results show that the SVM model without SMOTE achieved an accuracy of 84.62% and an F1-score of 76.79%. After applying SMOTE, model performance improved significantly, with accuracy reaching 90.09% and F1-score increasing to 90.15%. Furthermore, the results of 5-fold cross-validation confirmed the positive impact of SMOTE in enhancing the model's ability to classify sentiment, particularly for underrepresented classes.
Implementation of the K-Nearest Neighbor (K-NN) Algorithm for Predicting Bestseller of Religious Books Jamil, Alfan; Hermanto, Hermanto; Fajriyanto, Fajriyanto
Journal of Artificial Intelligence and Software Engineering Vol 5, No 3 (2025): September
Publisher : Politeknik Negeri Lhokseumawe

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30811/jaise.v5i3.7352

Abstract

The development of information technology provides significant opportunities in data management to help make more accurate business decisions. One method used is data mining, especially the K-Nearest Neighbor (K-NN) technique which is quite effective in classification and forecasting based on past data. This study aims to apply the K-NN technique to predict sales of the most popular books and scriptures at the Assyarif Book Store, located at the Salafiyah Syafi'iyah Islamic Boarding School in Sukorejo. It is hoped that this method can help in planning stock and identifying products that are most in demand by customers. This study uses a quantitative approach with observation, interviews, and documentation collection methods. The data used include price, quantity sold, initial stock, and final stock. The results of the analysis using Euclidean Distance show that the K-NN technique is able to predict sales categories (best-selling or not-selling) with an accuracy level of 75% obtained from cross-validation testing, so it can be an effective solution to support sales management and data-based decisions.
Decision Support System for PNBP Proposal Selection Using the Simple Multi-Attribute Rating Technique Suhada, Intan; Putra, Fajri Profesio
Journal of Artificial Intelligence and Software Engineering Vol 5, No 3 (2025): September
Publisher : Politeknik Negeri Lhokseumawe

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30811/jaise.v5i3.6964

Abstract

Non-Tax State Revenue (PNBP) is one of the key funding sources at Politeknik Negeri Bengkalis, managed by the Center for Research and Community Service (P3M). The proposal selection process often encounters issues related to objectivity and transparency. This study aims to develop a Decision Support System (DSS) based on the Simple Multi-Attribute Rating Technique (SMART) method to improve the efficiency and accuracy of proposal selection. The system wasdeveloped as a web-based application and tested on 12 proposals. The evaluation criteria include Problem Formulation, Research Output Potential, Research Methodology, Literature Review, and Research Feasibility. The test results showed a compatibility rate of 83.33%,where 10 proposals had identical rankings, and 2 proposals differed by one rank compared to manual assessments by P3M. The scoring was conducted through weight normalization, utility value calculation, and final score aggregation. System evaluation using the Blackbox Testingmethod demonstrated that all core functions operated correctly for three user types (admin, reviewer, and user) without any detected errors. The system successfully produces selection results that closely match real-world conditions and contributes to enhancing objectivity, transparency, and the overall quality of the PNBP proposal selection process.
Developing an NLP-Based Chatbot for Waste Management Education in Sungailiat Wisesa, Bradika Almandin; Mahat Putri, Vivin; Faristasari, Evvin; Jasman Duli, Sirlus Andreanto; Lionza, Rahmat
Journal of Artificial Intelligence and Software Engineering Vol 5, No 3 (2025): September
Publisher : Politeknik Negeri Lhokseumawe

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30811/jaise.v5i3.7522

Abstract

Penelitianinimemaparkanpengembangan dan evaluasi menyeluruh terhadap chatbot berbasis Natural Language Processing (NLP) yang dirancang untuk meningkatkan pendidikan pengelolaan sampah di Bank Sampah Sungailiat, Indonesia. Dengan mengintegrasikan logika fuzzy untuk pencocokan Pertanyaan yang Sering Diajukan (FAQ) secara akurat dan memanfaatkan model NLP berbasis transformer, DialoGPT-medium, chatbot inimemberikan respons yang relevan secara kontekstual terhadap pertanyaan pengguna mengenaioperasional bank sampah, termasuk pemilahan sampah, proses daur ulang, dan insentif ekonomi. Penelitian ini menangani masalah rendahnya kesadaran masyarakat terhadap praktik pengelolaan sampah yang tepat, yang menghambat partisipasi efektif dalam program daurulang. Sistem hibrida ini mencapai akurasi respons sebesar 85% dalam p engujian pengguna, divalidasi melalui analisis matriks konfusi yang mendetail. Temuan utama menunjukkan peningkatan signifikan dalam keterlibatan pengguna, retensi pengetahuan, dan kesadaran masyarakat, menunjukkan potensi chatbot sebagai solusi pendidikan lingkungan yang berbasis teknologi dan dapat diskalakan untuk konteks serupa di seluruh Indonesia

Page 5 of 5 | Total Record : 44

 1   2   3   4   5 

Filter by Year

2025 2025


Reset
Filter By Issues
All Issue Vol 5, No 4 (2025): Desember (On Progress) Vol 5, No 3 (2025): September Vol 5, No 2 (2025): Juni On-Progress Vol 5, No 2 (2025): June Vol 5, No 1 (2025): March Vol 5, No 1 (2025): Maret Vol 4, No 2 (2024) Vol 4, No 1 (2024) Vol 3, No 2 (2023) Vol 3, No 1 (2023) Vol 2, No 2 (2022) Vol 2, No 1 (2022) Vol 1, No 2 (2021) Vol 1, No 1 (2021) More Issue