Article Per Year (5 Year)
p-Index From 2021 - 2026
0.817
P-Index
This Author published in this journals
All Journal Jurnal Informatika Upgris Jambura Journal of Electrical and Electronics Engineering Jurnal Ilmiah Ilmu Komputer Banthayo Lo Komputer (BALOK)
Mustofa, Yasin Aril
Unknown Affiliation
Computer Science & IT Control & Systems Engineering Electrical & Electronics Engineering Energy Engineering

Published : 4 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 4 Documents
Search

 1 
Analisis Sentimen Terhadap Data Kuisioner Evaluasi Dosen Menggunakan Algoritma Naïve Bayes Puspita Sari Jan, Sitti Rachmah; Mustofa, Yasin Aril; Idris, Irma Surya Kumala
Jurnal Informatika UPGRIS Vol 9, No 2: Desember 2023
Publisher : Universitas PGRI Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26877/jiu.v9i2.17001

Abstract

Students' satisfaction with the quality of lecturers' way of teaching is oneof theimportant things in higher education institutions. Universitas Ichsan Gorontalo hasimplemented an online questionnaire as student feedback to determine and evaluatethe performance of lecturers. The Faculty of Computer Science is one of the facultiesthathasimplementedthequestionnairefillingsystem.Thequestionnaireismandatoryfor all students as a requirement to join a course contract at the beginning of thesemester. The evaluation of the performance of lecturers during lectures has a veryimportantrole.Itimprovesthequalityoflearningandacademicstandardization.Thisstudy aims to determine the level of student satisfaction with the services of lecturerswhen teaching. This study applies sentiment analysis using the Naïve Bayes Classifierclassificationmethod.ItalsoemploystheweightingmethodusingtheTermFrequency-Inverse Document Frequency (TF-IDF). The results of this study have determined theclassification of the lecturer service questionnaire data. The results are easy to read.Theresultsofthesurveyonthelevelofstudentsatisfactionwithlecturerservicesfrom1,989dataindicatethat1,946datahavepositivesentimentsand43datahavenegativesentiments.TheresultsgainedfromtheNaïve Bayesaccuracy is 97%accuracy.
Ensemble Approach to Sentiment Analysis of Google Play Store App Reviews Mustofa, Yasin Aril; Idris, Irma Surya Kumala
Jambura Journal of Electrical and Electronics Engineering Vol 6, No 2 (2024): Juli - Desember 2024
Publisher : Electrical Engineering Department Faculty of Engineering State University of Gorontalo

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37905/jjeee.v6i2.25184

Abstract

In the current digital era, sentiment analysis of Google Play Store application reviews has become a critical key to understanding public opinion on technology products. This study aims to evaluate the effectiveness of ensemble approaches in sentiment analysis compared to individual classification algorithms. The methods employed include ensemble techniques such as Random Forest and Boosting, along with individual algorithms like Naive Bayes and Support Vector Machine (SVM). This research incorporates extensive preprocessing steps, including cleaning, case folding, tokenization, stopword removal, and normalization, to prepare the data before classification. The results demonstrate that ensemble models, particularly Random Forest, achieve superior performance in sentiment classification of app reviews, with accuracy reaching 94.15% for Zoom app reviews and 80.69% for Shopee app reviews. This performance confirms that ensemble approaches are more effective in handling the complexity and variability of review data compared to individually operated algorithms. The study provides valuable insights for application developers to enhance their products based on user feedback. However, there is still room for improvement in terms of optimizing algorithms for highly unbalanced data and developing methods that can handle more complex language nuances. Recommendations for future research include the use of Deep Learning techniques and cross-domain testing to assess the effectiveness of these models in various sentiment analysis settings.
Analisis Sentimen Terhadap Penggunaan Aplikasi Shopee Mengunakan Algoritma Support Vector Machine (SVM) Idris, Irma Surya Kumala; Mustofa, Yasin Aril; Salihi, Irvan Abraham
Jambura Journal of Electrical and Electronics Engineering Vol 5, No 1 (2023): Januari - Juni 2023
Publisher : Electrical Engineering Department Faculty of Engineering State University of Gorontalo

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37905/jjeee.v5i1.16830

Abstract

Analisis Sentimen merupakan cabang dari penelitian text mining yang melakukan proses pengklasifikasian dokumen teks. Analisis sentimen dapat melakukan ekstraksi pendapat, emosi, dan evaluasi tertulis seseorang tentang topik tertentu menggunakan teknik pemrosesan Bahasa alami. Pada penelitian ini melakukan analisis sentiment terhadap penggunaan aplikasi Shopee menggunakan algoritma Support Vector Machine (SVM). Tujuan dari penelitian ini adalah untuk mengklasifikasi data komentar dari pengguna aplikasi Shopee kedalam komentar positif dan negatif dengan mempelajari pendapat pengguna tentang aplikasi Shopee melalui ulasan yang diberikan, dan untuk mengetahui kinerja dari metode pengklasifikasi yang digunakan. Pada penelitian ini data diperoleh dengan cara mengangkat data dari ulasan penggunakan aplikasi Shopee menggunakan metode scraping dan berhasil mendapat 3000 data ulasan. Hasil penelitian menggunakan algoritma Support Vector Machine terbukti mampu menghasilkan kinerja yang cukup baik dengan hasil akurasi sebesar 98% dan f1-score sebesar 0.98 atau sebesar 98%.Sentiment analysis is a branch of text mining research that carries out the process of classifying text documents. Sentiment analysis can extract one's opinions, emotions, and evaluations about a certain topic using natural language techniques. In this study, sentiment analysis was carried out on the use of the Shopee application using the Support Vector Machine (SVM) algorithm. The purpose of this study is to classify comment data from Shopee application users, positive and negative comments by studying user opinions about the Shopee application through the reviews provided, and to determine the performance of the classifier method used. In this study, the data was obtained by collecting data from reviews on the use of the Shopee application using the scraping method and managed to get 3000 data reviews. The results of research using the Support Vector Machine algorithm are proven to be able to produce quite good performance with an accuracy of 98% and an f1-score of 0.98 or 98%. 
Game Edukasi Menyusun Nama Hewan Sebagai Media Pembelajaran Anak-Anak Menggunakan Construct 2 Pontoh, Iftahul Farhan; Mustofa, Yasin Aril; Lamasigi, Zulfrianto Yusrin
Jurnal Ilmiah Ilmu Komputer Banthayo Lo Komputer Vol 4 No 2 (2025)
Publisher : Teknik Informatika Fakultas Ilmu Komputer Universitas Ichsan Gorontalo

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37195/balok.v4i2.900

Abstract

This research aims to develop an educational game to provide alternative learning and knowledge about animals and their types. The problem faced is the lack of interest and understanding of children's conventional learning materials that tend to be monotonous and non-interactive, which often results in decreased motivation to learn at home and school. To overcome this problem, an educational game application using Construct 2 software. The stages include system testing, development, construction, design, and analysis. This research takes place at SD Negeri 03 Kabila, engaging 30 students as respondents. The assessment of the game is carried out through a questionnaire analyzed descriptively and qualitatively to assess the feasibility of the application. The test results show that the application is free from component errors based on Black Box testing and is well received by users based on User Acceptance testing with a total score of 86.4%, categorized as very good. However, the random system used to generate the questions reappears which can reduce the variety and effectiveness of learning. The improvements to this system are proposed to enhance the learning quality. The development of this educational game application can be an effective solution to increase children's interest and understanding in learning while providing a fun learning experience while providing a fun and interactive learning experience.Keywords: educational game, Construct 2, animal recognition
Co-Authors Idris, Irma Surya Kumala Pontoh, Iftahul Farhan Puspita Sari Jan, Sitti Rachmah Salihi, Irvan Abraham Zulfrianto Yusrin Lamasigi