Claim Missing Document
Check
Articles

Found 17 Documents
Search

Analisis Sentimen Komentar Pengguna Aplikasi Threads Pada Google Playstore Menggunakan Algoritma Multinominal Naive Bayes Classfier Muhammad Nur Akbar; Nirwana Samrin
AGENTS: Journal of Artificial Intelligence and Data Science Vol 3 No 2 (2023): Maret - Agustus
Publisher : Prodi Teknik Informatika Universitas Islam Negeri Makassar

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24252/jagti.v3i2.67

Abstract

The advancement of technology, especially internet and social media technology, has enabled people across the country to connect and interact with each other. In this context, Instagram has become a popular platform for content creators to share their work. In an effort to compete with other platforms, Instagram launched an integrated app called Threads, which shares some features similar to Twitter. Threads allows users to share text-based posts and provides various other features. To enhance the quality of this application, developers need to review user comments. However, the influx of comments is substantial, making manual review inefficient. Therefore, an automated application is required to categorize comments and analyze user sentiment. By utilizing text mining techniques for sentiment analysis, developers can easily sort comments into positive and negative categories. Multinomial Naive Bayes was chosen as it's specifically designed for data with frequency occurrences, such as in text analysis. It is expected that this application can assist developers in improving the quality of the generated app. From the results of this study, an accuracy of 76% was achieved, which is  relatively good and offers potential for further development to attain better results.
KLASIFIKASI BIBLIOGRAFI OTOMATIS MENGGUNAKAN C4.5 DAN INFORMATION GAIN AKBAR, MUHAMMAD NUR
Jurnal INSTEK (Informatika Sains dan Teknologi) Vol 6 No 1 (2021): APRIL
Publisher : Department of Informatics Engineering, Faculty of Science and Technology, Universitas Islam Negeri Alauddin, Makassar, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (426.099 KB) | DOI: 10.24252/instek.v6i1.18636

Abstract

Permasalahan yang dibahas pada penelitian ini mengenai klasifikasi bibliografi. Klasifikasi dilakukan dengan memproses data-data dari berbagai sumber referensi yang diberikan. Metode yang diterapkan dalam pengklasifikasian adalah C4.5 dengan sebelumnya dilakukan beberapa tahap preprocessing. C4.5 yang digunakan untuk proses text mining karena memiliki akurasi dan kecepatan yang sangat tinggi dengan algoritma yang sederhana. Digunakan pula Information Gain untuk evaluasi atribut yang dipilih dalam mengklasifikasikan dokumen.Kata Kunci: Text mining, C.45, bibliography, feature selection, Information Gain  
KLASIFIKASI KANKER MENGGUNAKAN ALGORITMA NNGE, RANDOM FOREST, DAN RANDOM COMMITEE AKBAR, MUHAMMAD NUR
Jurnal INSTEK (Informatika Sains dan Teknologi) Vol 5 No 2 (2020): OCTOBER
Publisher : Department of Informatics Engineering, Faculty of Science and Technology, Universitas Islam Negeri Alauddin, Makassar, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (414.134 KB) | DOI: 10.24252/instek.v5i2.20133

Abstract

Permasalahan yang dibahas dalam penelitian ini adalah seputar data pasien kanker pada sebuah klinik. Data yang digunakan yaitu data pasien dimana setiap pasien menjalani 4 tipe tes laboratorium. Dari data tes tersebut, dilakukan pemrosesan yang menghasilkan suatu pola atau model. Selanjutnya, pola tersebut digunakan untuk mendiagnosa pasien yang lain apakah menderita penyakit kanker atau tidak. Dalam masalah ini pemprosesan dilakukan dengan algoritma NNGE, Random Forest, Random Committee. Penggunaan ketiga algoritma tersebut diharapkan dapat menghasilkan klasifikasi dengan tingkat ketidaktepatan minimum. Sebelumnya data training dibagi menjadi 2 bagian, dimana 75% diambil sebagai data training dan 25% sisanya digunakan sebagai data validation. Hasil klasifikasi terhadap data 100 data uji yaitu sebanyak 37 pasien dinyatakan malignant dan sebanyak 63 pasien dinyatakan benign. Kata Kunci: Klasifikasi, NNGE, Random Forest, Random Committee, preprocessing
ANALISIS PREDIKSI KETEPATAN MASA STUDI MAHASISWA MENGGUNAKAN ALGORITMA NAIVE BAYES CLASSIFIER DAN FEATURE SELECTION MUHAMMAD NUR AKBAR; HARIANI; ASEP INDRA SYAHYADI
Jurnal INSTEK (Informatika Sains dan Teknologi) Vol 7 No 2 (2022): OCTOBER
Publisher : Department of Informatics Engineering, Faculty of Science and Technology, Universitas Islam Negeri Alauddin, Makassar, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24252/instek.v7i2.32576

Abstract

Lama masa studi mahasiswa merupakan salah satu poin penilaian dalam akreditasi suatu program studi pada institusi perguruan tinggi. Pendeteksian dini keterlambatan masa studi dapat dilakukan dengan memanfaatkan teknik data mining. Pada penelitian ini diterapkan algoritma Naïve Bayes Classifier (NBC) dan teknik feature selection menggunakan Informaton Gain (IG) dan Correlation Attribute (CA) dengan tujuan membangun model prediksi yang akurat dan menganalisis atribut yang berpengaruh dalam menentukan lama masa studi sehingga dapat membantu perguruan tinggi dalam membuat kebijakan akademis agar dapat mengoptimalkan tingkat kelulusan mahasiswa pada tahun-tahun berikutnya. Hasil uji coba pada dataset diperoleh akurasi tertinggi yaitu NBC+CA sebesar 81.2%, meningkat 12% dibandingkan NBC tanpa feature selection
Deteksi Penyakit pada Daun Tomat Menggunakan Kombinasi Ekstraksi Fitur Colors Moments dan Grey Level Co-Occurrence Matrix (GLCM) Syarif , Ririn Suharni; Akbar , Muhammad Nur; Darmatasia, Darmatasia
Journal Software, Hardware and Information Technology Vol 5 No 2 (2025)
Publisher : Jurusan Sistem Informasi Universitas Islam Negeri Alauddin Makassar

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24252/shift.v5i2.214

Abstract

Tomato is one of the leading horticultural crops widely cultivated by farmers in Indonesia. In addition to its high economic value, tomatoes are rich in nutrients beneficial to human health, such as vitamin C, lycopene, and other antioxidants. However, tomato productivity is highly vulnerable to decline due to various diseases, particularly those affecting the leaves. These diseases not only reduce the quality of the harvest but also significantly threaten production quantity. Therefore, early detection of leaf diseases in tomato plants is essential to help farmers, especially novice farmers, take timely and appropriate treatment actions. This study aims to develop a digital image-based detection system for tomato leaf diseases using feature extraction methods and classification algorithms. In the image pre-processing and feature extraction stages, the Color Moments algorithm is used to capture color information, while the Gray Level Co-occurrence Matrix (GLCM) represents leaf texture. The classification process is carried out using the Random Forest algorithm. The dataset used in this study was obtained from Kaggle, consisting of 5,451 images of tomato leaves categorized into six classes: Leaf Spot, Leaf Mold, Septoria Leaf Spot, Mosaic Virus, Bacterial Spot, and Healthy Leaf. Test results show that the developed model achieved an accuracy of 90%. These findings indicate that the system can detect tomato leaf diseases with a relatively high level of accuracy. The system is expected to assist farmers, especially beginners, in identifying plant diseases more quickly and accurately, thereby improving treatment efficiency and increasing crop yields.
ANALISIS SENTIMEN KOMENTAR PENGGUNA TERHADAP GAME MOBA LOKAPALA DI GOOGLE PLAY STORE MENGGUNAKAN ALGORITMA SUPPORT VECTOR MACHINE Muiz, Rafiul; Ishar, Rahmat Fajri; Febrianto, Andi; Akbar, Muhammad Nur
AGENTS: Journal of Artificial Intelligence and Data Science Vol 4 No 2 (2024): March - August
Publisher : Prodi Teknik Informatika Universitas Islam Negeri Makassar

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24252/jagti.v4i2.79

Abstract

In this modern era, games are heavily influenced by technological advancements. The development of increasingly complex and captivating games can be played online by millions of players worldwide. The gaming industry in Indonesia has shown significant progress with the emergence of various games from local developers, one of which is Lokapala, a Multiplayer Online Battle Arena (MOBA) game that highlights the uniqueness of Indonesian culture. However, this game has received various responses from users on Google Play Store. This study aims to analyze user sentiment towards the Lokapala game on Google Play Store using the Support Vector Machine (SVM) algorithm. User review data were collected and pre-processed through stages such as data cleaning, tokenization, stopwords removal, and stemming. Subsequently, features were extracted using the TF-IDF method. The analysis results show that SVM with Radial Basis Function (RBF) kernel successfully classified user sentiment with an accuracy of 90% from a total of 300 reviews analyzed. This process not only helps in understanding overall user perceptions but also identifies specific aspects of the game that receive appreciation or criticism. Thus, game developers can use the results of this analysis to improve quality and user satisfaction, and strengthen the game's competitiveness in markets.
Perancangan Game Flashcard dengan Fitur Time Tracker pada Anak Usia Dini Berbasis Android Salsabilah, Fitriyah; Hasrul H, M.; Nur Akbar, Muhammad
AGENTS: Journal of Artificial Intelligence and Data Science Vol 4 No 2 (2024): March - August
Publisher : Prodi Teknik Informatika Universitas Islam Negeri Makassar

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24252/jagti.v4i2.81

Abstract

The presidential candidate election in Indonesia is a hot topic on social media, especially Twitter. This study analyzes public sentiment regarding the 2024 presidential candidate election using the IndoBERT model, which is specifically designed for the Indonesian language, on a dataset of 8,442 tweets. This research follows the CRISP-DM methodology, which includes business understanding, data understanding, data preparation, modeling, evaluation, and deployment. The data was collected through crawling with keywords related to the election, followed by preprocessing and manual labeling before being processed by the model. The results show that IndoBERT achieved an accuracy of 98%, with precision, recall, and F1-score also at 98% at the 10th epoch. Batch size evaluation indicated that a batch size of 4 yielded the best performance. This model is effective in classifying sentiment related to the 2024 presidential candidate election and serves as a useful tool for understanding public opinion.