Article Per Year (5 Year)
p-Index From 2021 - 2026
4.043
P-Index
This Author published in this journals
All Journal Semantik Jurnal Teknologi dan Manajemen Informatika Jurnal Buana Informatika Prosiding Seminar Nasional Sains Dan Teknologi Fakultas Teknik JSI: Jurnal Sistem Informasi (E-Journal) Indonesian Journal of Electrical Engineering and Informatics (IJEEI) Jurnal Teknologi Informasi dan Ilmu Komputer Jurnal Transformatika Jurnal Terapan Abdimas Jurnal Informatika Upgris JurTI (JURNAL TEKNOLOGI INFORMASI) JuSiTik : Jurnal Sistem dan Teknologi Informasi Komunikasi Jurnal Abdimas PHB : Jurnal Pengabdian Masyarakat Progresif Humanis Brainstorming Journal of Computer Science and Engineering (JCSE) Journal of Applied Data Sciences HOAQ (High Education of Organization Archive Quality) : Jurnal Teknologi Informasi Jurnal Pengabdian kepada Masyarakat Bina Darma Jurnal Teknologi Informasi Cyberku Jurnal Abdimas Musi Charitas Jurnal Ilmiah Ilmu Terapan Universitas Jambi J-ABDIPAMAS (Jurnal Pengabdian Kepada Masyarakat) MDP Student Conference Jurnal Informatika Polinema (JIP) Jurnal Pelayanan Masyarakat Pelayanan Unggulan: Jurnal Pengabdian Masyarakat Terapan
Latius Hermawan
Universitas Katolik Musi Charitas
Agriculture, Biological Sciences & Forestry Humanities Automotive Engineering Civil Engineering, Building, Construction & Architecture Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Education Electrical & Electronics Engineering Engineering Health Professions Industrial & Manufacturing Engineering Languange, Linguistic, Communication & Media Law, Crime, Criminology & Criminal Justice Library & Information Science Mechanical Engineering Medicine & Pharmacology Nursing Public Health Social Sciences Other

Published : 43 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 43 Documents
Search

 1   2   3   4   5 
PENERAPAN ALGORITMA DECISION TREE REGRESSION DALAM PREDIKSI PENJUALAN BARANG UNTUK REKOMENDASI STOK MASUK PADA CV ABC PALEMBANG: APPLICATION OF DECISION TREE REGRESSION FOR PRODUCT SALES PREDICTION AND INVENTORY REPLENISHMENT RECOMMENDATIONS AT CV ABC PALEMBANG Johannes; Aji Pragoyo; I Komang Darmawan; Latius Hermawan
HOAQ (High Education of Organization Archive Quality) : Jurnal Teknologi Informasi Vol. 17 No. 2 (2026): Jurnal HOAQ - Teknologi Informasi
Publisher : Universitas Uyelindo

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52972/hoaq.vol17no2.p193-202

Abstract

Pengelolaan stok barang pada toko bangunan yang tidak berbasis data historis dapat menyebabkan risiko kekurangan atau kelebihan persediaan. Penelitian ini dilakukan pada CV ABC Palembang, yaitu nama samaran dari salah satu toko bangunan di Palembang. Tahapan penelitian diawali dengan identifikasi masalah, studi literatur, pengumpulan data, pre-processing dan pembentukan target, feature engineering, pemodelan, pengujian, evaluasi, serta implementasi sistem web berbasis Django. Data yang digunakan merupakan transaksi penjualan dua produk semen, yaitu Semen Dynamix 40 KG dan Semen Merdeka 40 KG, pada periode 1 Januari 2025 sampai 30 Desember 2025. Dataset mentah berjumlah 243 baris, kemudian melalui proses pembersihan menjadi 241 baris transaksi valid. Target model dibentuk menggunakan variabel Jumlah_Penjualan_Berikutnya sehingga data siap model berjumlah 239 baris. Data dibagi secara berurutan berdasarkan waktu dengan rasio 80% untuk data latih dan 20% untuk data uji. Setelah dilakukan penyesuaian hyperparameter DecisionTreeRegressor, evaluasi model menghasilkan MAE sebesar 5,86 dan RMSE sebesar 7,70. Hasil tersebut menunjukkan bahwa model mampu menghasilkan estimasi awal dalam satuan jumlah penjualan, sedangkan sistem web dapat memberikan rekomendasi stok masuk berdasarkan safety stock dan stok akhir saat ini.   Inventory management in a building materials store that is not supported by historical data may increase the risk of stock shortages or excess inventory. This study was conducted at CV ABC Palembang, a pseudonym for a building materials store in Palembang, to apply the Decision Tree Regression algorithm to predict product sales in the next period and generate incoming stock recommendations. The dataset consists of sales transaction data for two cement products, namely Semen Dynamix 40 KG and Semen Merdeka 40 KG. The raw dataset contained 243 rows and was cleaned into 241 valid transaction rows. The model target was constructed using the Jumlah_Penjualan_Berikutnya variable, resulting in 239 rows of modeling data. The research stages include problem identification, literature review, data collection, preprocessing, feature engineering, model training, testing, evaluation, and web-based system implementation using Django. The dataset was split sequentially based on time using an 80% training and 20% testing ratio. After adjusting the DecisionTreeRegressor hyperparameters, the model evaluation produced an MAE of 5.86 and an RMSE of 7.70. The results indicate that the model can provide an initial sales prediction in unit form, while the web system can generate incoming stock recommendations based on safety stock and current ending inventory.
PENGARUH TEKNIK PELABELAN BERDASARKAN RATING DAN MANUAL TERHADAP KINERJA MODEL LOGISTIC REGRESSION BERBASIS TF-IDF PADA ANALISIS SENTIMEN ULASAN APLIKASI WIKIPEDIA: THE IMPACT OF RATING-BASED AND MANUAL LABELING TECHNIQUES ON THE PERFORMANCE OF A TF-IDF-BASED LOGISTIC REGRESSION MODEL FOR SENTIMENT ANALYSIS OF WIKIPEDIA APP REVIEWS Kevin Winardi; Jeremia Sandy Pratama; Delon Setiawan; Latius Hermawan
HOAQ (High Education of Organization Archive Quality) : Jurnal Teknologi Informasi Vol. 17 No. 2 (2026): Jurnal HOAQ - Teknologi Informasi
Publisher : Universitas Uyelindo

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52972/hoaq.vol17no2.p382-391

Abstract

Wikipedia merupakan salah satu ensiklopedia daring yang menyediakan berbagai informasi dan pengetahuan yang dapat diakses melalui browser ataupun menggunakan aplikasi. Sebagai aplikasi yang tersedia di Google Play Store, Wikipedia menerima berbagai ulasan pengguna yang dapat dimanfaatkan untuk mengetahui persepsi dan tingkat kepuasan terhadap aplikasi. Penelitian ini bertujuan untuk menganalisis pengaruh teknik pelabelan sentimen ulasan pada aplikasi Wikipedia. Proses pelabelan sentimen dilakukan menggunakan dua teknik, yaitu pelabelan berdasarkan rating pengguna (1-2: negatif, 3: netral, 4-5: positif) dan pelabelan manual. Data yang telah melalui tahap preprocessing kemudian diekstraksi menggunakan TF-IDF dan diklasifikasikan menggunakan Logistic Regression dengan pembagian data latih dan data uji sebesar 80:20. Hasil penelitian menunjukkan kalau teknik pelabelan memiliki pengaruh terhadap kinerja model Logistic Regression berbasis TF-IDF. Hasil evaluasi awal menunjukkan nilai macro average F1-score sebesar 0,69 pada pelabelan manual lebih tinggi dibandingkan pelabelan berdasarkan rating sebesar 0,46. Data yang digunakan memiliki distribusi kelas yang tidak seimbang sehingga dilakukan penyeimbangan data menggunakan SMOTE dan optimasi parameter terbaik menggunakan GridSearchCV. Namun hasil analisis lanjutan tersebut belum memberikan peningkatan performa yang berarti pada kedua teknik pelabelan. Temuan penelitian ini menunjukkan bahwa pelabelan manual menghasilkan representasi sentimen yang lebih sesuai dengan isi ulasan dibandingkan pelabelan berdasarkan rating, sehingga memberikan performa klasifikasi yang lebih baik.   Wikipedia is an online encyclopedia providing a wealth of information and knowledge accessible via web browsers or mobile applications. As an app available on the Google Play Store, Wikipedia receives numerous user reviews that can be leveraged to gauge user perceptions and satisfaction levels. This study aims to analyze the impact of sentiment labeling techniques on Wikipedia app reviews. Sentiment labeling was conducted using two methods: labeling based on user ratings (1-2: negative, 3: neutral, 4-5: positive) and manual labeling. After undergoing preprocessing, the data were extracted using TF-IDF and classified using Logistic Regression, with an 80:20 split between training and testing data. The results indicate that the labeling method influences the performance of the TF-IDF-based Logistic Regression model. Initial evaluations showed a macro average F1-score of 0.69 for manual labeling, which was higher than the 0.46 score obtained with rating-based labeling. Due to the imbalanced class distribution of the dataset, data balancing was performed using SMOTE, and optimal parameters were determined using GridSearchCV. However, these further analyses did not yield significant performance improvements for either labeling method. The findings demonstrate that manual labeling produces sentiment representations that better align with review content compared to rating-based labeling, thereby resulting in superior classification performance.
PENGEMBANGAN WEBSITE REKOMENDASI JUDUL DAN DRAF ARTIKEL KEGIATAN KOMUNIO PALEMBANG MENGGUNAKAN TF-IDF, NAIVE BAYES DAN COSINE SIMILARITY: DEVELOPMENT OF A WEB-BASED RECOMMENDATION SYSTEM FOR ACTIVITY ARTICLE TITLES AND DRAFTS AT KOMUNIO PALEMBANG USING TF-IDF, NAIVE BAYES, AND COSINE SIMILARITY Yulianus Febry Tri Nugroho; Marselinus Dewadaru Bayu Adeodatus; Sepiyana Nopitasari; Latius Hermawan
HOAQ (High Education of Organization Archive Quality) : Jurnal Teknologi Informasi Vol. 17 No. 2 (2026): Jurnal HOAQ - Teknologi Informasi
Publisher : Universitas Uyelindo

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52972/hoaq.vol17no2.p373-381

Abstract

KOMUNIO Palembang telah memiliki arsip artikel digital, tetapi sistem publikasi yang berjalan belum menyediakan dukungan editorial untuk mengubah deskripsi kegiatan baru menjadi prediksi kategori, artikel rujukan, rekomendasi judul, dan draf awal dalam satu alur. Penelitian ini mengembangkan dan mengevaluasi pipeline editorial berbasis TF-IDF, Multinomial Naive Bayes, dan Cosine Similarity pada 2.991 artikel yang dipetakan ke empat kategori. Data dibagi 80:20 dengan random state 42 dan oversampling diterapkan hanya pada data latih. Model final memperoleh accuracy 83,97%, macro precision 81,97%, macro recall 82,11%, dan macro F1-score 81,95%. Performa antarkelas tidak seragam: Liturgi mencapai F1-score 99,6%, sedangkan Berita dan Kegiatan Gereja hanya 57,0%. Sebanyak 51 dari 114 artikel Berita dan Kegiatan Gereja (44,7%) diprediksi sebagai Orang Muda dan Anak Remaja, yang menunjukkan tumpang tindih kosakata dan batas label. Dibanding majority-class baseline, accuracy meningkat dari 38,06% menjadi 83,97%. Pada pengujian rekomendasi, Cosine Similarity tertinggi berada sekitar 22–26%, sehingga skor ditafsirkan sebagai kedekatan leksikal relatif untuk pemeringkatan rujukan, bukan kesamaan semantik mutlak. Kontribusi penelitian terletak pada integrasi klasifikasi dan pencarian rujukan ringan untuk bantuan editorial berbahasa Indonesia, disertai analisis kesalahan kelas dan batas interpretasi rekomendasi.   KOMUNIO Palembang maintains a digital article archive, but the existing publication system does not provide an integrated editorial workflow that transforms a new activity description into category prediction, reference-article retrieval, title recommendation, and an initial draft. This study develops and evaluates an editorial pipeline based on TF-IDF, Multinomial Naive Bayes, and Cosine Similarity using 2,991 articles mapped into four categories. The data were split 80:20 with a random state of 42, and oversampling was applied only to the training data. The final model achieved 83.97% accuracy, 81.97% macro precision, 82.11% macro recall, and 81.95% macro F1-score. Class performance was heterogeneous: Liturgy reached an F1-score of 99.6%, whereas Church News and Activities reached only 57.0%. Fifty-one of 114 Church News and Activities articles (44.7%) were predicted as Youth and Children, indicating lexical overlap and non-exclusive class boundaries. Compared with a majority-class baseline, accuracy increased from 38.06% to 83.97%. The highest Cosine Similarity scores in the recommendation test were approximately 22–26%; therefore, the scores are interpreted as relative lexical proximity for ranking references rather than absolute semantic equivalence. The contribution is an integrated, lightweight Indonesian editorial-assistance workflow combining classification and content retrieval with class-level error analysis and a conservative interpretation of recommendation scores.
Co-Authors Agatha Felicia Ahmad Ghiffari Aji Pragoyo Alamsyah, Alfin Gusti Anak Agung Gede Sugianthara Andayani, Sri Andri Wijaya Andryani, Ria Asmiatun, Siti Astrid Novita Putri, Astrid Bobbi Setiawan BS, Klaudius Jevanda Cevin, Jery Dandi, Dandi Dedy Hermanto Delon Setiawan Deris Stiawan Desy Arisandy Dhita Wahyu Anggraeni, Dhita Wahyu Edi Surya Negara Farozi, Mohamad Felicia, Agatha Felicia, Agatha Felix Octavian Fransiska Ninda Permata Nugraha Fransiska Soejono Gultom, David Gunadi Emmanuel Hastari Mayrita, Hastari Hendrik Fery Herdiyatmoko I Komang Darmawan Indri Ramayanti Jawa Bendi, Reginaldus Kritoforus Jeremia Sandy Pratama Jevanda BS, Klaudius Johannes Kevin Winardi Klaudius Jevanda BS Klaudius Jevanda BS Malla, Maria Maria Bellaniar Ismiati Maria Bellaniar Ismiati Marselinus Dewadaru Bayu Adeodatus Meilinda Meilinda Meilinda, Meilinda Mochamad Hariadi Muhammad Fahmi Muhammad Qurhanul Rizqie Mutika, Suzzana Winda Artha Negara, Edi Surya Ninda Permata Nugraha, Fransiska Oemar, Rexy Orlando, Nikolas Paskalina Widiastuti R. Prasetya, Benedikto Nugroho Pratama, Arnoldus Julio R. Kristoforus Jawa Bendi Rafael Tomi Prakoso Ramadan, Rahmat Rizma Adlia Syakurah Rizqie, Muhammad Qurhanul Romiya, Romiya Ruri Suko Basuki Sepiyana Nopitasari Sri Andayani Sri Andayani Sunda Ariana, Sunda Syakurah, Rizma Adlia Taslim, Jimmy Theresia Sunarni Tri Daryatni Vega, Laurentius Dika Andreano Vincent Marcellio Violentina Wijaya wawan nurmansyah Wawan Nurmansyah, Wawan Yeniyati, Prisca Yulianus Febry Tri Nugroho Yunitasari Yunitasari