Claim Missing Document
Check
Articles

Found 13 Documents
Search

Comparison of F1-Score Naive Bayes, Logistic Regression, K-Nearest Neighbors, and SVM for Sentiment Classification X in Police Institutions Robertos Hartanto Wijaya; Adi Nugroho
Eduvest - Journal of Universal Studies Vol. 6 No. 3 (2026): Eduvest - Journal of Universal Studies
Publisher : Green Publisher Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59188/eduvest.v6i3.53005

Abstract

Social media, especially platform X, is the main channel for the public to express their opinions on public institutions, including the police. Analysis of public sentiment on this platform can provide insight into police performance. This study aims to compare the performance of machine learning algorithms Naive Bayes, Logistic Regression, K-Nearest Neighbors (KNN), and Support Vector Machine (SVM) in classifying negative sentiments towards policing on social media X, as well as overcoming data imbalances using the SMOTE method. The dataset consisted of 1,274 Indonesian-language data collected by crawling, then processed using preprocessing techniques such as text cleaning, stopword removal, and TF-IDF feature extraction. Testing is conducted with and without the implementation of SMOTE for data balancing. Evaluate the model's performance using F1-Score. Without SMOTE, all algorithms fail to recognize neutral classes. After the implementation of SMOTE, Logistic Regression showed the best performance with an F1-Score of 80.85%, followed by SVM, Naive Bayes, and KNN. The implementation of SMOTE significantly improves the model's ability to classify negative sentiments.  The combination of Logistic Regression and SMOTE is the best approach to classifying public sentiment towards policing, which can help police agencies understand public sentiment more accurately.
Peningkatan Kapasitas Penelitian Guru dan Siswa SMA Melalui Pelatihan Metodologi Penelitian dan Pendampingan Olimpiade Penelitian Siswa Indonesia Andreas A. Sukmana; Sri Kasmiyati; Betty E. Kristiani; Hindriyanto D. Purnomo; Budhi Kristianto; Krismiyati Krismiyati; Teguh I. Bayu; Radius Tanone; Adi Nugroho; Hanita Yulia; Evangs Mailoa; Erwien Christianto
JURNAL PENGABDIAN PAPUA Vol 10 No 1 (2026)
Publisher : LPPM Uncen

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31957/jpp.v10i1.5252

Abstract

Critical and innovative thinking skills are essential requirements for students to meet the global challenges. One strategy to develop these skills is through participation in the Indonesian Student Research Olympiad (OPSI), which requires collaboration between teachers and students in implementing fundamental research concepts. However, the implementation of basic research concepts within the high school curriculum remains limited. Consequently, collaboration with higher education institutions serves as a potential solution, specifically through research training and mentoring. This training initiative aimed to enhance the research competence of teachers and students at SMAN 1 Ambarawa by providing methodology training and mentoring for OPSI research teams, conducted by a faculty team from Satya Wacana Christian University. The program was conducted intensively consisting of research design training and research mentoring for nine student groups. The training and the mentoring were provided by lecturers whose expertise aligned with the specific OPSI proposal topics of each group. This mentoring resulted in an overall improvement in the research capabilities of both teachers and students, with one group successfully won a gold medal at OPSI 2025. In conclusion, this program results in a positive reception, which expressed the hope that similar initiatives can be conducted on a regular basis.
Analisis Kepuasan Pengguna Layanan GoFood pada Aplikasi Gojek Menggunakan Metode End User Computing Satisfaction di Kota Salatiga Netiva Hidayah; Adi Nugroho
JIPI (Jurnal Ilmiah Penelitian dan Pembelajaran Informatika) Vol 9, No 4 (2024)
Publisher : STKIP PGRI Tulungagung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29100/jipi.v9i4.5509

Abstract

Dengan kemajuan teknologi di era digital, layanan masyarakat telah berubah karena aplikasi berbasis mobile menjadi lebih mudah diakses. Sebagai bagian dari ekosistem Gojek, GoFood adalah perusahaan pesan antar makanan terkemuka di Indonesia. Kualitas layanan yang lebih baik sangat penting dalam per-saingan yang semakin ketat, yang dapat diukur melalui kepuasan pengguna. Untuk mendapatkan pemahaman yang lebih baik tentang komponen yang memengaruhi kepuasan pengguna aplikasi ini, penelitian ini meneliti pengalaman pengguna GoFood di Kota Salatiga dengan menggunakan metode EUCS dan mengintegrasikan variabel Perceived of Usefulness dari metode TAM. Hasil penelitian menunjukkan bahwa variabel konten, ketepatan, format, kemudahan penggunaan, waktu, dan kepuasan pengguna memiliki hubungan yang signifikan satu sama lain. Penelitian ini menyoroti pentingnya penyesuaian strategi berdasarkan lokasi spesifik seperti Kota Salatiga untuk meningkatkan pengalaman pengguna. Implikasi temuan ini diarahkan pada upaya pengembangan pendekatan yang lebih tepat sasaran guna meningkatkan kepuasan pengguna aplikasi, khususnya GoFood, dalam konteks lokal.