Leveraging ANN, KNN, and SVM with Comparison Word2Vec Dimensions for Sentiment Analysis of ChatGPT App Reviews - Dalam bentuk buku karya ilmiah
MUHAMAD KHOIR FAHNI NUR ISLAMI
Informasi Umum
Kode
25.04.1384
Klasifikasi
000 - General Works
Jenis
Karya Ilmiah - Skripsi (S1) - Reference
Subjek
Machine Learning
Dilihat
30 kali
Informasi Lainnya
Abstraksi
ChatGPT, a Large Language Model (LLM) concept, that enables human-machine interaction in natural conversation. ChatGPT has elicited diverse assumptions among its users, encompassing both positive and negative sentiments. Sentiment analysis reveals user opinions about ChatGPT, showing positives, negatives, and areas to improve. To achieve competent analysis results with minimal bias and diverse perspectives, this research leverages Artificial Neural Network (ANN) and Support Vector Machine (SVM). K-Nearest Neighbor (KNN) becomes the baseline model for ANN and SVM to reference. This research also evaluates the comparison of Word2Vec dimensions applied to each classification method. The results of this research show that the best combination is obtained using a 300-dimensional model on Word2Vec and using the ANN classification model. This is evidenced by an accuracy value of 87.45%, f1-score 87.45%, recall 87.45%, and precision 87.45%. This facilitates sentiment analysis with reduced bias and diverse perspectives, contributing to the enhancement of ChatGPT’s performance.
Koleksi & Sirkulasi
Tersedia 1 dari total 1 Koleksi
Anda harus log in untuk mengakses flippingbook
Pengarang
| Nama | MUHAMAD KHOIR FAHNI NUR ISLAMI |
| Jenis | Perorangan |
| Penyunting | Kemas Muslim Lhaksmana |
| Penerjemah |
Penerbit
| Nama | Universitas Telkom, S1 Informatika |
| Kota | Bandung |
| Tahun | 2025 |
Sirkulasi
| Harga sewa | IDR 0,00 |
| Denda harian | IDR 0,00 |
| Jenis | Non-Sirkulasi |
