Multi-aspect Sentiment Analysis of Tiktok Application Usage Using FasText Feature Expansion and CNN Method
RIFKI ALFIAN ABDI MALIK
Informasi Umum
Kode
23.04.1046
Klasifikasi
006.312 - Data mining
Jenis
Karya Ilmiah - Skripsi (S1) - Reference
Subjek
Data Mining, Data Analysis,
Dilihat
347 kali
Informasi Lainnya
Abstraksi
<p><strong>Among the many social media platforms that have emerged, TikTok is the platform that has the most significant number of subscribers compared to other platforms. However, not all reviews given by TikTok users are good reviews. These reviews will later be analyzed according to predetermined aspects, namely feature aspects, business aspects, and content aspects based on reviews written on the Google Play Store, using data crawling and will pass the preprocessing and weighting stages. The weighting method used is Term FrequencyInverse Document Frequency (TF-IDF). Then, the sentiment analysis process using the Convolutional Neural Network (CNN) method will be carried out to determine whether each review is included in Sentiment Analysis, and feature expansion will be carried out to determine what words are interrelated with a particular word. The purpose of this research is to analyze sentiment using Convolutional Neural Network and fastText feature expansion. The highest accuracy result was 87.74%.</strong></p>
Koleksi & Sirkulasi
Seluruh (1) koleksi tidak tersedia
Anda harus log in untuk mengakses flippingbook
Pengarang
| Nama | RIFKI ALFIAN ABDI MALIK |
| Jenis | Perorangan |
| Penyunting | Yuliant Sibaroni |
| Penerjemah |
Penerbit
| Nama | Universitas Telkom, S1 Informatika |
| Kota | Bandung |
| Tahun | 2023 |
Sirkulasi
| Harga sewa | IDR 0,00 |
| Denda harian | IDR 0,00 |
| Jenis | Non-Sirkulasi |
