Multi-Aspect Sentiment Analysis on Tiktok Using Random Forest Classifier and Word2Vec

ADIV HARJADINATA

Informasi Dasar

22.04.3443
621.367
Karya Ilmiah - Skripsi (S1) - Reference

The number of people using the internet today is directly proportionate to the number of people using social media. Compared to other social media platforms, Tiktok is one of the most downloaded social media platforms on Google Play. However, not among Tiktok’s reviews are positive. Based on reviews on Google Play, these reviews can be used as data in sentiment analysis to determine which aspects are reviewed by users and whether the sentiment is positive or negative. The aspects used in this study include features, business, and content. Word2Vec was used for data modeling, and Random Forest Classifier was used for classification. Using the Skip-gram model, without Stemming and CBOW model without stopwords the best parameter testing on Random Forest achieved the accuracy an average of all aspects of 78.33%.

Subjek

Machine Learning
Image processing - computer image,

Katalog

Multi-Aspect Sentiment Analysis on Tiktok Using Random Forest Classifier and Word2Vec
 
 
Indonesia

Sirkulasi

Rp. 0
Rp. 0
Tidak

Pengarang

ADIV HARJADINATA
Perorangan
Yuliant Sibaroni
 

Penerbit

Universitas Telkom, S1 Informatika
Bandung
2022

Koleksi

Kompetensi

  • CII4E4 - TUGAS AKHIR

Download / Flippingbook

 

Ulasan

Belum ada ulasan yang diberikan
anda harus sign-in untuk memberikan ulasan ke katalog ini