Sentiment Analysis and Topic Modelling on English-Language Reviews of the Novel Yellowface Using Support Vector Machine (SVM) and Latent Dirichlet Allocation (LDA)

Zuzzaifa, Nur (2025) Sentiment Analysis and Topic Modelling on English-Language Reviews of the Novel Yellowface Using Support Vector Machine (SVM) and Latent Dirichlet Allocation (LDA). Tugas Akhir thesis, University of Technology Yogyakarta.

Text #Abstrak_Nur Zuzzaifa_5211811011_Sains Data.pdf Download (220kB)

Abstract

ABSTRACT This study aims to classify readers’ reviews of Yellowface by R.F. Kuang into positive and negative sentiments and to identify the dominant topics within each sentiment group. The dataset consists of 10,000 English-language reviews collected from the Goodreads platform. The preprocessing stages include case folding, punctuation removal, word normalization, stopword removal, tokenization, and lemmatization. Feature extraction was performed using Term Frequency-Inverse Document Frequency (TF-IDF) for sentiment classification and Bag of Words for topic modelling. The classification model was built using the Support Vector Machine (SVM) algorithm, which demonstrated strong performance, achieving 95% accuracy on training data and 86% on testing data. Precision, recall, and F1-score metrics confirmed that the model is balanced and not biased toward any particular class. Topic modelling was conducted using Latent Dirichlet Allocation (LDA) separately for each sentiment group. The results showed that the positive sentiment model achieved the highest coherence score of 5.706 with an optimal number of 4 topics, while the negative sentiment model reached a coherence score of 5.886 with 8 optimal topics. The positive topics reflected the novel’s core themes, racial issues, cancel culture, and favorable reader responses. In contrast, the negative topics included criticism of the publishing industry, writing style, plot development, and disappointing reading experiences. Keywords: Classification, Latent Dirichlet Allocation (LDA), Topic Modelling, Support Vector Machine (SVM), Yellowface.

Item Type:	Thesis (Skripsi, Tugas Akhir or Kerja Praktek) (Tugas Akhir)
Subjects:	T Technology > T Technology (General)
Divisions:	Fakultas Sains Dan Teknologi > Data Science
Depositing User:	Sains Data
Date Deposited:	08 Aug 2025 02:31
Last Modified:	08 Aug 2025 02:31
URI:	http://eprints.uty.ac.id/id/eprint/18427

Actions (login required)

View Item