Sentiment Analysis using Machine Learning Models on Shopee Reviews


Ahmad Azrir, Ahmad Hariz Imran and Naveen, Palanichamy and Haw, Su Cheng (2024) Sentiment Analysis using Machine Learning Models on Shopee Reviews. Journal of System and Management Sciences, 14 (2). ISSN 1816-6075, 1818-0523

[img] Text
22.pdf - Published Version
Restricted to Repository staff only

Download (744kB)


Sentiment analysis is essential for understanding customer opinions and feedback in the e-commerce industry. It is a valuable tool for businesses, providing insights into customer preferences and opinions. By understanding customer sentiment, companies can tailor their messaging to better resonate with their target audience and identify areas of improvement to increase customer satisfaction. However, sentiment analysis precision requires enhancement when informal language is present in the reviews. Therefore, we aim to enhance and boost sentiment analysis's accuracy when informal language is present in the reviews. In this study, the shopee reviews are extracted; preprocessed and sentiments are extracted and labelled as positive or negative. We employ feature extraction approaches such as N-grams, Bag of Words (BOW), and Term Frequency-Inverse Document Frequency (TF-IDF). Next, we apply machine learning methods such as Naive Bayes (NB), Support Vector Machine (SVM), Gated Recurrent Unit (GRU), and Long Short-Term Memory (LSTM). The performance of the models are evaluated using Area Under the Curve (AUC) and Receiver Operating Characteristic (ROC). Our findings show that the SVM classifier using 2-gram TF-IDF features achieves the best performance with an accuracy score of 86% when compared to NB, LSTM and GRU. Overall, our results suggest that using machine learning algorithms can effectively analyze user sentiment in e-commerce platforms like Shopee when informal language is present.

Item Type: Article
Uncontrolled Keywords: Sentiment Analysis
Subjects: Q Science > QA Mathematics > QA71-90 Instruments and machines > QA75.5-76.95 Electronic computers. Computer science
Divisions: Faculty of Computing and Informatics (FCI)
Depositing User: Ms Nurul Iqtiani Ahmad
Date Deposited: 04 Mar 2024 02:50
Last Modified: 04 Mar 2024 02:50


Downloads per month over past year

View ItemEdit (login required)