Moderating Useful Reviews using Machine Learning


Suhaimi, Liyana Aisyah and Goh, Vik Tor and Tan, Yi Fei (2022) Moderating Useful Reviews using Machine Learning. Periodic Research Publication, Faculty of Engineering. (Unpublished)

[img] Text
19_1171101659 Liyana Aisyah_Viktor_FYP2 Poster.pdf
Restricted to Repository staff only

Download (575kB)


For some of the most popular products, hundreds, if not thousands, of online product reviews are written. Users may find it difficult and overwhelming to process such enormous amount of user-generated content In this project, the focus is to design a system that can automatically rate the usefulness of product reviews using machine learning techniques, namely, SVM classifiers. The machine learning system utilises datasets from online shopping platforms, specifically Shopee and Amazon. These datasets were used to train and validate our machine learning model. The model is then implemented in an interactive website that can automatically rate users’ reviews, thus facilitating the decision-making process when making online purchases. By using SVM classifiers in our model, this system was able to attain 89.36% average accuracy in classifying the reviews.

Item Type: Other
Subjects: Q Science > QA Mathematics > QA71-90 Instruments and machines > QA75.5-76.95 Electronic computers. Computer science > QA76.75-76.765 Computer software
Divisions: Faculty of Engineering (FOE)
Depositing User: Assoc. Dr Chee Pun Ooi
Date Deposited: 29 Nov 2022 01:13
Last Modified: 29 Nov 2022 01:13


Downloads per month over past year

View ItemEdit (login required)