Intelligence Shopee Product Comparison (i-SPC) and Visualization of Product Information via Naïve Bayes Adaptation

Authors

  • Khyrina Airin Fariza Abu Samah Computing Sciences Studies, College of Computing, Informatics and Mathematics, Universiti Teknologi MARA Melaka Branch, Melaka, Malaysia
  • Nurul Syuhada’ Abd Raub Computing Sciences Studies, College of Computing, Informatics and Mathematics, Universiti Teknologi MARA Melaka Branch, Melaka, Malaysia
  • Lala Septem Riza Department of Computer Science Education, Universitas Pendidikan Indonesia, Bandung, Indonesia
  • Hana Fakhira Almarzuki Computing Sciences Studies, College of Computing, Informatics and Mathematics, Universiti Teknologi MARA Shah Alam, Selangor, Malaysia
  • Nurazian Mior Dahalan Computing Sciences Studies, College of Computing, Informatics and Mathematics, Universiti Teknologi MARA Melaka Branch, Melaka, Malaysia
  • Ahmad Firdaus Ahmad Fadzil Computing Sciences Studies, College of Computing, Informatics and Mathematics, Universiti Teknologi MARA Melaka Branch, Melaka, Malaysia

DOI:

https://doi.org/10.37934/araset.37.1.179190

Keywords:

E-Commerce, i-SPC, Shopee, Naïve Bayes, Data visualization

Abstract

Electronic Commerce (E-Commerce) is a type of commerce that takes place online. The most used platform based on frequently visited in Malaysia is Shopee. According to a questionnaire survey of 102 respondents, 95.1% agreed that manually comparing Shopee product information takes time. Manual analyzing a group of similar products is notoriously complicated, and finding informative reviews for product purchases is becoming increasingly challenging. This study aims to obtain Shopee information from the real-time Shopee website. Hence, Intelligence Shopee Product Comparison (i-SPC), aims to design a web-based application system that compares Shopee product information from different shops using the Naïve Bayes algorithm. The user can copy and paste the chosen Shopee product link to a maximum of ten links for comparison. The i-SPC displays the information based on seven focused factors and categorizes whether the pasted link is “recommended” or “not recommended”. The visualization result uses a bar chart to show four types of information: shop rating, product price, followers, and chat response. Testing phases have proven that the classifier accomplished all the research’s objectives and successfully classified Shopee product information with 87.50% accuracy, which is considered “good”. All test cases for the functionality test proved that the i-SPC successfully solved the problem. Therefore, it can conclude that i-SPC overcame the problem and improved the product comparison process.

Downloads

Download data is not yet available.

Author Biographies

Khyrina Airin Fariza Abu Samah, Computing Sciences Studies, College of Computing, Informatics and Mathematics, Universiti Teknologi MARA Melaka Branch, Melaka, Malaysia

khyrina783@uitm.edu.my

Nurul Syuhada’ Abd Raub, Computing Sciences Studies, College of Computing, Informatics and Mathematics, Universiti Teknologi MARA Melaka Branch, Melaka, Malaysia

syuhadaraub39@gmail.com

Lala Septem Riza, Department of Computer Science Education, Universitas Pendidikan Indonesia, Bandung, Indonesia

lala.s.riza@upi.edu

Hana Fakhira Almarzuki , Computing Sciences Studies, College of Computing, Informatics and Mathematics, Universiti Teknologi MARA Shah Alam, Selangor, Malaysia

hanafakhira@uitm.edu.my

Nurazian Mior Dahalan, Computing Sciences Studies, College of Computing, Informatics and Mathematics, Universiti Teknologi MARA Melaka Branch, Melaka, Malaysia

nurazian@uitm.edu.my

Ahmad Firdaus Ahmad Fadzil, Computing Sciences Studies, College of Computing, Informatics and Mathematics, Universiti Teknologi MARA Melaka Branch, Melaka, Malaysia

firdausfadzil@uitm.edu.my

Downloads

Published

2024-01-09

How to Cite

Khyrina Airin Fariza Abu Samah, Nurul Syuhada’ Abd Raub, Lala Septem Riza, Hana Fakhira Almarzuki, Nurazian Mior Dahalan, & Ahmad Firdaus Ahmad Fadzil. (2024). Intelligence Shopee Product Comparison (i-SPC) and Visualization of Product Information via Naïve Bayes Adaptation. Journal of Advanced Research in Applied Sciences and Engineering Technology, 37(1), 179–190. https://doi.org/10.37934/araset.37.1.179190

Issue

Section

Articles