Twitter sentiment analysis of Malaysian fast food restaurant chains: a novel approach to understand customer perception using Naïve Bayes / Muhammad Hafeez Hakimi Muhd Zahidi Ridzuan and Khairul Nizam Abd Halim
Social media has emerged as a prominent platform for users to share ideas, opinions, and thoughts, leading to an increase in consumers expressing their product feedback through these channels rather than providing direct feedback to companies. Fast food has gained popularity in recent years due to i...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Book Section |
| Language: | English |
| Published: |
Faculty of Computer and Mathematical Sciences
2023
|
| Subjects: | |
| Online Access: | https://ir.uitm.edu.my/id/eprint/93881/1/93881.pdf https://ir.uitm.edu.my/id/eprint/93881/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Institution: | Universiti Teknologi Mara |
| Language: | English |
| Summary: | Social media has emerged as a prominent platform for users to share ideas, opinions, and thoughts, leading to an increase in consumers expressing their product feedback through these channels rather than providing direct feedback to companies. Fast food has gained popularity in recent years due to its affordability, tastiness, and convenience. However, there is a lack of a dedicated platform for customers to access comprehensive reviews of fast food restaurants in Malaysia, resulting in time-consuming processes when trying to read online reviews. This project introduces a web-based system that uses Twitter sentiment analysis to visualize reviews of Malaysian fast food restaurants. It employs Naïve Bayes algorithm and Plotly library in Python to provide insights into customer perceptions, enhancing the fast food brand experience in Malaysia. This system introduces a comprehensive solution to understand restaurant sentiments by employing a visualization dashboard and conducting comparative analysis between various companies. Moreover, it empowers users to analyze their own Twitter data by utilizing a sentiment analyzer, which predicts the sentiments associated with the provided textual data. |
|---|