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 more consumers expressing their product feedback through these channels rather than providing direct feedback to companies. Fast food has gained popularity recently due to its affordability, tastiness, and convenience. However, a lack of a dedicated platform for customers to access comprehensive reviews of fast-food restaurants in Malaysia results in time-consuming processes when trying to read online reviews. This study introduces a web-based system that uses Twitter sentiment analysis to visualise reviews of Malaysian fast-food restaurants. It employs the 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 visualisation dashboard and conducting a comparative analysis between various companies. Moreover, it empowers users to analyse their Twitter data using a sentiment analyser, which predicts the sentiments associated with the provided textual data.