Social Media Analytics (Public Awareness and Behaviors in Road Safety)

🌌 This is a group project of Social Media Data Analytics course.

🌌 This research aims to fill a gap in the understanding of road safety by investigating the dynamics of public awareness and behavior in road safety using data analytics and social network analysis (SNA). By analyzing the content people deliver and express on social media platforms, we can get a better idea of how people feel about road safety and what influences their behaviors.

Tech Stack:
🌌 Natural Language Processing (NLP): NLTK, Text Classification, Sentiment Analysis
🌌 Machine Learning: K-means Clustering
🌌 Deep Learning Transformer: Google BERT
🌌 Graph network analysis and Visualization: Gephi

🌌 The social media data, scraped from TikTok and Instagram by Apify, undergoes preprocessing using NLP techniques to prepare it for machine learning. BERT model is used to capture the context of the sentences. K-Means clustering is then applied to group the data into clusters. To analyze these clusters and extract meaningful insights, sentiment analysis are performed, allowing for a deeper understanding of the sentiments and patterns within the clustered data.

🌌 Through a series of analysis of social media users’ interaction, they enable a deeper understanding of public perceptions and behaviors, facilitating the development of interventions and initiatives to reduce the accident rates.

In collaboration with:
1. Lee Qi Zun
2. Abdul Rahman bin Muhamad Faidulatraf
3. Lee Kien Soon
4. Yap Jia Jun