Bulk scraping news from Google RSS feeds, extracting and storing information like titles, publishers, dates, URLs, content, and keywords
#Python
#Crawler
Featured Project
PRU15 Twitter Sentiment Analysis
Scraped 2.5 million local tweets data. Utilized Malay LLM from Mesolitica to get sentiment prior to election day. Aimed to determine bias and sentiment and compare them to the actual election results
#Python
#Research
#LLM
Featured Project
Scalability and Performance in Duplicate Detection: Relational vs Graph Database
Comparing exact and near-duplicate detection algorithms across varied variables, including database size and server specifications.
