Twitter Word Phrequency

Master Chen presents Twitter Word Phrequency, an open-source Python research project designed to perform natural language processing (NLP) and behavioral sentiment analysis on high-profile social media accounts [00:04]. Chen explains how open-source intelligence (OSINT) gathered from public social media feeds can reveal psychological profiles, communication habits, and ideological shifts [10:25].

The presentation covers the technical data collection and analysis pipeline built using Python, Twitter API scrapers, and Jupyter Notebooks [15:28]. Chen details the data normalization techniques required to process social media text, including tokenization, stop-word removal, and calculating n-gram word frequencies [20:54]. Using Donald Trump's public Twitter history as a primary case study, Chen demonstrates how tracking changes in lexical diversity, repetitive keyword spikes, and emotional terminology correlates with political market movements on platforms like PredictIt [05:13, 20:54].

Chen discusses data visualization techniques, showing how to transform raw frequency tables into intuitive word clouds, time-series frequency plots, and sentiment heatmaps [26:17]. He concludes with methodologies for adapting these scripts into active OSINT monitoring tools for social engineering assessments and threat intelligence profiling [31:23].

(AI summary — Gemini Flash)