Analysis of Google Ngram Viewer's unreliable data on the word 'grok', highlighting OCR errors and date misattribution issues.
A tool to detect and highlight clichéd phrases common in LLM-generated text, like 'no X, no Y' chains.
A tool to detect and highlight common clichéd phrases in LLM-generated text, like 'no X, no Y' and 'you already know'.
An introduction to stylometry, the statistical analysis of writing style, with examples from historical texts and natural language processing.
A technical guide on using AI models like ChatGPT and Claude2 in R to analyze and summarize large volumes of public comment text for policy research.
A technical analysis using sentiment analysis on Warren Buffett's shareholder letters from 1977-2016 to identify trends in tone and market influence.
A technical guide on using K-Means clustering in R to analyze and segment search keywords for understanding user intent in digital analytics.
