A Bossy Sort of Voice: Uncovering Gender Bias in Harry Potter
summary
Claim: narration applies pejorative or infantilizing verbs to Hermione more often than to Harry or Ron. Method: Python Jupyter notebooks parse 1.1M words, split dialogue from narration, use NLTK part‑of‑speech tagging and pattern matching to extract nearby verbs and adverbs, visualize with Matplotlib. Result: conservative sample finds words like squeaked, breathless appearing uniquely for Hermione; code and notebooks exist on GitHub and reproduce the analysis.
AI-written summary · about
chapters (4)
- 0:00Start
- 7:38Deciding how to approach the project
- 11:00Isolate the parts of the text we need to analyze
- 18:04Calling out coded language & everyday bias
related talks
24mHarry Potter and the Elastic Python Clients
20mGender Differences in Story, Game and Visual Adventures in Hedy
09mTropes! Cliches! Made-Up Slang! It’s the Data-Sitters Club!
15mBechdel.io: How We Used JavaScript To Help Make Film More Inclusive
35mDecoding bias and narrative in competitive video games
31mAnalyzing Rap Lyrics Using Python
27mLet's get meta! What the data from the joind.in API can teach us about the PHP
03mInterview with Vanessa Borobia