PersaLog: Personalization of News Article Content
summary
PersaLog is a newsroom tool that lets journalists embed a simple domain-specific language in HTML to personalize article text and visualizations, then transpile to JavaScript for client- or server-side rendering. The team surveys 22 newsroom staff and interviews 3 authors, implements age/city/lat-long/inferred-occupation variables, supports segment by rules and external data binding, and recreates NYT/Guardian examples and Post case studies; lab tests with journalism students show authors can read, edit, and generate personalized content.
AI-written summary · about
chapters (12)
- 0:00Introduction and background
- 2:53From personalized feeds to content
- 5:39Challenges for journalists
- 7:47Design goals for PersaLog
- 9:12How PersaLog works
- 11:15PersaLog language basics
- 13:42Segmentation examples
- 15:29Hyperlocal personalization demo
- 16:54Transpiling and embedding
- 17:39Modifying graphics
- 18:21Evaluation and future work
- 19:03Conclusion and Q&A
related talks
12mPOET: Supporting Prompting Creativity and Personalization with Automated Expansion of Text-to-Ima...
01h 00mThe Future of Content: Context-Aware, Centralized, and Written by Robots
09mRethinking AI: Building What Matters, Not Just What's Possible
26mHow To Win Friends & Influence LLMs (with Prompt Engineering)
13mStrategies for Enhanced Personal Knowledge Management
48mGenerative AI and Email Personalization
13mAI language models in journalism
41m"Natural Interfaces" and "Natural Language Programming"