Paper

This is the companion site for the Rookie paper [PDF], presented at the Data science + Journalism workshop at KDD 2017 [slides].

Abram Handler and Brendan O'Connor created Rookie, which began as a newsroom project at The Lens in New Orleans with help from Steve Myers.

The Knight Foundation funded initial work on Rookie through a prototype grant.

Abstract

News archives are an invaluable primary source for placing current events in historical context. But current search engine tools do a poor job at uncovering broad themes and narratives across documents. We present Rookie: a practical soft‰ware system which uses natural language processing (NLP) to help readers, reporters and editors uncover broad stories in news archives. Unlike prior work, Rookie's design emerged from 18 months of iterative development in consultation with editors and computational journalists. ŒThis process lead to a dramatically different approach from previous academic systems with similar goals. Our efforts off‚er a generalizable case study for others building real-world journalism software using NLP.

BibTex

@inproceedings{Handler17,
author = {Handler, Abram and O'Connor, Brendan},
title = {Rookie: A unique approach for exploring news archives},
booktitle = {Workshop on Data Science + Journalism at KDD 2017},
year = 2017,
address = {Halifax, Canda},
}