hollyjackson / NYT_Content_Analysis

This code accompanies the pre-print "The New York Times Distorts the Palestinian Struggle: A Case Study of Anti-Palestinian Bias in American News Coverage of the First and Second Palestinian Intifadas", recently submitted to the Journal of Palestine Studies. The study proves a history of bias against Palestine in the New York Times during the First and Second Palestinian Intifadas.

Francis Ferraro, Max Thomas, Matthew Gormley, Travis Wolfe, Craig Harman, and Benjamin Van Durme. "Concretely Annotated Corpora." In The Proceedings of the NIPS Workshop on Automated Knowledge Base Construction (AKBC). NIPS Workshop 2014.

This script preprocesses the Concretely Annotated New York Times and parses articles related to Israel and/or Palestine in a specific year of a specific Intifada. Before running this script, sort and extract all year-month tar.gz files into two folders, based on the dates of each Intifada.

This script processes articles related to Israel and/or Palestine in the Concretely Annotated New York Times and classifies the voice (active or passive) of all sentences with Israeli or Palestinian subjects. It should be run after preprocessing.py (all pre-processed data must be stored in a subdirectory called sorted_files).

Leave a Comment