Association rule mining detects news framing without annotations
Mining Frames: Association Rule Mining as an Unsupervised Framework for News Framing Detection
Computation and LanguageComputers and SocietyInformation Retrieval
Summary
Many methods to analyze how news stories frame events rely on large sets of labeled examples, limiting their use for less common languages or new events. This paper shows how treating sentences or articles as collections of words and finding frequent word patterns can reveal common frames without needing labeled data. The authors tested their approach on thousands of news articles about the Gaza war and found consistent framing patterns across outlets and time. They also confirmed the method works on Arabic news articles about another conflict and shared supporting code.
What this means in practice
- •For newsroom data teams: Identify dominant framing patterns in news articles across different media outlets without needing manual annotations or predefined categories.
- •For multilingual social media analysts: Detect emerging frames in low-resource or non-English languages for new events by mining frequent word associations in large text collections.
Authors
Hager Hesham Mustafa
Abstract
Computational framing analysis is dominated by supervised classifiers that require large annotated corpora and predefined frame taxonomies, limiting their use for non-English languages, novel events, and low-resource settings. This paper presents Association Rule Mining (ARM) as an unsupervised, annotation-free framework for news framing detection. Each document or sentence is treated as a transaction of lexical items, and high-lift co-occurrence rules are read as candidate framing signals (Gamson and Modigliani's condensing symbols), confirmed in context by journalist-researchers. The primary validation is Framing Gaza: 25,512 English-language articles from 16 US, UK, French, and German outlets covering the first year of the Gaza war (October 2023 to October 2024), analyzed with Apriori (mlxtend), platform-weighted support, POS-filtered n-grams, and lift-based scoring. ARM inductively surfaces interpretable patterns without predefined categories: a cross-platform military frame, {israeli, strike} to {kill}, appears as a closed rule in 14 of 16 outlets, and a month-by-month analysis recovers event-driven framing pivots (e.g., the April 2024 World Central Kitchen strike) with no prior event labeling. A systematic headline-body divergence is identified, with headlines carrying concentrated, high-lift editorial framing and body text reproducing institutional, procedural language. A methodological validation on the Seven Days project (1,575 Arabic articles on the 2026 Iran war) shows that FP-Growth enables sentence-level analysis with far lower memory overhead. Findings were validated through editorial uptake: two published investigative stories (Daraj Media; Saheeh Masr). Preprocessing code is released openly; the full pipeline is documented but withheld to preserve operational deployability.