Detecting Contextomized Quotes in News Headlines by Contrastive Learning

TL;DR

This paper introduces QuoteCSE, a contrastive learning framework that detects contextomized quotes in news headlines by analyzing their semantic alignment with the article body, addressing a challenge in journalistic credibility.

Contribution

The paper proposes a novel contrastive learning approach and provides a new dataset for identifying contextomized quotes in news headlines.

Findings

QuoteCSE effectively detects contextomized quotes.

The framework outperforms baseline methods.

The dataset and code are publicly available.

Abstract

Quotes are critical for establishing credibility in news articles. A direct quote enclosed in quotation marks has a strong visual appeal and is a sign of a reliable citation. Unfortunately, this journalistic practice is not strictly followed, and a quote in the headline is often "contextomized." Such a quote uses words out of context in a way that alters the speaker's intention so that there is no semantically matching quote in the body text. We present QuoteCSE, a contrastive learning framework that represents the embedding of news quotes based on domain-driven positive and negative samples to identify such an editorial strategy. The dataset and code are available at https://github.com/ssu-humane/contextomized-quote-contrastive.