Automatic Fake News Detection: Are current models "fact-checking" or "gut-checking"?

TL;DR

This paper investigates whether current fake news detection models truly reason about facts or rely on superficial signals like emotion and sentiment, proposing methods to neutralize these signals and improve factual reasoning.

Contribution

The paper demonstrates that many models depend on manipulable signals rather than genuine reasoning, and introduces an emotion-based attention model to enhance fact verification.

Findings

Models can perform well without claim content by exploiting superficial signals.

Neutralizing extraneous signals forces models to use both claims and evidence.

Emotion vectors and attention improve fact-checking robustness.

Abstract

Automatic fake news detection models are ostensibly based on logic, where the truth of a claim made in a headline can be determined by supporting or refuting evidence found in a resulting web query. These models are believed to be reasoning in some way; however, it has been shown that these same results, or better, can be achieved without considering the claim at all -- only the evidence. This implies that other signals are contained within the examined evidence, and could be based on manipulable factors such as emotion, sentiment, or part-of-speech (POS) frequencies, which are vulnerable to adversarial inputs. We neutralize some of these signals through multiple forms of both neural and non-neural pre-processing and style transfer, and find that this flattening of extraneous indicators can induce the models to actually require both claims and evidence to perform well. We conclude with the construction of a model using emotion vectors built off a lexicon and passed through an "emotional attention" mechanism to appropriately weight certain emotions. We provide quantifiable results that prove our hypothesis that manipulable features are being used for fact-checking.