Why is "Chicago" Predictive of Deceptive Reviews? Using LLMs to Discover Language Phenomena from Lexical Cues
This work addresses the challenge of interpretability in deception detection for consumers and businesses, though it is incremental as it builds on existing classifier and LLM techniques.
The paper tackled the problem of interpreting subtle lexical cues learned by deceptive review classifiers by using large language models (LLMs) to translate these cues into human-understandable language phenomena, resulting in phenomena that are empirically grounded, generalizable, and more predictive than prior methods.
Deceptive reviews mislead consumers, harm businesses, and undermine trust in online marketplaces. Machine learning classifiers can learn from large amounts of training examples to effectively distinguish deceptive reviews from genuine ones. However, the distinguishing features learned by these classifiers are often subtle, fragmented, and difficult for humans to interpret. In this work, we explore using large language models (LLMs) to translate machine-learned lexical cues into human-understandable language phenomena that can differentiate deceptive reviews from genuine ones. We show that language phenomena obtained in this manner are empirically grounded in data, generalizable across similar domains, and more predictive than phenomena either in LLMs' prior knowledge or obtained through in-context learning. These language phenomena have the potential to aid people in critically assessing the credibility of online reviews in environments where deception detection classifiers are unavailable.