Character N-Grams for Detecting Deceptive Controversial Opinions

Abstract

Controversial topics are present in the everyday life, and opinions about them can be either truthful or deceptive. Deceptive opinions are emitted to mislead other people in order to gain some advantage. In the most of the cases humans cannot detect whether the opinion is deceptive or truthful, however, computational approaches have been used successfully for this purpose. In this work, we evaluate a representation based on character n-grams features for detecting deceptive opinions. We consider opinions on the following: abortion, death penalty and personal feelings about the best friend; three domains studied in the state of the art. We found character n-grams effective for detecting deception in these controversial domains, even more than using psycholinguistic features. Our results indicate that this representation is able to capture relevant information about style and content useful for this task. This fact allows us to conclude that the proposed one is a competitive text representation with a good trade-off between simplicity and performance.

Untitled

“…Cardoso et al [7] evaluated content-based classification methods, revealing a temporal shift in data features that affected model performance over time. Sánchez-Junquera et al [8] proposed a method using n-gram features, outperforming some methods in identifying fake reviews but falling short when compared to alternative approaches.…”

Fake Reviews Detection: A Survey

“…Sánchez-Junquera, et al [139] proposed a fake review detection model based on the character n-gram feature. They used a support vector machine and Naïve Bayes as classification algorithms.…”

Masking domain-specific information for cross-domain deception detection

“…More sophisticated features, such as deep syntactic patterns (Feng et al, 2012), argumentative features (Cocarascu and Toni, 2016), and word embeddings (Ren and Ji, 2017), were also successfully evaluated. More recently, the character n-grams features have shown a good trade-off between simplicity and performance for detecting deception in online reviews and essays on controversial topics (Cagnina and Rosso, 2017;Sánchez-Junquera et al, 2018). All these works found that both content and style are important factors to distinguish deception from truth.…”