Detecting Deceptive Reviews using Generative Adversarial Networks

Aghakhani, Hojjat; Machiry, Aravind; Nilizadeh, Shirin; Kruegel, Christopher; Vigna, Giovanni

doi:10.48550/arxiv.1805.10364

Cited by 2 publications

(1 citation statement)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Such models have achieved good results on various generative tasks such as image synthesis (Zhang et al, 2018) and text generation (Yu et al, 2016). Recently, adversarial schemes have begun to be adapted for non-strictly-generative tasks such as fake review detection (Aghakhani et al, 2018), improving the robustness of predictive models to adversarial attacks and image retrieval (Song, 2017).…”

Section: Adversarial Learningmentioning

confidence: 99%

Extractive Adversarial Networks: High-Recall Explanations for Identifying Personal Attacks in Social Media Posts

Carton

Mei

Resnick

2018

Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing

View full text Add to dashboard Cite

We introduce an adversarial method for producing high-recall explanations of neural text classifier decisions. Building on an existing architecture for extractive explanations via hard attention, we add an adversarial layer which scans the residual of the attention for remaining predictive signal. Motivated by the important domain of detecting personal attacks in social media comments, we additionally demonstrate the importance of manually setting a semantically appropriate "default" behavior for the model by explicitly manipulating its bias term. We develop a validation set of humanannotated personal attacks to evaluate the impact of these changes.

show abstract

Section: Adversarial Learningmentioning

confidence: 99%

Extractive Adversarial Networks: High-Recall Explanations for Identifying Personal Attacks in Social Media Posts

Carton

Mei

Resnick

2018

Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing

View full text Add to dashboard Cite

show abstract

Multilingual deep learning framework for fake news detection using capsule neural network

2023

View full text Add to dashboard Cite

Fake news detection is an essential task; however, the complexity of several languages makes fake news detection challenging. It requires drawing many conclusions about the numerous people involved to comprehend the logic behind some fake stories. Existing works cannot collect more semantic and contextual characteristics from documents in a particular multilingual text corpus. To bridge these challenges and deal with multilingual fake news detection, we present a semantic approach to the identification of fake news based on relational variables like sentiment, entities, or facts that may be directly derived from the text. Our model outperformed the state-of-the-art methods by approximately 3.97% for English to English, 1.41% for English to Hindi, 5.47% for English to Indonesian, 2.18% for English to Swahili, and 2.88% for English to Vietnamese language reviews on TALLIP fake news dataset. To the best of our knowledge, our paper is the first study that uses a capsule neural network for multilingual fake news detection.

show abstract

Detecting Deceptive Reviews using Generative Adversarial Networks

Cited by 2 publications

References 0 publications

Extractive Adversarial Networks: High-Recall Explanations for Identifying Personal Attacks in Social Media Posts

Extractive Adversarial Networks: High-Recall Explanations for Identifying Personal Attacks in Social Media Posts

Multilingual deep learning framework for fake news detection using capsule neural network

Contact Info

Product

Resources

About