CSI: A Hybrid Deep Model for Fake News Detection

By Natali Ruchansky, Sungyong Seo, Yan Liu. International Conference on Information and Knowledge Management, 2017

1,063 citations recorded by the source corpus.

The topic of fake news has drawn attention both from the public and the academic communities. Such misinformation has the potential of affecting public opinion, providing an opportunity for malicious parties to manipulate the outcomes of public events such as elections. Because such high stakes are at play, automatically detecting fake news is an important, yet challenging problem that is not yet well understood. Nevertheless, there are three generally agreed upon characteristics of fake news: the text of an article, the user response it receives, and the source users promoting it. Existing work has largely focused on tailoring solutions to one particular characteristic which has limited their success and generality. In this work, we propose a model that combines all three characteristics for a more accurate and automated prediction. Specifically, we incorporate the behavior of both parties, users and articles, and the group behavior of users who propagate fake news. Motivated by the three characteristics, we propose a model called CSI which is composed of three modules: Capture, Score, and Integrate. The first module is based on the response and text; it uses a Recurrent Neural Network to capture the temporal pattern of user activity on a given article. The second module learns the source characteristic based on the behavior of users, and the two are integrated with the third module to classify an article as fake or not. Experimental analysis on real-world data demonstrates that CSI achieves higher accuracy than existing models, and extracts meaningful latent representations of both users and articles.

Subfields: Artificial Intelligence, Information Systems, Sociology and Political Science

View Paper: https://www.semanticscholar.org/paper/cefaf434d84f54bbf83a13691db58f37d9ed6e6a

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Bo Li
2. Philip S. Yu
3. Lichao Sun
4. Huan Liu
5. Kai Shu
6. Yi-Ju Lu
7. Cheng-Te Li
8. Xinyi Zhou

In Information Systems

1. Xinyi Zhou
2. Huan Liu
3. Kai Shu
4. Pratik Narang
5. Rohit Kumar Kaliyar
6. Reza Zafarani
7. Xinyi Zhou
8. Jing Qian

In Sociology and Political Science

1. Xinyi Zhou
2. Kai Shu
3. Yi-Ju Lu
4. Cheng-Te Li
5. Pratik Narang
6. Rohit Kumar Kaliyar
7. Reza Zafarani
8. Xinyi Zhou

Citations in the corpus

• Multimodal Fusion with Co-Attention Networks for Fake News Detection (2021, background): “Following the previous work (Ruchansky et al., 2017; Shu et al., 2017), we specify that fake news is the news that is intentionally fabricated and can be verified as false .”
• Mining Dual Emotion for Fake News Detection (2019, background): “The dataset Weibo-16 is firstly proposed in [26] and has been a benchmark dataset of fake news detection in Chinese [17, 38, 47].”
• Fake News Detection Using Machine Learning Ensemble Methods (2020, background): “In the current fake news corpus, there have been multiple instances where both supervised and unsupervised learning algorithms are used to classify text [20, 21].”
• Combating Fake News (2019, methodology): “To detect group behaviours, Ruchansky et al. 2017 constructed a weighted user-user graph where an edge between users denotes the number of articles that both have co-engaged with.”
• DeClarE: Debunking Fake News and False Claims using Evidence-Aware Deep Learning (2018, neutral): “…et al., 2015; Volkova et al., 2017) propose supervised methods for detecting deceptive content in social media platforms like Twitter, Sina Weibo, etc. Similarly, approaches like Ma et al. (2016); Ruchansky et al. (2017) use neural network methods to identify fake news and rumors on social media.”
• FakeBERT: Fake news detection in social media with a BERT-based deep learning approach (2021, methodology): “In the context of writing style, fake news is written or published with the intent to mislead the people and to damage the image of an agency, entity, person, either for financial or political benefits [14, 35, 39, 53].”
• Fake news, disinformation and misinformation in social media: a review (2023, neutral): “However, it has proven challenging to successfully auto-mate fake news detection based on just a single type of feature (Ruchansky et al. 2017).”
• Deep Learning for Anomaly Detection: A Survey (2019, methodology): “…SVDD: Support Vector Data Description, RNN : Recurrent Neural Networks Relief: Feature selection Algorithm Kira and Rendell [1992], KNN: K-Nearest Neighbours Altman [1992] CSI: Capture, Score, and Integrate Ruchansky et al. [2017]. number of hidden layers used for representative feature learning.”
• Fake News: A Survey of Research, Detection Methods, and Opportunities (2018, methodology): “en utilized. Deep learning techniques can skip feature engineering and automatically represent features; thus, have been widely applied to many problems including fake news detection [Liu and Wu2018; Ruchansky et al. 2017;Wang et al. 2018;Yang et al. 2018;Zhang et al. 2018]. Similarly, matrix factor”
• User Preference-aware Fake News Detection (2021, background): “In addition, computational approaches using feature engineering or deep learning have shown many promising results [3, 12, 23, 31].”
• GCAN: Graph-aware Co-Attention Networks for Explainable Fake News Detection on Social Media (2020, background): “(5) CSI (Ruchansky et al., 2017): a state-of-the-art fake news detection model incorporating articles, and the group behavior of users who propagate fake news by using LSTM and calculating the user scores.”