Tracing Fake-News Footprints: Characterizing Social Media Messages by How They Propagate

@article{Wu2018TracingFF,
  title={Tracing Fake-News Footprints: Characterizing Social Media Messages by How They Propagate},
  author={Liang Wu and Huan Liu},
  journal={Proceedings of the Eleventh ACM International Conference on Web Search and Data Mining},
  year={2018}
}
  • Liang Wu, Huan Liu
  • Published 2 February 2018
  • Computer Science
  • Proceedings of the Eleventh ACM International Conference on Web Search and Data Mining
When a message, such as a piece of news, spreads in social networks, how can we classify it into categories of interests, such as genuine or fake news. [] Key Method Specifically, we propose a novel approach, TraceMiner, to (1) infer embeddings of social media users with social network structures; and (2) utilize an LSTM-RNN to represent and classify propagation pathways of a message. Since content information is sparse and noisy on social media, adopting TraceMiner allows to provide a high degree of…

Figures and Tables from this paper

Unsupervised Fake News Detection on Social Media: A Generative Approach
TLDR
This paper proposes an efficient collapsed Gibbs sampling approach to infer the truths of news and the users’ credibility without any labelled data, and shows that the proposed method significantly outperforms the compared unsupervised methods.
Tracing the fake news propagation path using social network analysis
TLDR
A novel method to learn discriminative features from tweets content, Facebook posts and followed their non-sequential propagation structure, and generated more powerful representations for identifying fake news and its propagation by constructing a social network graph.
Graph Neural Networks with Continual Learning for Fake News Detection from Social Media
TLDR
This work uses graph neural networks to differentiate between the propagation patterns of fake and real news on social media, and proposes a method that achieves balanced performance on both existing and new datasets, by using techniques from continual learning to train GNNs incrementally.
Studying Fake News via Network Analysis: Detection and Mitigation
TLDR
This chapter will review network properties for studying fake news, introduce popular network types, and propose how these networks can be used to detect and mitigate fake news on social media.
Embracing Domain Differences in Fake News: Cross-domain Fake News Detection using Multi-modal Data
TLDR
A novel framework that jointly preserves domain-specific and cross-domain knowledge in news records to detect fake news from different domains is proposed and an unsupervised technique to select a set of unlabelled informative news records for manual labelling is introduced, which can be ultimately used to train a fake news detection model that performs well for many domains while minimizing the labelling cost.
Beyond News Contents : The Role of Social Context for Fake News Detection
TLDR
A tri-relationship embedding framework TriFN is proposed, which models publisher-news relations and user-news interactions simultaneously forfake news classification and significantly outperforms other baseline methods for fake news detection.
Beyond News Contents : The Role of Social Context for Fake News Detection
TLDR
A tri-relationship embedding framework TriFN is proposed, which models publisher-news relations and user-news interactions simultaneously forfake news classification and significantly outperforms other baseline methods for fake news detection.
Beyond News Contents: The Role of Social Context for Fake News Detection
TLDR
A tri-relationship embedding framework TriFN is proposed, which models publisher-news relations and user-news interactions simultaneously forfake news classification and significantly outperforms other baseline methods for fake news detection.
A data-driven model for social media fake news detection
TLDR
A fake news detection model based on data augmentation that can effectively solve the problem of a lack of fake news, and the generalization ability and robustness of the model are improved.
...
...

References

SHOWING 1-10 OF 55 REFERENCES
Fake News Detection on Social Media: A Data Mining Perspective
TLDR
This survey presents a comprehensive review of detecting fake news on social media, including fake news characterizations on psychology and social theories, existing algorithms from a data mining perspective, evaluation metrics and representative datasets, and future research directions for fake news detection on socialMedia.
Relational learning via latent social dimensions
TLDR
This work proposes to extract latent social dimensions based on network information, and then utilize them as features for discriminative learning, and outperforms representative relational learning methods based on collective inference, especially when few labeled data are available.
A new approach to bot detection: Striking the balance between precision and recall
TLDR
A model which increases the recall in detecting bots, allowing a researcher to delete more bots is proposed, and it is shown that the detection algorithm removes more bots from a dataset than current approaches.
Adaptive Spammer Detection with Sparse Group Modeling
TLDR
A group modeling framework that adaptively characterizes social interactions of spammers is proposed that outperforms the state-of-the-art approaches and introduces to integrate content information into the group modeling process.
Leveraging the Implicit Structure within Social Media for Emergent Rumor Detection
TLDR
This work proposes a method for classifying conversations within their formative stages as well as improving accuracy within mature conversations through the discovery of implicit linkages between conversation fragments, and shows that current state-of-the-art rumor classification methods can leverage implicit links to significantly improve the ability to properly classify emergent conversations when very little conversation data is available.
TargetVue: Visual Analysis of Anomalous User Behaviors in Online Communication Systems
TLDR
A novel visual analysis system, TargetVue, is proposed, which detects anomalous users via an unsupervised learning model and visualizes the behaviors of suspicious users in behavior-rich context through novel visualization designs and multiple coordinated contextual views.
The spreading of misinformation online
TLDR
A massive quantitative analysis of Facebook shows that information related to distinct narratives––conspiracy theories and scientific news––generates homogeneous and polarized communities having similar information consumption patterns, and derives a data-driven percolation model of rumor spreading that demonstrates that homogeneity and polarization are the main determinants for predicting cascades’ size.
Relational Learning with Social Status Analysis
TLDR
This paper proposes a novel framework RESA to model social status using the network structure that extracts robust and intrinsic latent social dimensions for social actors, which are further exploited as features for supervised learning models.
Provenance Data in Social Media
TLDR
This lecture reviews the current research on information provenance, explores exciting research opportunities to address pressing needs, and shows how data mining can enable a social media user to make informed judgements about statements published in social media.
LINE: Large-scale Information Network Embedding
TLDR
A novel network embedding method called the ``LINE,'' which is suitable for arbitrary types of information networks: undirected, directed, and/or weighted, and optimizes a carefully designed objective function that preserves both the local and global network structures.
...
...