Disinformation in Open Online Media: 5th Multidisciplinary International Symposium, MISDOOM 2023, Amsterdam, The Netherlands, November 21–22, 2023, Proceedings (Lecture Notes in Computer Science)

Preface
Organization
Keynote Talks
	From Opacity to Clarity: Embracing Transparent and Accountable Fact Verification
	The User and the Algorithm: A Tug of War or Allies?
	Contents
Generative AI for Explainable Automated Fact Checking on the FactEx: A New Benchmark Dataset
	1 Introduction
	2 Related Work
	3 Methodology
		3.1 The FactEx Dataset
		3.2 Preprocessing and Methods
		3.3 Evaluation
	4 Results and Discussion
		4.1 LLMs and Seq2Seq Results Comparison
		4.2 Model’s Performance vs Dataset Size
	5 Conclusion and Future Work
	References
Multi-Modal Embeddings for Isolating Cross-Platform Coordinated Information Campaigns on Social Media
	1 Introduction
	2 Related Work
	3 Datasets
	4 Methodology
		4.1 Assumptions
		4.2 Text (Semantic) Similarity
		4.3 Network Similarity: Random Walks
		4.4 Temporal Dynamics
	5 Results
		5.1 Metrics
		5.2 Evaluation: Ablation Study
		5.3 Coordinated Campaigns
		5.4 Limitations
	6 Summary
	References
FaKy: A Feature Extraction Library to Detect the Truthfulness of a Text
	1 Introduction
	2 Related Work
	3 Research Methodology and Experimental Design
		3.1 Data Collection
		3.2 Experiment Pipeline
		3.3 Classification
		3.4 Evaluation
	4 Results and Discussion
		4.1 Distinguishing True and False Claims: Insights from IC, Readability, VSS, NER, and POS Tags.
		4.2 Classifying Fake Claims: Insights from NB, RF, and GB
		4.3 Limitations & Future Research
	5 Conclusion
	References
From Sharing Misinformation to Debunking It: How Coordinated Image Text Sharing Behaviour is Used in Political Campaigns on Facebook
	1 Introduction
	2 Methods
	3 Results
		3.1 What is the Network Structure Based on Accounts Involved in Coordinated Behaviour?
		3.2 What are the Political Affiliations of Facebook Accounts Engaged in Coordinated Behaviour?
		3.3 What is the Content Shared in Different Clusters of Coordinated Accounts?
	4 Discussion
	5 Conclusion
	References
The Information Disorder Level (IDL) Index: A Human-Based Metric to Assess the Factuality of Machine-Generated Content
	1 Introduction
	2 Method
	3 Results
	4 Conclusion
	References
Lost in Transformation: Rediscovering LLM-Generated Campaigns in Social Media
	1 Introduction
	2 Background
		2.1 Campaign Detection
		2.2 LLM-Generated Content Detection
	3 Detection of Artificial Content in Social Media Campaigns
		3.1 Transformer-Based Siamese Neural Network Approach
		3.2 Traditional ML Models
	4 Experimental Setup
		4.1 Data Collection
		4.2 Siamese Neural Network Setup
		4.3 ML Models Setup
	5 Results
		5.1 Detection Quality of the SNN
		5.2 Detection Quality of the Standard Approaches
		5.3 Pattern Rediscovery Capabilities
	6 Discussion and Conclusion
	References
The Effect of Misinformation Intervention: Evidence from Trump\'s Tweets and the 2020 Election
	1 Introduction
	2 Twitter\'s Moderation of Trump\'s Tweets in 2020
	3 Does Labelling and Limiting Misinformation Work?
	4 Data
	5 Effects of Trump\'s Tweets
	6 Effects of Twitter\'s Actions
	7 Discussion
	References
Coordinated Information Campaigns on Social Media: A Multifaceted Framework for Detection and Analysis
	1 Introduction
	2 Related Work
	3 Methodology
		3.1 Co-Sharing Network Construction
		3.2 Network Backbone Extraction
		3.3 Community Detection
		3.4 Edge Feature Extraction
		3.5 Anomaly Detection
	4 Datasets
	5 Results
		5.1 Extracting the Backbone of Co-Sharing Networks
		5.2 Anomaly Detection Using Isolation Forest
		5.3 Qualitative Analysis of Anomalous Clusters
	6 Conclusions and Future Work
	References
Unveiling Truth Amidst the Pandemic: Multimodal Detection of COVID-19 Unreliable News
	1 Introduction
	2 Related Work
	3 Dataset
	4 Methodology
		4.1 Fine-Tuned BERT for Text Embedding
		4.2 CLIP for Image Embedding
		4.3 Classification
	5 Experiments
		5.1 Experimental Settings
		5.2 Analysis and Discussion
	6 Conclusions, Limitations, and Future Work
	References
Holistic Analysis of Organised Misinformation Activity in Social Networks
	1 Introduction
	2 Previous Work
		2.1 Content Analysis
		2.2 Social Network Analysis
		2.3 Multi-modal Analysis
	3 Problem Statement
	4 Towards a Holistic Methodology for Disinformation Analysis
		4.1 Disinformation Detection at the Message Level in Multiple Modalities
		4.2 Disinformation Detection at Social Network Level
		4.3 Studying the Context Behind Intentional Spreading of Misleading Information
		4.4 Holistic Integration and Prediction
	5 Risks and Challenges
	6 Conclusion
	References
Towards Multimodal Campaign Detection: Including Image Information in Stream Clustering to Detect Social Media Campaigns
	1 Introduction
	2 Background
		2.1 Multimodal Campaign Detection
		2.2 Image Captioning Models
		2.3 Implemented Approach
	3 Experimental Setup
		3.1 Objective 1 - Image Captioning Model Configuration
		3.2 Objective 2 - Image Information for Campaign Detection
	4 Results
		4.1 Objective 1 - Image Captioning Model Configuration
		4.2 Objective 2 - Image Information for Campaign Detection
	5 Conclusion
	References
ChatGPT as a Commenter to the News: Can LLMs Generate Human-Like Opinions?
	1 Introduction
	2 Related Work
		2.1 Large Language Models and GPT-3.5
		2.2 BERT
		2.3 Previous Research on GPT-3.5\'s Capabilities
	3 Methods
		3.1 Data Collection
		3.2 Generating Opinions with GPT-3.5
		3.3 Evaluation Through Classification
	4 Results
		4.1 Output
		4.2 Classification Results
		4.3 Lexical Diversity
		4.4 Qualitative Analysis
	5 Discussion
	6 Conclusion
	References
Is Foreign Language News More or Less Credible Than Native Language News? Examining the Foreign Language Effect on Credibility Perceptions
	1 Introduction
	2 Theoretical Background
		2.1 Credibility Perceptions of News
		2.2 The Foreign Language Effect
		2.3 Credibility Perceptions and the FLE
	3 Method
		3.1 Sample and Procedure
		3.2 Dependent Variables
		3.3 Independent Variables
	4 Results
	5 Discussion
		5.1 Limitations and Future Studies
	6 Conclusion
	References
Author Index