Skip to main content

An Artificial Intelligence-Driven Temporal Network Analysis of Myanmar’s Cyber Scam Ecosystem

Eray Arda Akartuna ; Matthew Garnet Manning (2025) — Asian Journal of Criminology

Citation activity

Total citations · Google Scholar
Unavailable
Average per calendar year
Citation count unavailable

Counts reflect Google Scholar’s coverage and do not measure research quality. Source, calculation and limitations

View Original Source (opens in a new tab)

DOI: 10.1007/s11417-025-09474-0 (opens in a new tab)

Country:   Myanmar
Tags:   Crime Displacement, Cyber Scam Compounds, Horizon Scanning, Large Language Models, Myanmar, Pig Butchering, Romance Baiting, Temporal Network Analysis
What do these research terms mean?
Preprint
A manuscript shared before formal peer review and publication. Check whether a later published version is available.
Dataset
A collection of data or examples for others to inspect or reuse. It can appear in Library search and topic mapping, but RSRC does not use dataset records as evidence in Research Insights.
Dissertation or thesis
Research submitted for an academic degree. This describes its format, not its reliability.
Journal article
An article published in a journal. This label alone does not establish peer review, study quality, or how well the findings apply elsewhere.
Qualitative research
Examines experiences, meanings, or processes, often through interviews or observations. It can explain how something happens without estimating how common it is.
Quantitative research
Uses numerical measurements to describe patterns or test relationships. A relationship between two measurements does not by itself show that one causes the other.
Systematic review
Uses a planned, documented method to find and assess research addressing a question. Its conclusions still depend on the included studies and what the search covered.
Meta-analysis
Statistically combines results from multiple studies. Combining studies does not remove weaknesses in their design or make unlike populations interchangeable.
Not classified
This record has no recognized label in this filter. It does not mean the publication used no method, or that no research exists.

Definitions draw on DataCite resource types; Cochrane review methods; NLM: association and causation. RSRC’s dataset and classification rules are explained in our methodology.

Citation tools
Download RIS Download BibTeX 


              
              

            

          

        


      

      

    

        
Transparency

        
Evidence and review status

        
This page contains AI-generated content. No human content review or subject-matter-expert review is recorded.

    


    

                    

                
Source basis

                

                    Downloaded PDF
                

            

                    

                
Source updates

                

                    No notice found at last check
                

            

                    

                
AI-generated page content

                

                    Yes
                

            

                    

                
Automated checks

                

                    Passed
                

            

                    

                
Administrative approval

                

                    Yes
                

            

                    

                
Human content review

                

                    Not recorded
                

            

                    

                
Subject-matter-expert review

                

                    Not recorded
                

            

            


    

        
            How this was prepared
        
        

                            

                    
Source basis

                    

                    
RSRC downloaded and privately stored a copy of the paper for internal analysis. The PDF is not offered to viewers from this page.


                                            
    
                                                            
  • 
                                    PDF added to RSRC:
                                    
                                
    • 
                                                    

                    
                                        

                

                            

                    
Source updates

                    

                    
No incoming update notice was found in the dated Crossref response. Coverage is incomplete, particularly for corrections and expressions of concern; this is not a guarantee that the source is valid or unchanged.


                                            
    
                                                            
  • 
                                    Last source-status attempt:
                                    
                                
    • 
                                                    

                    
                                        

                

                            

                    
AI-generated page content

                    

                    
AI-generated research notes displayed on this page: Synopsis, Identified gaps, Methods, Limitations, Future work. The paper itself is not described as AI-generated.


                                            
    
                                                            
  • 
                                    Document analysis recorded:
                                    
                                
    • 
                                                            
  • 
                                    Synopsis generation recorded:
                                    
                                
    • 
                                                            
  • 
                                    Page record updated:
                                    
                                
    • 
                                                    

                    
                                        

                

                            

                    
Automated checks

                    

                    
The current, source-bound synopsis passed the recorded versioned publication checks.


                                            
    
                                                            
  • 
                                    Checks completed:
                                    
                                
    • 
                                                    

                    
                                            

                            
                                View passed checks (3)
                            
                            
    
                                                                    
  • Length, completeness, repetition, refusal, boilerplate, and active-markup screening
    • 
                                                                    
  • Numerical claims checked against the available source text
    • 
                                                                    
  • English-source lexical grounding check
    • 
                                                            

                        

                                        

                

                            

                    
Administrative approval

                    

                    
An authenticated administrator approved the bibliographic record for public Library display. This is not a review of every research claim.


                                            
    
                                                            
  • 
                                    Approved for public display:
                                    
                                
    • 
                                                    

                    
                                        

                

                            

                    
Human content review

                    

                    
No human review is recorded for the AI-generated content displayed on this page.


                    
                                        

                

                            

                    
Subject-matter-expert review

                    

                    
RSRC has not recorded review of this content by a subject-matter or methods expert.


                    
                                        

                

                    

    


    

        Review-state definitions

        Found a possible error?
        Request a correction.
    



    



              

        
                  

            
Synopsis

            
This publication presents an AI-assisted, temporal network analysis of Myanmar’s industrialized cyber scam ecosystem, focusing on how propagating linkages among criminals, enablers, and enforcers sustain globally consequential fraud operations. The study frames the problem within a broader Southeast Asian context where scam compounds staffed by trafficking victims operate in zones with limited governance, and where technologies such as artificial intelligence, deepfakes, and cryptocurrencies have accelerated criminal capabilities. The authors propose a horizon-scanning approach that uses large language models to construct dynamic networks from open-source reporting, aiming to illuminate operational infrastructures and relationships that underlie the scam economy. Methodologically, the researchers compare multiple commercial LLM tools for entity and relationship extraction, selecting Grok-4 as their primary parser after iterative testing against human coding. They build three interconnected datasets—entities, relationships, and sources—capturing actors, directional ties, quotes, and evidence. The resulting network comprises thousands of entity and relationship entries and is analyzed through centrality concepts and retroduction-informed interpretation, with human checks to manage bias and ambiguity in sources. The authors emphasize that their approach is intended to augment horizon-scanning efforts, not replace expert judgment, and they acknowledge data limitations given the fluid and politically contested reporting surrounding Myanmar’s conflict environment. Principal implications discussed include the resilience and displacement dynamics of the network under enforcement pressures, the practical challenges of direct punitive action against armed groups, and the value of network-informed foresight for anticipating future shifts in the ecosystem. The study also notes limitations related to incomplete edges, potential source bias, and the heuristic nature of centrality interpretations in criminal networks.

          

        
                  

            
Identified Gaps

            
The paper identifies a gap in horizon-scanning methods: apart from desk research, existing approaches rarely directly incorporate on-the-ground insights about criminal infrastructure, relationships, and dynamic change. It also notes that prior social-network research often examines specific groups rather than a broad, multiplex ecosystem involving criminal syndicates, armed groups, businesses, governments, and scam compounds. Systematic validation and reproducibility testing of LLM tools for this task remain absent.

          

        
                  

            
Methods

            
The study used LLM-assisted open-source intelligence collection and temporal social network analysis of Myanmar's cyber scam ecosystem. It identified 1,208 media and research sources through Boolean searches, tested Grok-4, GPT-5, and Gemini-2.5 Pro on five articles, then used Grok-4 to extract entities, relationships, and source quotations. Researchers manually deduplicated and checked the output, producing a directed network of 743 entities and 2,623 relationships. The analysis computed compound reach, bridge, and set-betweenness measures over time and used 50,000-permutation MRQAP models to assess associations between criminal connections and enforcement responses.

          

        
                  

            
Limitations

            
The exploratory network is limited to Myanmar-focused open-source reporting, even though the scam ecosystem is regional; relevant Cambodia-linked material may therefore be missed. It only captures reported and publicly known relationships, not privileged evidence such as direct criminal communications. The single-model extraction approach was not systematically validated using standard performance metrics, and results from the small LLM test are not generalizable. Underlying reporting may also have political bias, particularly because sources sympathetic to Myanmar's Junta were virtually absent. The dataset cannot be publicly shared because it links people to alleged criminality.

          

        
                  

            
Future Work

            
Replicate the approach in other contexts to help standardize best practices for integrating network analysis into foresight. Test advanced time-series analysis, predictive modeling, and multiplex centrality measures where network robustness permits. Conduct resilience analysis to anticipate displacement after hypothetical removal of relationships, such as electricity supplies. Future studies could also combine multiple LLMs and broaden source collection beyond Myanmar to build a more robust network foundation.

          

              

    
    

        
Related Research Insights

        

            See how this publication connects to RSRC's living evidence syntheses through current citations and research-topic mapping.