Skip to main content

Building of safer urban hubs: Insights from a comparative study on cyber telecom scams and early warning design

Zhu, Chunjin ; Zhang, Chenlu ; Wang, Renke ; Tian, Jingwen ; Hu, Ruoxuan ; Zhao, Jingtong ; Ke, Yaxin ; Liu, Ning (2023) — Urban Governance

View Original Source (opens in a new tab)

DOI: 10.1016/j.ugj.2023.05.004 (opens in a new tab)

Type:   Journal Article
Country:   China
Tags:   AI-Enabled Fraud, Cross Border Cooperation, Cyber Telecom Scams, Early Warning, Fraud Detection, Romance Scams, Victim Experience, Victim Profiling
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
                

            

                    

                
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:
                                    
                                
    • 
                                                    

                    
                                        

                

                            

                    
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 examines how data analytics can support antifraud efforts to create safer urban hubs, focusing on cyber telecom scams in Mainland China and Hong Kong. The authors aim to understand victim profiles and scam patterns through a comparative lens, and to explore how data-driven methods can bolster early warning and public guidance against fraud. Using public news reports and open-source message datasets collected between 2018 and 2021, the study applies data mining and machine learning to identify scam techniques and to build victim portraits via a target group index (TGI). They labeled messages as fraudulent or nonfraudulent, performed natural language processing to extract meaningful features, and tested several classifiers to detect fraudulent messages. The best-performing model was a decision tree, achieving about 97% accuracy on their test set. The analysis also maps scam types to victim characteristics across gender, age, occupation, and region, revealing regional and demographic variations in vulnerability and highlighting impersonation and finance-related schemes as prevalent concerns. The authors discuss implications for policy and practice, including cross-border information sharing, targeted antifraud publicity, and the potential for sentiment- and portrait-based messaging to reduce scam exposure. They acknowledge limitations, such as reliance on media reports for case data, which may not fully represent all fraud activity, and call for further refinement of models (e.g., incorporating newer NLP techniques) and broader data access to improve accuracy and generalizability. Overall, the study demonstrates how data analytics can inform public governance and antifraud strategies in urban settings, while noting the need for cautious interpretation and ongoing methodological enhancement.

          

        
                  

            
Identified Gaps

            
The paper identifies limited access to precise fraud data, the early stage of comparative research between Mainland China and Hong Kong because of information-sharing barriers, and limited use of big data for proactive early-warning design rather than retrospective investigation.

          

        
                  

            
Methods

            
The study crawled publicly available news and website reports on cyber-telecom scams in Mainland China and Hong Kong from October 2018 to December 2021. It constructed victim profiles using target group index analysis and processed Chinese messages with NLP, TF-IDF, and singular value decomposition. It trained and compared decision tree, SVM, logistic regression, and naive Bayes classifiers using a 70/30 train-test split.

          

        
                  

            
Limitations

            
Cases came from reputable news websites rather than comprehensive official records and may not represent all fraud cases. Privacy-protective reporting limited available victim information and made modeling harder. Comparisons are constrained by economic, cultural, social-interaction, language, and geographic-scale differences between Mainland China and Hong Kong.

          

        
                  

            
Future Work

            
Future studies should obtain more comprehensive data from multiple sources, optimize comparison methods and predictive analytics, and improve the classifier before practical deployment. The authors specifically suggest BERT or neural-network approaches to raise accuracy to at least 99.99%.

          

              

    
    

        
Related Research Insights

        

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