Skip to main content

The tinder swindler: Analyzing public sentiments of romance fraud using machine learning and artificial intelligence

Mark E. Lokanan (2023) — Journal of Economic Criminology

View Original Source (opens in a new tab)

DOI: 10.1016/j.jeconc.2023.100023 (opens in a new tab)

Type:   Journal Article
Country:   Canada
Tags:   Bert, Impression Management, Machine Learning, Romance Scams, Sentiment Analysis, Tinder Swindler, Twitter, Victim Blaming
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:
                                    
                                
    • 
                                                            
  • 
                                    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

                    

                    
The record is approved for public display, but a complete historical administrator action is not recorded.


                    
                                        

                

                            

                    
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 study analyzed 47,876 Twitter posts from 29,630 unique users containing #tinderswindler between February 1 and March 18, 2022. It used TextBlob to classify polarity and subjectivity and compared several machine-learning and neural sentiment models, framing interpretation through Goffman's impression-management theory. The author reports that classifications were predominantly neutral or positive and relatively infrequently negative; negative vocabulary also included victim-blaming terms portraying the defrauded women as desperate, unintelligent, or deserving of harm. These labels describe discourse around one documentary and hashtag, not public approval of romance fraud generally. Sarcasm, missing conversational context, algorithmic labeling error, and self-selected Twitter participation limit interpretation of individual posts and broader public sentiment.

          

        
                  

            
Identified Gaps

            
The paper identifies a gap in applying Goffman’s impression-management theory to relational dynamics in romance fraud and states that no prior work had analyzed fraudsters’ actions through a Goffmanesque narrative lens. It also notes a need for more rigorous scientific analysis of self-presentation on social media. Methodologically, sentiment analysis has difficulty interpreting contextual meaning, irony, and sarcasm.

          

        
                  

            
Methods

            
The study collected 47,876 Twitter posts using #tinderswindler from 1 February to 18 March 2022 (29,630 unique users). Tweets were cleaned, anonymized, tokenized, stemmed/lemmatized, and vectorized with bag-of-words and TF-IDF. TextBlob generated polarity and subjectivity classifications. Sentiment prediction compared Naïve Bayes, SVM, random forest, CNN, RNN+LSTM, and BERT models using a 60:20:20 train-validation-test split. The analysis was framed by Goffman’s impression-management theory.

          

        
                  

            
Limitations

            
Sentiment is subjective and a tweet may reflect personal experience, irrationality, or sarcasm. Although the large aggregate sample was used to dilute outliers and bias, sentiment analysis can analyze text without adequate context, and algorithms struggle to distinguish ironic or sarcastic content. These issues caution against interpreting individual tweet-level classifications as definitive evidence of users’ views.

          

        
                  

            
Future Work

            
Develop NLP/ML methods that can separate irrational and sarcastic tweets and preserve relevant textual context. Refine and optimize deep-learning approaches for sentiment analysis of romance-fraud discussions. Apply sentiment findings to test targeted awareness, moderation, and dating-platform interventions addressing manipulation and victim blaming.

          

              

    
    

        
Related Research Insights

        

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