Abstract:
This paper investigates the evolution of investment scam lures and scam-related keywords in the cryptocurrency online forum Bitcointalk over a period of 12 years. Our fin...Show MoreMetadata
Abstract:
This paper investigates the evolution of investment scam lures and scam-related keywords in the cryptocurrency online forum Bitcointalk over a period of 12 years. Our findings show a shift in scam-related keywords found within posts in the forum, where “Ponzi” was the most popular and most frequently mentioned in 2014 and 2018 and “HYIP” appeared more often in 2018 and 2021. We also identify that the financial principle is the tactic more likely to be used to lure people into investment scams from 2015 until 2017, coinciding with the period when “Ponzi” was the most commonly found keyword. This is followed by a transition to the authority and distraction principles from 2018 until 2022, which also coincides with the increase of popularity of “HYIP”.We collect more than 17.8M posts from 399k threads from the forum, from July 2010 until June 2022. Our longitudinal analysis shows the popularity transition between subforums and keywords across time. We design a categorisation criteria and annotate 4,218 posts from 2,630 threads based on it. We then use the annotated sample to train four machine learning statistical models. We use the best performing model to classify all 281k English-language threads into four categories: overt scams, potential scams, scam comments and not investment scam related. We analyze the frequency changes of scam-related threads across the 12 year period and observe that overt and potential scams peaked in 2015 and 2018 respectively. We see that potential scams also increased during the COVID-19 pandemic. We use heuristics to pinpoint the types of cryptocurrencies most frequently used within scam advertisements. Bitcoin is most commonly found in potential scams while Ethereum appears more often than other cryptocurrencies in overt scams. We use machine learning classifiers to identify the scam actor types behind the posts categorised as overt and potential scams. We also classify the type of lure used by scammers. Our results indicate that the t...
Date of Conference: 30 November 2022 - 02 December 2022
Date Added to IEEE Xplore: 06 June 2023
ISBN Information: