Atondo Siu, Gilberto;
Hutchings, Alice;
Vasek, Marie;
Moore, Tyler;
(2022)
“Invest in crypto!”: An analysis of investment scam advertisements found in Bitcointalk.
In:
Proceedings of theSymposium on Electronic Crime Research 2022.
APEG: Online.
Preview |
Text
eCrime_paper___IEEE_Conference_Template.pdf - Published Version Download (558kB) | Preview |
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 time principle is not a tactic used as frequently as expected. Finally, we observe the influence of the pandemic in the strategies used to lure victims, reflected in higher than expected use of the kindness principle in 2021 and 2022.
| Type: | Proceedings paper |
|---|---|
| Title: | “Invest in crypto!”: An analysis of investment scam advertisements found in Bitcointalk |
| Event: | Symposium on Electronic Crime Research |
| Open access status: | An open access version is available from UCL Discovery |
| Publisher version: | https://apwg.org/event/ecrime2022/ |
| Language: | English |
| Additional information: | This version is the author accepted manuscript. For information on re-use, please refer to the publisher’s terms and conditions. |
| Keywords: | cybercrime, cryptocurrency, Bitcoin, investment scams, machine learning, natural language processing |
| UCL classification: | UCL UCL > Provost and Vice Provost Offices > UCL BEAMS UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Computer Science |
| URI: | https://discovery.ucl.ac.uk/id/eprint/10164686 |
Loading...
Loading...Loading...Loading...Archive Staff Only
 |
View Item |
