Skip to main content

Using Machine Learning Methods to Study Technology-Facilitated Abuse: Evidence from the Analysis of UK Crimestoppers’ Text Data

Abstract

Quantitative evidence on technology-facilitated abuse (“tech abuse”) in intimate partner violence (IPV) contexts is lacking globally. This shortcoming creates barriers to the development of evidence-based interventions. This chapter draws on a data science-driven research project which aims to generate statistical evidence on the nature and extent of IPV tech abuse in the United Kingdom (UK). Using data from the independent UK charity Crimestoppers (2014–2019), we showcase an automated approach, facilitating Natural Language Processing and machine learning methods, to identify tech-abuse cases within large amounts of unstructured text data. The chapter offers both useful insights into the types of tech abuse found within the data, as well as the challenges and benefits computational methodologies provide. The research team has released the code and trained machine learning algorithm along with the publication of this chapter. This hopefully allows other researchers to test, deploy, and further improve the automated approach and could facilitate the analysis of other text datasets to identify tech abuse.

This is a preview of subscription content, access via your institution.

Buying options

Chapter
USD   29.95
Price excludes VAT (USA)
  • DOI: 10.1007/978-3-030-83734-1_24
  • Chapter length: 23 pages
  • Instant PDF download
  • Readable on all devices
  • Own it forever
  • Exclusive offer for individuals only
  • Tax calculation will be finalised during checkout
eBook
USD   169.00
Price excludes VAT (USA)
  • ISBN: 978-3-030-83734-1
  • Instant PDF download
  • Readable on all devices
  • Own it forever
  • Exclusive offer for individuals only
  • Tax calculation will be finalised during checkout
Hardcover Book
USD   219.99
Price excludes VAT (USA)

Notes

  1. 1.

    University College London (UCL) Research Ethics Committee—Project ID Number: 10503/001.

  2. 2.

    The code and the trained model for making predictions can be found at: “https://osf.io/fea5j/?view_only=35786879fdee4d21bc1da71cba3661d1”.

  3. 3.

    For a full list of all stopwords, see Bird et al. (2009).

  4. 4.

    We also extracted n-gram, and POS proportions, but they resulted in lower classification performances.

  5. 5.

    Model parameters were set to l = 1 and dual = False, while the remaining parameters were unchanged (default settings).

References

Download references

Acknowledgements

The authors are indebted to Crimestoppers for sharing their data, the Jill Dando Institute Research Laboratory (JDIRL) for hosting all records, and to Oli Hutt and Nigel Swift for providing us with technical support while using the JDIRL. We are also thankful to the book editors (Dr. Asher Flynn, Dr. Anastasia Powell, and Dr. Lisa Sugiura) for their flexibility and support throughout our analysis and write-up process. Parts of the insights discussed in this publication stem from findings derived from UCL’s “Gender and IoT” research project. The latter has received funding from the UCL Social Science Plus+ scheme, UCL Public Policy, the PETRAS IoT Research Hub (EP/N02334X/1), the UK Home Office, and the NEXTLEAP Project (EU Horizon 2020 Framework Programme for Research and Innovation, H2020-ICT-2015, ICT-10-2015, grant agreement No. 688722). The work was also supported by the Dawes Centre for Future Crime at UCL.

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Leonie Maria Tanczer .

Editor information

Editors and Affiliations

Appendix A: Used Keywords

Appendix A: Used Keywords

Physical devices:

“smart”, “device”, “computer”, “laptop”, “alexa”, “tablet”, “keytracker”, “tracker”, “(smart)-heater”, “light”, “lock”

Online platform apps:

“online”, “technology”, “internet”, “digital”, “dating app”, “facebook”, “systems”, “messages””, “apps”, ““service”, “account”, “platform”, “dating site”, “instagram”, “snapchat”, “tinder”, “app”, “whatsapp”, “spyware”, “find my iPhone”, “find my Friends”, “gps”, “youtube”, “caller id”, “profile”, “sniffer”, “Badoo”, “messenger”, “chat messenger”, “fake account”, “flirtfinder”, “ipad”, “snap chat”, “what’s app”

Verbs:

“dating”, “stalking”, “control”, “victimisation”, “report”, “access”, “texting”, “calling”, “sexting”, “experience”, “bullying”, “rape”, “video”, “use”, “abuse”, “sexualise”, “harass”, “harm”, “perpetrate”, “experiment”, “sharing”, “threat”, “intimate”, “message”, “phone”, “post”, “follow”, “cyberbullying”, “doxing”, “tracking”, “monitoring”, “watching”, “blackmailing”, “humiliate”, “restrict”, “destroy”, “punish”, “force”, “impersonate”, “gaslight”, “controlling”, “distribute”, “hacking”, “attack”, “expose”, “film”, “command”, “spread”, “shout”

Rights and permissions

Reprints and Permissions

Copyright information

© 2021 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this chapter

Verify currency and authenticity via CrossMark

Cite this chapter

Soldner, F., Tanczer, L.M., Hammocks, D., Lopez-Neira, I., Johnson, S.D. (2021). Using Machine Learning Methods to Study Technology-Facilitated Abuse: Evidence from the Analysis of UK Crimestoppers’ Text Data. In: Powell, A., Flynn, A., Sugiura, L. (eds) The Palgrave Handbook of Gendered Violence and Technology. Palgrave Macmillan, Cham. https://doi.org/10.1007/978-3-030-83734-1_24

Download citation

  • DOI: https://doi.org/10.1007/978-3-030-83734-1_24

  • Published:

  • Publisher Name: Palgrave Macmillan, Cham

  • Print ISBN: 978-3-030-83733-4

  • Online ISBN: 978-3-030-83734-1

  • eBook Packages: Social SciencesSocial Sciences (R0)