Skip to main content
SpringerLink
Log in

Anorexia Detection: A Comprehensive Review of Different Methods

  • Conference paper
  • First Online:
Computer Science – CACIC 2021 (CACIC 2021)

Part of the book series: Communications in Computer and Information Science ((CCIS,volume 1584))

Included in the following conference series:

  • 265 Accesses

Abstract

The need for identity validation and self-image approval by the society places adolescents and young adults in a situation of vulnerability. Social networks can make this validation positive, but they could also be a risk factor that triggers various Eating Disorders (ED), particularly, Anorexia Nervosa. Many technologies have already started trying to identify when these risks exist. Thus, our main objective in this work is to analyze the performance of various methods that allow the early detection of anorexia nervosa. In principle we analyze the performance of representations such as k-TVT, Word2Vec, GloVe and BERT’s embeddings, classifying with standard algorithms such as SVM, Naïve Bayes, Random Forest and Logistic Regression. Then, we carry out an analysis of the performance of the classifying models comparing those classical models with methods based on deep learning, such as CNN, LSTM and BERT. As a result, k-TVT, CNN and BERT’s embeddings performed best.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 69.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 89.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Notes

  1. 1.

    https://www.who.int/news-room/fact-sheets/detail/adolescent-mental-health.

  2. 2.

    Pre-trained vectors were obtained from https://nlp.stanford.edu/projects/glove/ and https://s3.amazonaws.com/dl4j-distribution/GoogleNews-vectors-negative300.bin.gz.

  3. 3.

    https://github.com/hanxiao/bert-as-service.

  4. 4.

    https://github.com/google-research/bert.

  5. 5.

    As it ran on a virtual platform Google Colab, memory and disk resources depend on the allocation of the moment, having only chosen GPU environment.

  6. 6.

    https://huggingface.co/bert-base-cased.

References

  1. Aguilera, J., Farías, D.I.H., Ortega-Mendoza, R.M., Montes-y-Gómez, M.: Depression and anorexia detection in social media as a one-class classification problem. Appl. Intell. 51(8), 6088–6103 (2021). https://doi.org/10.1007/s10489-020-02131-2

    Article  Google Scholar 

  2. Blumenstock, J.E.: Size matters: word count as a measure of quality on Wikipedia (2008)

    Google Scholar 

  3. Bucur, A.M., Cosma, A., Dinu, L.P.: Early risk detection of pathological gambling, self-harm and depression using BERT. In: CLEF (2021)

    Google Scholar 

  4. Cagnina, L., Errecalde, M.L., Garciarena Ucelay, M.J., Funez, D.G., Villegas, M.P.: k-TVT: a flexible and effective method for early depression detection. In: XXV Congreso Argentino de Ciencias de la Computación (CACIC) (2019)

    Google Scholar 

  5. Cavnar, W.B., Trenkle, J.M.: N-gram-based text categorization. In: Proceedings of SDAIR-94, 3rd Annual Symposium on Document Analysis and Information Retrieval (1994)

    Google Scholar 

  6. Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. ArXiv abs/1810.04805 (2019)

    Google Scholar 

  7. Funez, D.G., et al.: UNSL’s participation at eRisk 2018 lab. In: CLEF (2018)

    Google Scholar 

  8. Harris, Z.S.: Distributional structure. Word 10(2–3), 146–162 (1954)

    Article  Google Scholar 

  9. Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735–1780 (1997)

    Article  Google Scholar 

  10. LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278–2324 (1998)

    Article  Google Scholar 

  11. McCulloch, W.S., Pitts, W.: A logical calculus of the ideas immanent in nervous activity. Bull. Math. Biophys. 5(4), 115–133 (1943)

    Article  MathSciNet  Google Scholar 

  12. Mikolov, T., Sutskever, I., Chen, K., Corrado, G.S., Dean, J.: Distributed representations of words and phrases and their compositionality. In: NIPS (2013)

    Google Scholar 

  13. Pennington, J., Socher, R., Manning, C.D.: Glove: global vectors for word representation. In: EMNLP (2014)

    Google Scholar 

  14. Ramiandrisoa, F., Mothe, J.: Early detection of depression and anorexia from social media: a machine learning approach. In: CIRCLE (2020)

    Google Scholar 

  15. Rizwan, B., et al.: Increase in body dysmorphia and eating disorders among adolescents due to social media. Pakistan BioMed. J. 5(1) (2022)

    Google Scholar 

  16. Rumelhart, D.E., Hinton, G.E., Williams, R.J.: Learning representations by back-propagating errors. Nature 323(6088), 533–536 (1986)

    Article  Google Scholar 

  17. Shah, F.M., et al.: Early depression detection from social network using deep learning techniques. In: 2020 IEEE Region 10 Symposium (TENSYMP) pp. 823–826 (2020)

    Google Scholar 

  18. Vaswani, A., et al.: Attention is all you need. ArXiv abs/1706.03762 (2017)

    Google Scholar 

  19. Villegas, M.P., Errecalde, M.L., Cagnina, L.: A comparison of text representation approaches for early detection of anorexia. In: XXVII Congreso Argentino de Ciencias de la Computación (CACIC) (Modalidad virtual), pp. 301–310 (2021)

    Google Scholar 

  20. Wang, Y.T., Huang, H.H., Chen, H.H.: A neural network approach to early risk detection of depression and anorexia on social media text. In: CLEF (2018)

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Laboratorio de Investigación y Desarrollo en Inteligencia Computacional, Universidad Nacional de San Luis (UNSL), Ejército de los Andes 950, 5700, San Luis, Argentina

    María Paula Villegas, Leticia Cecilia Cagnina & Marcelo Luis Errecalde

  2. Consejo Nacional de Investigaciones Científicas y Técnicas (CONICET), San Luis, Argentina

    María Paula Villegas & Leticia Cecilia Cagnina

Authors
  1. María Paula Villegas
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Leticia Cecilia Cagnina
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Marcelo Luis Errecalde
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to María Paula Villegas .

Editor information

Editors and Affiliations

  1. National University of La Plata, La Plata, Argentina

    Patricia Pesado

  2. National University of Salta, Salta, Argentina

    Gustavo Gil

Rights and permissions

Reprints and permissions

Copyright information

© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Villegas, M.P., Cagnina, L.C., Errecalde, M.L. (2022). Anorexia Detection: A Comprehensive Review of Different Methods. In: Pesado, P., Gil, G. (eds) Computer Science – CACIC 2021. CACIC 2021. Communications in Computer and Information Science, vol 1584. Springer, Cham. https://doi.org/10.1007/978-3-031-05903-2_12

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-05903-2_12

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-05902-5

  • Online ISBN: 978-3-031-05903-2

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation