Analysing language in Internet support groups for mental health
Keywords:
natural language processing, machine learning, text classification, mental healthAbstract
Assisting moderators to triage critical posts in Internet Support Groups is relevant to ensure its safe use. Automated text classification methods analysing the language expressed in posts of online forums is a promising solution. Natural Language Processing and Machine Learning technologies were used to build a triage post classifier using a dataset from Reachout.com mental health forum. When comparing with the state-of-the-art, our solution achieved the best classification performance for the crisis posts (52%), which is the most severe class.
References
Altszyler, E., Berenstein, A. J., Milne, D. N., Calvo, R. A. y Slezak, D. F. (2018). Using contextual information for automatic triage of posts in a peer-support forum. En Loveys, K., Niederhoffer, K., Prud’hommeaux, E., Resnik, R., y Resnik, P., editors, Proceedings of the Fifth Workshop on Com- putational Linguistics y Clinical Psychology: From Keyboard to Clinic, CLPsych@NAACL-HTL, New Orleans, LA, USA, June 2018, pp. 57–68. Association for Computational Linguistics.
Carron-Arthur B., Ali K., Cunningham JA. y Griffiths KM (2015). From help-seekers to influential users: A systematic review of participation styles in online health communities. Journal of Medical Internet Research.
Brew, C. (2016). Classifying reachout posts with a radial basis function svm. En Proceedings of the Third Workshop on Computational Linguistics and Clinical Psychology, págs. 138–142. Association for Computational Linguistics.
Cash, S.J., Thelwall, M., Peck, S.N., Ferrell, J.Z. y Bridge, J. A. (2013). Adolescent suicide statements on myspace. Cyberpsychology, Behavior, and Social Networking, 16(3):166–174. PMID: 23374167.
Cimino, A., Cresci, S., Dell’Orletta, F. y Tesconi, M. (2014). Linguistically-motivated y lexicon features for sentiment analysis of italian tweets. 4th evaluation campaign of Natural Language Processing and Speech tools for Italian (EVALITA 2014), pp. 81–86.
Cohan, A., Young, S. y Goharian, N. (2016). Triaging mental health forum posts. En Proceedings of the Third Workshop on Computational Linguistics and Clinical Psychology, pp. 143–147, San Diego, CA, USA. Association for Computational Linguistics.
Conway, M. y O’Connor, D. (2016). Social media, big data, y mental health: current advances y ethical implications. Current Opinion in Psychology, 9:77–82. Social media and applications to health behavior.
Gerrard, Y. (2018). Beyond the hashtag: Circumvent- ing content moderation on social media. New Media & Society, 20(12):4492–4511.
Gkotsis, G., Velupillai, S., Oellrich, A., Dean, H., Liakata, M. y Dutta, R. (2016). Don’t let notes be misunderstood: A negation detection method for assessing risk of suicide in mental health records. En Proceedings of the Third Workshop on Computational Linguistics and Clinical Psychology, pp. 95–105, San Diego, CA, USA. Association for Computational Linguistics.
Griffiths, K. M. (2017). Mental health internet support groups: just a lot of talk or a valuable intervention? World Psychiatry, 16(3):247–248.
Hartzler, A. y Pratt, W. (2011). Managing the personal side of health: How patient expertise differs from the expertise of clinicians. J Med Internet Res, 13(3):e62.
Hollingshead, K., Irely, M. E. y Loveys, K., (eds.) (2017). Proceedings of the Fourth Workshop on Computational Linguistics y Clinical Psychology — From Linguistic Signal to Clinical Reality. Association for Computational Linguistics, Vancouver, BC.
Huh, J., Yetisgen-Yildiz, M. y Pratt, W. (2013). Text classification for assisting moderators in online health communities. Journal of Biomedical Informatics, 46(6):998–1005. Special Section: Social Media Environments.
Islam, M.R., Kabir, M.A., Ahmed, A., Kamal, A. R. M., Wang, H. y Ulhaq, A. (2018). Depression detection from social network data using machine learning techniques. Health Information Science y Systems, 6(1):8.
Kaplan, K., Salzer, M., Solomon, P., Brusilovskiy, E. y Cousounis, P. (2011). Internet peer support for individuals with psychiatric disabilities: A randomized controlled trial. 72:54– 62.
Kim, S. M., Wang, Y., Wan, S. y Paris, C. (2016). Data61-Csiro systems at the Clpsych 2016 shared task. En Proceedings of the Third Workshop on Computational Linguistics and Clinical Psychology, pp. 128–132, San Diego, CA, USA. Association for Computational Linguistics.
Kornfield, R., Sarma, P. K., Shah, D. V., Mc- Tavish, F., Lyucci, G., Pe-Romashko, K. y Gustafson, D. H. (2018). Detecting recovery problems just in time: Application of automated linguistic analysis and supervised machine learning to an online substance abuse forum. J Med Internet Res, 20(6):e10136.
Kroenke, K., Spitzer, R. L. y Williams, J. B. W. (2001). The phq-9. Journal of General Internal Medicine, 16(9):606–613.
Le, Q. y Mikolov, T. (2014). Distributed representations of sentences and documents. En Proceedings of the 31st International Conference on International Conference on Machine Learning - Volume 32, ICML’14, págs. II–1188–II–1196. JMLR.org.
Liu, R.T., Kleiman, E.M., Nestor, B.A. y Cheek, S. M. (2015). The hopelessness theory of depression: A quarter-century in review. Clinical Psychology: Science and Practice, 22(4):345–365.
Malmasi, S., Zampieri, M. y Dras, M. (2016). Predicting post severity in mental health forums. En Proceedings of the Third Workshop on Computational Linguistics and Clinical Psychology, pp. 133–137. The Association for Computational Linguistics.
Mikal, J., Hurst, S. y Conway, M. (2017). Investigating patient attitudes towards the use of social media data to augment depression diagnosis and treatment: a qualitative study. En Proceedings of the Fourth Workshop on Computational Linguistics and Clinical Psychology — From Linguistic Signal to Clinical Reality, pp. 41–47, Vancouver, BC. Association for Computational Linguistics.
Milne, D. N., Pink, G., Hachey, B. y Calvo, R. A. (2016). Clpsych 2016 shared task: Triaging content in online peer-support forums. En Proceedings of the Third Workshop on Computational Linguistics and Clinical Psychology, pp. 118–127, San Diego, CA, USA. Association for Computational Linguistics.
Mohammad, S. y Turney, P. D. (2013). Crowdsourcing a word-emotion association lexicon. Computational Intelligence, 29:436–465.
Naslund, J. A., Grye, S. W., Aschbrenner, K. A. y Elwyn, G. (2014). Naturally occurring peer support through social media: The experiences of individuals with severe mental illness using Youtube. PLoS One, 9(10).
O’Dea, B., Larsen, M. E., Batterham, P. J., Calear, A. L. y Christensen, H. (2017). A linguistic analysis of suicide-related twitter posts. Crisis, 38(5):319–329. PMID: 28228065.
O’Dea, B., Wan, S., Batterham, P.J., Calear, A.L., Paris, C. y Christensen, H. (2015). Detecting suicidality on twitter. Internet Interventions, 2(2):183–188.
Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Prettenhofer, P., Weiss, R., Dubourg, V., Vyerplas, J., Passos, A., Cournapeau, D., Brucher, M., Perrot, M. y Duchesnay, E. (2011). Scikit-learn: Machine learning in Python. Journal of Machine Learning Research, 12:2825–2830.
Pink, G., Radford, W. y Hachey, B. (2016). Classification of mental health forum posts. En Proceedings of the 3rd Workshop on Computational Linguistics y Clinical Psychology: From Linguistic Signal to Clinical Reality, CLPsych@NAACL-HLT 2016, June 16, 2016, San Diego, California, USA, pp. 180–182.
Schwartza, H.A., Sap, M., Kern, M.L., Eichstaedt, J. C., Kapelner, A., Agrawal, M., Blanco, E., Dziurzynski, L., Park, G., Stillwell, D., Kosinski, M., Seligman, M. E. y Ungar, L. H. (2016). Predicting individual well-being through the language of social media, pp. 516–527.
Shickel, B., Heesacker, M., Benton, S., Ebadi, A., Nickerson, P. y Rashidi, P. (2016). Self-reflective sentiment analysis. En Proceedings of the Third Workshop on Computational Linguistics y Clinical Psychology, págs. 23–32. Association for Computational Linguistics.
Smithson, J., Sharkey, S., Hewis, E., Jones, R., Emmens, T., Ford, T. y Owens, C. (2011). Problem presentation and responses on an online forum for young people who self-harm. Discourse Studies, 13(4):487–501.
Spärck Jones, K. (1972). "A Statistical Interpretation of Term Specificity and Its Application in Retrieval". Journal of Documentation. 28: 11–21.
Staiano, J. y Guerini, M. (2014). Depeche mood: a lexicon for emotion analysis from crowd annotated news. En Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), págs. 427–433, Baltimore, Maryly. Association for Computational Lin- guistics.
Tausczik, Y. R. y Pennebaker, J. W. (2010). The psychological meaning of words: Liwc y computerized text analysis methods. Journal of Language y Social Psychology, 29(1):24–54.
Vapnik, A. Y. L. (1963). Recognition of patterns with help of generalized portraits. volume 24, págs. 774– 780.
van Genderen, M. y Vlake, J. (2018). Virtual healthcare; use of virtual, augmented and mixed reality. Nederlands tijdschrift voor geneeskunde, 162:D3229.
Pennebaker, J., Boyd, R., Jordan, K. y Blackburn, . (2015). The Development and Psychometric Properties of LIWC2015. 10.15781/T29G6Z.
Zirikly, A., Kumar, V. y Resnik, P. (2016). The gw/umd Clpsych 2016 shared task system. En Proceedings of the Third Workshop on Computational Linguistics y Clinical Psychology, págs. 166–170. Association for Computational Linguistics.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2021 Anales de Lingüística
Esta obra está bajo una Licencia Creative Commons Atribución 2.5 Argentina.
Los/as autores/as que publican en esta revista están de acuerdo con los siguientes términos:
1. Los/as autores conservan los derechos de autor y garantizan a la revista el derecho de ser la primera publicación del trabajo bajo una licecncia Creative Commons Atribución 2.5 Argentina (CC BY 2.5 AR) . Por esto pueden compartir el trabajo con la referencia explícita de la publicación original en esta revista.
2. Anales de lingüística permite y anima a los autores a difundir la publicación realizada electrónicamente, a través de su enlace y/o de la versión postprint del archivo descargado de forma independiente.
3. Usted es libre de:
Compartir — copiar y redistribuir el material en cualquier medio o formato
Adaptar — remezclar, transformar y construir a partir del material para cualquier propósito, incluso comercialmente.
