Manan Suri
ABSTRACT
One of the most common mental illnesses that affects 5% of adults globally is depression. The advancement of social media has meant that more and more people have gained a platform to voice their thoughts and beliefs. People’s social media interactions and posted content can be used to infer critical characteristics such as depressive tendencies which will allow for timely intervention and help. This paper describes a novel supervised approach to detect depressive tendencies in Twitter users using multimodal frameworks which account for user interaction and online behaviour in addition to the tweet content processed using transformers like BERT. The performance of three multimodal frameworks is described with different methods for combining modalities. The best result is obtained a cross-modality based model which improves the baseline by 12% points.
- Kara Chan and Wei Fang. 2007. Use of the internet and traditional media among young people. Young Consumers: Insight and Ideas for Responsible Marketers 8 (11 2007), 244–256. https://doi.org/10.1108/17473610710838608Google Scholar
Cross Ref
- Munmun De Choudhury, Michael Gamon, Scott Counts, and Eric Horvitz. 2013. Predicting Depression via Social Media. In ICWSM.Google Scholar
- Munmun De Choudhury, Emre Kıcıman, Mark Dredze, Glen A. Coppersmith, and Mrinal Kumar. 2016. Discovering Shifts to Suicidal Ideation from Mental Health Content in Social Media. Proceedings of the 2016 CHI Conference on Human Factors in Computing Systems (2016).Google ScholarDigital Library
- Glen Coppersmith, Mark Dredze, and Craig Harman. 2014. Quantifying Mental Health Signals in Twitter. In Proceedings of the Workshop on Computational Linguistics and Clinical Psychology: From Linguistic Signal to Clinical Reality. Association for Computational Linguistics, 51–60. https://doi.org/10.3115/v1/W14-3207Google ScholarCross Ref
- Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers). Association for Computational Linguistics, 4171–4186. https://doi.org/10.18653/v1/N19-1423Google ScholarCross Ref
- Guglielmo Faggioli, Nicola Ferro, Allan Hanbury, and Martin Potthast (Eds.). 2022. Proceedings of the Working Notes of CLEF 2022 - Conference and Labs of the Evaluation Forum (CLEF). Number 3180 in CEUR Workshop Proceedings. Aachen. http://ceur-ws.org/Vol-3180/Google Scholar
- Bruce Ferwerda and Marko Tkalcic. 2018. You Are What You Post: What the Content of Instagram Pictures Tells About Users’ Personality. In IUI Workshops.Google Scholar
- Sharath Chandra Guntuku, Daniel Preotiuc-Pietro, Johannes C. Eichstaedt, and Lyle H. Ungar. 2019. What Twitter Profile and Posted Images Reveal About Depression and Anxiety. In ICWSM.Google Scholar
- Diederik Kingma and Jimmy Ba. 2014. Adam: A Method for Stochastic Optimization. International Conference on Learning Representations (12 2014).Google Scholar
- Adam M. Kremen. 1996. Depressive Tendencies and Susceptibility to Anxiety: Differential Personality Correlates. Journal of Personality 64, 1 (1996), 209–242. https://doi.org/10.1111/j.1467-6494.1996.tb00820.x arXiv:https://onlinelibrary.wiley.com/doi/pdf/10.1111/j.1467-6494.1996.tb00820.xGoogle ScholarCross Ref
- Kurt Kroenke, Robert L. Spitzer, and Janet B. W. Williams. 2001. The PHQ-9. Journal of General Internal Medicine 16, 9 (Sept. 2001), 606–613. https://doi.org/10.1046/j.1525-1497.2001.016009606.xGoogle ScholarCross Ref
- David N. Milne, Glen Pink, Ben Hachey, and Rafael A. Calvo. 2016. CLPsych 2016 Shared Task: Triaging content in online peer-support forums. In Proceedings of the Third Workshop on Computational Linguistics and Clinical Psychology. Association for Computational Linguistics, San Diego, CA, USA, 118–127. https://doi.org/10.18653/v1/W16-0312Google ScholarCross Ref
- Ricardo F. Muñoz, William R. Beardslee, and Yan Leykin. 2012. Major depression can be prevented.American Psychologist 67, 4 (2012), 285–295. https://doi.org/10.1037/a0027666Google ScholarCross Ref
- David Owen, José Camacho-Collados, and Luis Espinosa Anke. 2020. Towards Preemptive Detection of Depression and Anxiety in Twitter. CoRR abs/2011.05249(2020). arXiv:2011.05249https://arxiv.org/abs/2011.05249Google Scholar
- Gregory J. Park, H. A. Schwartz, Johannes C. Eichstaedt, Margaret L. Kern, Michal Kosinski, David Stillwell, Lyle H. Ungar, and M. Seligman. 2015. Automatic personality assessment through social media language.Journal of personality and social psychology 108 6 (2015), 934–52.Google Scholar
- Harold Alan Pincus, Deborah A. Zarin, and Michael First. 1998. "Clinical Significance" and DSM-IV. Archives of General Psychiatry 55, 12 (12 1998), 1145–1145. https://doi.org/10.1001/archpsyc.55.12.1145 arXiv:https://jamanetwork.com/journals/jamapsychiatry/articlepdf/204490/ylt1298.pdfGoogle ScholarCross Ref
- Andrew G. Reece, Andrew J. Reagan, Katharina Lix, Peter Sheridan Dodds, Christopher M. Danforth, and Ellen J. Langer. 2017. Forecasting the onset and course of mental illness with Twitter data. Scientific Reports 7(2017).Google Scholar
- Ramin Safa, Peyman Bayat, and Leila Moghtader. 2022. Automatic detection of depression symptoms in twitter using multimodal analysis. The Journal of Supercomputing 78 (03 2022). https://doi.org/10.1007/s11227-021-04040-8Google ScholarDigital Library
- Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Lukasz Kaiser, and Illia Polosukhin. 2017. Attention Is All You Need. CoRR abs/1706.03762(2017). arXiv:1706.03762http://arxiv.org/abs/1706.03762Google Scholar
- Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Łukasz Kaiser, and Illia Polosukhin. 2017. Attention is All You Need. In Proceedings of the 31st International Conference on Neural Information Processing Systems (Long Beach, California, USA) (NIPS’17). Curran Associates Inc., 6000–6010.Google ScholarDigital Library
- Ma-Li Wong and Julio Licinio. 2001. Research and treatment approaches to depression. Nature Reviews Neuroscience 2, 5 (01 May 2001), 343–351. https://doi.org/10.1038/35072566Google ScholarCross Ref
- Shweta Yadav, Jainish Chauhan, Joy Prakash Sain, Krishnaprasad Thirunarayan, Amit Sheth, and Jeremiah Schumm. 2020. Identifying Depressive Symptoms from Tweets: Figurative Language Enabled Multitask Learning Framework. CoRR abs/2011.06149(2020). arXiv:2011.06149https://arxiv.org/abs/2011.06149Google Scholar
- Andrew Yates, Arman Cohan, and Nazli Goharian. 2017. Depression and Self-Harm Risk Assessment in Online Forums. CoRR abs/1709.01848(2017). arXiv:1709.01848http://arxiv.org/abs/1709.01848Google Scholar
- Jianlong Zhou, Hamad Zogan, Shuiqiao Yang, Shoaib Jameel, Guandong Xu, and Fang Chen. 2021. Detecting Community Depression Dynamics Due to COVID-19 Pandemic in Australia. IEEE Transactions on Computational Social Systems PP (01 2021), 1–10. https://doi.org/10.1109/TCSS.2020.3047604Google ScholarCross Ref
Index Terms
- I don’t feel so good! Detecting Depressive Tendencies using Transformer-based Multimodal Frameworks
Recommendations
Facebook use and depressive symptomatology
We examined the impact of Facebook use, personality, and sex on depressive symptoms.We found no direct link between Facebook use and depressive symptoms.Facebook use among high neuroticism females predicted lower depressive symptoms. The popularity of ...
Insights from an expressive writing intervention on Facebook to help alleviate depressive symptoms
Depression is one of the most common mental disorders. Studies have shown that various online social network (OSN) activities can be used as a marker for people's moods as well as symptoms of subsyndromal depression, suggesting possibilities for online-...
Detecting Sarcasm in Multimodal Social Platforms
MM '16: Proceedings of the 24th ACM international conference on MultimediaSarcasm is a peculiar form of sentiment expression, where the surface sentiment differs from the implied sentiment. The detection of sarcasm in social media platforms has been applied in the past mainly to textual utterances where lexical indicators (...
Comments