The prevalence of mental illnesses is rapidly increasing, with approximately 20-25% of individuals experiencing these disorders during their lifetime. This rise has been further exacerbated within the Covid-19 pandemic. Depression, anxiety, and substance or alcohol abuse related disorders are among the most frequent mental health conditions affecting individuals. Mental illnesses not only cause significant personal burden but also have substantial economic costs due to sick-leaves and early retirements. The early onset of mental illness, particularly during childhood and adolescence, is critical as it can interfere with essential developmental tasks such as building social relationships, developing of an autonomous personality and academic achievements. Furthermore, it is associated with a high probability of chronification and more severe courses of diseases until adulthood. Unfortunately, despite the increasing prevalence of mental illnesses, several shortcomings due to structural and personal barriers, the supply, uptake, and effectiveness of mental health treatments remain modest, resulting in high numbers of non-responders or relapse.

It is crucial to address this gap between the increasing need for mental health services and the availability of and access to effective treatments – ideally for all, anytime, and anywhere. Therefore, we must explore innovative data mining solutions to improve timeliness, access to, and the effectiveness of mental health treatments. This can involve a collaboration between Artificial Intelligence solutions based on current and next generation data mining and mental health professionals, researchers, policymakers, and other stakeholders to discuss evidence-based practices, emerging technologies, and policy recommendations.

In this light, the workshop will explore data mining for mental disorder, aiming to solicit highest quality contributions with, but not limited to:
   • Data Mining for Mental Disorder systems based on textual, audiovisual, biochemical, electrophysiological, photoelectric, physical data, and their multimodal combination   • Data Mining for prevention and treatment of mild and severe mental disorders    • Foundation Models and their tuning in mental disorders
    • Transfer, active, drifting target, federated, few-shot, and self/semi-supervised learning for mental disorders   • Dependable, explainable, fair, green, and reliable mental disorder modelling    • Cooperative human/AI data mining approaches for mental disorders    • Mobile and ubiquitous data mining for mental disorders
   • Applications in alcohol and further addictions, Alzheimer’s disease, anorexia nervosa, autism, bipolar disorder, dementia, depression, negative emotions, suicidal risk, and beyond   • Datasets and benchmarks for Data Mining in Mental Disorders    • Surveys, systematic overviews, and blue-sky contributions for Data Mining in Mental Disorder

 The impacts of mental illnesses are far-reaching, and we need to work together to find solutions that can make a real difference in the lives of individuals struggling with mental health conditions. Your expertise and perspectives will be invaluable to the success of this workshop. By bringing together a diverse group of experts and stakeholders, we hope to develop actionable solutions that can improve mental health services and resources.
We invite you to join us in this critical discussion and contribute to the development of innovative data mining solutions to address the increasing prevalence of mental disorders.
Dates
 1 August 2023 – Paper submission deadline
 15 September 2023 – Notification of acceptance
1 October 2023 – Camera-ready submission deadline
 4 December 2023 – Workshop held in Shanghai, China @ICDM 2023

Contribute

Submit your paper online: 

https://wi-lab.com/cyberchair/2023/icdm23/scripts/submit.phpsubarea=S12&undisplay_detail=1&wh=/cyberchair/2023/icdm23/scripts/ws_submit.php

Organisers
Björn W. Schuller, Imperial College London, UK;  Johanna Löchner, University of Tübingen, Germany; Kun Qian, Beijing Institute of Technology, China; Zichao Nie, Beihang University, China; Bin Hu, Beijing Institute of Technology, China; Yoshiharu Yamamoto, The University of Tokyo, Japan

Program Committee
Oliver Amft, University of Freiburg, Germany; Katrin Bartl-Pokorny, Medical University of Graz, Austria; Anton Batliner, University of Augsburg, Germany; Harald Baumeister, University of Ulm, Germany; Björn Eskofier, FAU, Germany; Anna Esposito, University of Campania, Italy; Jing Han, University of Cambridge, UK; Haifeng Li,HIT, China; Shrikanth Narayanan, USC, USA; Florian Pokorny, Medical University of Graz, Austria; Matthew Purver, QMUL, UK; Zhao Ren, University of Bremen, Germany; Fabien Ringeval, Université Grenoble Alpes, France; Dongrui Wu, GE, USA;  Zixing Zhang, Hunan University, China; Ziping Zhao, TJNU, China; Jiayu Zhou, Michigan State University, USA