Depression Detection via Harvesting Social Media: A Multimodal Dictionary Learning Solution

Our work aims to make timely depression detection via harvesting social media data

Guangyao Shen; Jia Jia; Liqiang Nie; Fuli Feng; Cunjun Zhang; Tianrui Hu; Tat-Seng Chua; Wenwu Zhu

2017

Scholarcy highlights

  • Depression is a leading cause of disability worldwide. Globally, an estimated 350 million people of all ages suffer from depression1
  • Depressed people have various depression symptoms manifested by distinguishing behaviors
  • We have the following observations: 1) Wasserstein Dictionary Learning achieved better performance than Naive Bayesian by 10% which shows that latent and sparse representation are effective in depression detection
  • This paper aims to make timely depression detection via harvesting social media
  • With the benchmark depression and non-depression datasets as well as well-defined discriminative depression-oriented feature groups, we proposed a multimodal depressive dictionary learning method to detect depressed users in Twitter
  • Since online behaviors cannot be ignored in modern life, we expect our findings to provide more perspectives and insights for depression researches in computer science and psychology

Need more features? Save interactive summary cards to your Scholarcy Library.