| RUIZ CAMILLE MARIE | M, 2回目発表 | ソーシャル・コンピューティング | 松本 裕治, 中村 哲, 荒牧 英治, 田中 宏季 |
|
title: Melancholic Rambling on Twitter: The Effect of Time Window Size and Coherence on Estimating Depression
abstract: Depression is a serious and prevalent mental illness, affecting 300 million people worldwide. One symptom of depression is rumination, wherein a person thinks about a thought repetively. Social media sites, such as Twitter, are rich sources of data from which rumination may be detected since these are avenues where people can ramble about their thoughts and feelings. In light of this, this study uses Twitter data to explore whether coherence over a period of time can detect rumination and help in estimating depression. As a first step, we look at tweets over different periods of time by exploring the effects of dividing user data using varying time window sizes when estimating depression using different SVM kernels. The results show that the optimal time window size for each kernel differs. We also found that mental health topics for depressed users and topics on activities for healthy users are used as main clues for classifying users regardless of time window size. language of the presentation: English | |||