Name
Sissi Wang
Major
Data Science
Class
2023
About
| Trend of Depression in Online Mutual Help Group for Major Depressive Disorder by a Two-step NLP Method |
| Trend of Depression in Online Mutual Help Group for Major Depressive Disorder by a Two-step NLP Method |
| Major depressive disorder (MDD) has become a common problem in recent years. Online mutual help groups provide an interactive channel for patients with MDD to communicate, find support, and pursue a sense of belonging. In order to verify the effectiveness of such groups, we introduced a comprehensive two‐step NLP method to quantify the degree of depression and then investigate the trend of depression in an MDD mutual help group on the Chinese social platform Douban. The two‐step method combines a BiLSTM model and the dictionary‐based method, which overcomes the shortcoming of the traditional term‐frequency‐based methods that fail to determine the negative expression or suppression before promotion cases. The results support four main findings: first, replies are more positive compared with posts in the group; second, group members tend to reply to more depressive posts; third, through the within‐group interaction, posters become less depressive as they post more in the group; fourth, whether received any reply in the previous post affects the degree of depression in the next post while the number and content of the reply do not matter. This research result is meaningful for future online MDD treatment. |
昆山杜克大学 苏ICP备16021093号