Abstract
Recently, there will be more than 4.62 billion social media users worldwide. A large number of users tend to publish personal emotional dynamics or express opinions on social media. These massive user data provide data support for the development of mental illness detection research and have achieved good results. However, it is difficult for current mental illness detection models to accurately identify key emotional features from a large number of posts issued by users to detect problem users. In view of the fact that the existing models cannot more accurately extract the words with high emotional contribution in the content of user posts, this paper proposes two hierarchical user post feature representation models, named Single-Gated LeakReLU-CNN (SGL-CNN) and Multi-Gated LeakyReLU-CNN (MGL-CNN). We leverage these 2 models to identify users with mental illness in online forums. For all posts published by each user within a certain time span, the model proposed in this paper can identify key emotional features in them and filter out other unimportant information as much as possible. In addition, the addition of gating units in this paper can significantly improve the performance of emotion detection tasks. The experimental results based on the task of RSDD dataset prove that the performance of the model proposed in this paper is superior to that of the existing methods.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.