Gong Liang Hu

The Institute for Health Metrics and Evaluation (IHME) has stated that over 1.1 billion people suffered from mental disorders globally in 2016, and the burden of mental disorders has continued to grow with impacts on social development. Despite the implementation of strategies for promotion and prevention in mental health WHO’s Comprehensive Mental Health Action Plan 2013–2020, the difficulty of diagnosis of mental disorders makes the objective “To provide comprehensive, integrated, and responsive mental health and social care services in community-based settings” hard to carry out. This paper presents a mental-disorder-aided diagnosis model (MDAD) to quantify the multipolarity sentiment affect intensity of users’ short texts in social networks in order to analyze the 11-dimensional sentiment distribution. We searched the five mental disorder topics and collected data based on Twitter hashtag. Through sentiment distribution similarity calculations and Stochastic Gradient Descent (SGD), people with a high probability of suffering from mental disorder can be detected in real time. In particular, mental health warnings can be made in time for users with an obvious emotional tendency in their tweets. In the experiments, we make a comprehensive evaluation of MDAD by five common adult mental disorders: depressive disorder, anxiety disorder, obsessive-compulsive disorder (OCD), bipolar disorder, and panic disorder. Our proposed model can effectively diagnose common mental disorders by sentiment multipolarity analysis, providing strong support for the prevention and diagnosis of mental disorders.

As a new education product in the information age, Massive Open Online Courses (MOOCs) command momentous public attention for their unexpected rise and flexible application. However, the striking contrast between the high rate of registration and the low rate of completion has put their development into a bottleneck. In this paper, we present a semantic analysis model (SMA) to track the emotional tendencies of learners in order to analyze the acceptance of the courses based on big data from homework completion, comments, forums and other real-time update information on the MOOC platforms. Through emotional quantification and machine learning calculations, graduation probability can be predicted for different stages of learning in real time. Especially for learners with emotional tendencies, customized instruction could be made in order to improve completion and graduation rates. Furthermore, we classified the learners into four categories according to course participation time series and emotional states. In the experiments, we made a comprehensive evaluation of the students’ overall learning status by kinds of learners and emotional tendencies. Our proposed method can effectively recognize learners’ emotional tendencies by semantic analysis, providing an effective solution for MOOC personalized teaching, which can help achieve education for sustainable development.