Public concerns and attitudes towards autism on Chinese social media based on K-means algorithm

Abstract

To investigate the hot topics and attitudes of autism in the larger community. In this study, we analyzed and summarized experimental texts from the social media platform Zhihu using the TF-IDF algorithm and K-means clustering approach. Based on the analysis of the 1,740,826-word experimental text, we found that the popularity of autism has steadily risen over recent years. Sufferers and their parents primarily discuss autism. The K-means clustering algorithm revealed that the most popular topics are divided into four categories: self-experience of individuals with autism, external views of individuals with autism, caring and stressful behaviors of caregivers, and information about autism. This study concluded that people with autism face more incredible negative emotions, external cognitive evaluations of the autistic group reflect stereotypes, the caregiver’s family suffers high financial and psychological stress, and disorders caused by disease in autistic individuals.

Application of unsupervised clustering model based on graph embedding in water environment

“…Common neural network methods include GCN 21 , GraphSAGE 22 , GAT 23 , etc. Community detection is to use a Euclidean space clustering method, such as k-means 24 , on the data obtained after graph embedding to identify the clusters of the graph 25 , 26 .…”