JMIR Publications

ABSTRACT

Background:

For the last decade, doctor-patient contradiction in China has remained prominent, and violent incidents involving medical staff still happen frequently. However, few scholars have conducted research on the types and laws of propagation of the incidents online.

Objective:

By using Self-Organizing Map (SOM), we aimed to predict the microblog propagation law for violent incidents in China that involve medical staff, to classify the types of incidents, and to provide a basis for rapidly and accurately predicting trends in public opinion and developing corresponding measures to improve the relationship between doctors and patients.

Methods:

For the object of study, we selected 60 violent incidents in China involving medical staff with obvious transmission characteristics on the Sina microblog from 2011 to 2018, searched the web data of the microblog with crawler software, recorded the amount of new tweets every two hours, and used the Self-Organizing Map neural network to cluster the number of tweets. A method using polynomial and exponential functions in MATLAB software was applied to predict and analyze the data.

Results:

Trends in the propagation of online public opinion regarding the violent incidents were categorized into eight types: the bluff type, the waterfall type, the zigzag type, the steep type, the abrupt type, the wave type, the steep slope type, and the long slope type. The communications exhibited different characteristics. The prediction effect of four types of incidents (the bluff type, the waterfall type, the zigzag type, and the steep slope type) was good and accorded with actual spreading trends.

Conclusions:

Our study found that the more serious the consequences of a violent incident, such as serious injury or death, the more attention it drew on microblog, the faster was its propagation speed, and the longer its duration. In these cases, the propagation types were mostly steep-slope, long-slope, and zigzag type. What’s more, the more serious the consequences of a violent incident, the higher popularity it exhibited on the microblog. For acts resulting from patients' dissatisfaction with treatments, the popularity within a week was significantly higher than that of incidents caused by non-therapeutic effects.