Analysis Of Participant Behavior In Online Healthcare Communities

With the progress of society and the rapid development of the Internet,many social media platforms have begun to integrate into all aspects of people's lives.Taking the medical field as an example,in the case of serious shortage of medical resources,the online healthcare community formed by the combination of medical and Internet has important practical significance in solving medical problems.However,the online healthcare community still has many problems in restricting participant behavior and implementing management decisions,which affects the healthy development of the online healthcare community to a certain extent.At present,the use of data analysis technology to deeply dig out the behavior rules of participants,and at the same time to discover potential problems in the operation of the online healthcare community and provide corresponding management suggestions,has become a hot spot and focus in the field of online healthcare community.Based on this,this article selects a good doctor online website as a typical representative of the online healthcare community,and uses crawler technology to crawl a large amount of real-time data from the website and dig deep into it.Combined with the multi-dimensional important variables related to participants,through analysis and research on the behaviors of doctors,patients and online healthcare community managers,potential problems leading to uneven community development were found.The main research contents of this article are as follows:First,the research selects participation as the form of doctor participation in the online healthcare community,and uses crawling data to conduct an in-depth analysis of doctor participation.The results of the study found that the top 10% of doctors' participation increased by 92.4% of the total increase in participation,and the Gini coefficient reached 0.935.This shows that only a small number of doctors are willing to actively participate in the activities of the online medical community,and most doctors have not fully utilized the resources of the online healthcare community.Further research found that the top 1% of doctors increased their participation,and 54% of them were from the top 1% of cumulative participation.The results of the study indicate that the Matthew effect can be used to explain the imbalance of doctor participation.At the same time,further research based on the multiple linear regression model found that when the distribution of the number of psychological or material rewards received by doctors is unbalanced,the distribution of the increased amount of participation of doctors will be more unbalanced.Second,this article takes patient visits as a manifestation of patient participation behaviors.Based on the analysis of crawling data,it is found that patient visits are mainly concentrated in the top 10% of doctors,accounting for 78.0% of the total increase in visits.The coefficient is as high as 0.854.This shows that in the online healthcare community,the uneven distribution of patient visits is very serious.Further research found that the top 1% of doctors with increased visits,and 78.2% of the doctors came from the top 1% of doctors with cumulative visits.The results of the study showed a strong Matthew effect,that is,the data in the previous period A small number of doctors who have a clear advantage are more likely to get more visits in the next stage.Studies using multiple linear regression models have found that when the distribution of psychological or material rewards is unbalanced,the distribution of increased patient visits will be more unbalanced.Third,this paper identifies the growth model of the number of patients each doctor consults with the S-shaped curve and summarizes them into a normal model,a damping index model,and a volatility model.The study found that 1.2% of the increase in the number of doctors to be diagnosed is a normal model,13.9% is a damping index model and 84.9% is a volatility model.Further,this article uses a multiple logistic regression model to analyze the influencing factors of the growth model,and finds that the main factors affecting the growth model are the registration time,the increase in thank-you letters,the increase in gifts,and the increase in the number of visits to the doctor's homepage.Based on the comprehensive experimental results,this article provides corresponding management suggestions for the online healthcare community managers.