Research On The Intervention Effect Of Perceived Social Support On User's Exercise Behavior

Achieving universal health is an important strategy of "Healthy China 2030",and exercising is an effective way to promote people's health.With the rapid development of mobile social media,an increasing number of people are closely embedded in an interactive social network,and individual behavior and attitude are affected by many factors in the social network.It is a new topic in the field of health communication whether the digitization and socialization of individual exercise behavior can stimulate health behavior.We Run is a typical platform for the digitization and socialization of individual exercise.Nowadays,more and more users are starting to pay attention to and use We Run for sharing exercise data and doing personal health management.The development of the Internet has made many e-health platforms,such as We Run,become the main way for users to obtain social support.Social support is the product of relying on social networks.This thesis mainly analyzes the relationship between the user's exercise behavior and perceived social support in social networks and explores the factors that affect perceived social support.Based on the research background,this thesis first summarizes the relevant research on exercise participation behavior and e-health,then conducts follow-up research based on the theories of social networks,social support,social comparison,and persuasion technology.In the early stage,a total of 907 users' exercise behaviors and personal characteristics data were collected by questionnaire,and the missing and abnormal data were corrected by BP neural network.Then,the decision tree is used to evaluate the relationship between the perceived social support and exercise behavior under different intervention conditions,and detects the heterogeneous intervention effects for different pre-intervention profiles.In addition,this thesis further discusses the performances of social support features of persuasion technology in the We Run.This thesis uses the C4.5 decision tree model to evaluate the changes in user exercise behavior under intervention conditions with different levels of perceived social support.The results of the study show that the frequency of comparison with the topranked friends has the greatest effect on the users' social support perception;there is a correlation between social support and social comparison,when the user lacks strong competition consciousness,the social support perception is more effective in stimulating their exercise behaviors;in some cases,there is not a perfectly positive correlation between the degree of perceived social support and the number of average daily steps.The thesis indicates that the decision tree model can effectively observe the heterogeneous intervention effect between the user's perceived social support and the daily average number of steps.This thesis expands the research on the intervention effect of users' perceived social support on exercise behavior in social networks.The data-driven approach adopted in this study is conducive to reducing self-selection bias and evaluating intervention effects.Evaluation of intervention effects by decision tree does not require decision makers with much expertise or make parameter assumptions,and the results are more direct and easier to understand.The research results help users to better understand the value and function of ‘step ranking' and peer influence,and help them to better manage their health.At the same time,it also provides some practical suggestions for the operation of the E-Health social service platform: the platform can use a proper ranking mechanism in social networks to motivate the user's exercise behaviors,and design differentiated services according to the user's personal characteristics to encourage different users to do more exercise;improve the participation mechanism of social support,focus on the stimulating role of friends,and thus improve the user participation and attention of the platform.