Research On Knowledge Asymmetry Of Online Health Community Users Based On Text Mining

Information exchange is the most basic activity of human society,and it is an important guarantee for realizing the value of information.Inevitably,information exchange obstacles such as insufficient information representation or difficulty in understanding by the other party may occur.For example,people mainly use the online medical community to obtain relevant health information,but due to the knowledge asymmetry in terms of professional knowledge and thinking mode,when the online health platform conducts medical consultation,the patient and the doctor have communication problems.At present,the research on communication barriers between doctors and patients is mainly through qualitative research methods such as interviews or questionnaires,and the main factor leading to communication barriers—knowledge asymmetry,which mainly focuses on knowledge producers and knowledge sharing.Lacking the quantitative study of the characteristics of knowledge asymmetry between communicators.Aiming at this situation,and due to the representation of knowledge asymmetry in dialogue,this paper proposes a knowledge asymmetry framework of online health community users based on text mining,which can analyze the knowledge asymmetry behavior of online health community users.On the basis of preprocessing the text set,the vocabulary richness of online community users is analyzed from three aspects:medical vocabulary density,medical vocabulary diversity and medical vocabulary complexity.The LDA topic model was used to select the feature words for doctors and patients in the online health community,and then the selected keywords were analyzed and semantically analyzed using word2 vec and semantic dependence analysis.In order to verify the validity of the framework,this paper selects the online consultation data of Dr.Chun Yu,one of the largest online healthl communities in China,as the research object.Experimental shows that there is a big difference in vocabulary richness between doctors and patients in the online medical community.The medical vocabulary density and vocabulary complexity of doctors are significantly higher than those of patients.And the medical vocabulary diversity of patients is higher than that of doctors,which may be caused by repeated patient use,inaccurate patient use,and uneven patient and patient numbers.In terms of the expression of keywords,there is a big difference between doctors and patients in the online medical community.In general,patients are more diversified.The semantic differences of co-occurring keywords mainly reflected in the number and types of semantic dependencies.From the results,doctors will be significantly higher than the patient's semantic dependence,which means that doctors will have more semantic knowledge than patients.The semantic asymmetry between the two revealed from the semantic level.Therefore,the knowledge asymmetry framework of online health community users based on text mining in this study can well find the knowledge asymmetry performance of doctors and patients in online healthl communities.