Research On Evaluation Model And Influencing Mechanism Of User Contribution Content Quality In Online Q&A Communities

The rapid development of the Internet has caused the problem of information overload,which promotes users' demand for precise and personalized information.The online Q&A communities combine online Q&A and social interaction,so that on the one hand,users can obtain answers that meet their needs by asking questions,and on the other hand,they can convert their implicit knowledge into explicit knowledge by answering questions.In addition,users can communicate with other members of the community through interactive behaviors such as comments and likes,which greatly facilitates the exchange and dissemination of knowledge.At the same time,with the increasing knowledge resources in the online Q&A communities,it has hindered users' knowledge search and acquisition.In addition,there are problems with uneven quality of answers and a large number of overwhelmed high-quality answers,which result in users spending a lot of time and effort in searching for answers.Therefore,how to effectively evaluate the quality of the existing answers in the online Q&A communities has become an important issue.In addition,since the knowledge of the online Q&A communities is user-generated content,the continuous development of the communities depends on the active participation and knowledge contribution of users.Therefore,how to promote user knowledge contribution and improve the quality of user contribution content are another concern.Based on these,this article proposes the theoretical indicators of answer quality evaluation from the two perspectives of information quality and source credibility guided by the information adoption theory,and further integrates the BERT text representation model to build an answer quality classifier to achieve the automatic evaluation of answer quality.Experimental results show that the quality evaluation model proposed in this paper has better classification effect and performance.Based on the research of answer quality assessment,this paper uses the binary selection model to further explore the factors that affect the quality of user contribution content based on the motivation theory.We focus on the impact of the financial incentives and incentive mechanisms on the quality of user contribution content,and their interaction with the user intrinsic motivation.Our research illustrates a detailed approach of applying the information adoption theory to the design of a text classification model for answer quality evaluation,which provides theoretical inspiration for the research on the answer quality evaluation,and also provides a practical guide for the online Q&A communities to establish an automated quality evaluation system.In addition,this article innovatively introduces the classification results of answer quality by machine learning algorithms into the empirical research model to explore the impact of user intrinsic motivation and extrinsic financial incentives on the quality of user contribution content and their interaction.It enriches the research on user knowledge contribution behavior in the online Q&A communities,and also provides theoretical guidance and suggestions for the community operation.