Research On Automobile Users' Innovation Knowledge Identification Based On Social Q&A Community

With the increasing development of information technology,enterprises pay more attention to users' effects in innovation activities driven by the change of innovation patterns.Obtaining the innovative content of users has vital influences on enterprises in many aspects,such as capturing market demand,motivating innovative thought and shortening the development process of new products.In the era of knowledge economy,the social Q&A community has changed the way of sharing knowledge and become an indispensable part in people's life.Owing to users interact spontaneously,the content of social Q&A community can adequately reflect users' intrinsic preferences and demands.This says that it is high-quality information.Compared with traditional investigation to get users' demand,building knowledge network based on social Q&A community and discovering users' innovation knowledge is an efficient and accurate approach.However,current knowledge network models usually ignore some text attributes that can affect the importance of knowledge,like the number of reviews and answers.Therefore,this paper builds a multi-attributes weighted knowledge network based on social Q&A community,and then effectively identifies users' innovation knowledge.Firstly,this paper considers attributes that influence the importance of words,and proposes a multi-attributes weighted knowledge network(MWKN)model for the social Q&A community.Especially,in the process of extracting and weighting knowledge,MWKN adopts a multi-attributes weighted strategy.This strategy improved the traditional TF-IDF algorithm by introducing the tuning function and the part of speech.Besides,it calculated the weight of words based on a linear weighting formula,which fused four attributes of user focus by dealing with numbers of users' answer,attention,browse,and comments.Next,this paper constructs an automobile knowledge network of users' innovation using MKWN,based on the data from “automobile design” topic of ZHIHU.Then,this paper takes the automobile knowledge network as analysis object and discover three parts knowledge,respectively.There are identifying innovation knowledge of active users based on the multi-attributes weight,finding core innovation knowledge by analyzing the network centrality,and discovering hot essential innovation knowledge according to comprehensive analysis.Finally,hot fields are identified through hierarchical clustering of popular knowledge.