开放式知识协同平台中的“回音室效应”研究——以Bilibili“新能源汽车”视频评论为例

Research on“Echo Chamber Effect”in Open Knowledge Collaboration Platform:A Case Study of Bilibili’s“New Energy Vehicle”Video Review

[目的/意义]为提高知识协同质量,针对开放式平台的知识协同过程,分析“回音室效应”的成因及其影响因素,以帮助企业更有效地利用协同数据。[方法/过程]从观点动力学的视角出发,首先考虑知识水平、消极情绪等因素,建立个体决策模型;然后基于马尔可夫链建立群体观点演化模型,用以分析任意网络结构和规模的群体观点演化过程;最后利用群体观点异质性指标,检验是否存在“回音室效应”,并探究各因素与异质性的关系。[结果/结论]仿真和实证分析结果验证了模型的有效性,表明初始评论情绪消极程度和群体知识水平与异质性分别呈正相关和负相关,群体认同比例越接近均值异质性越高,并证实了知识协同中“回音室效应”的存在。

[Purpose/significance]In order to improve the quality of knowledge collaboration,we analyse the causes of the“echo chamber effect”and its influencing factors for the knowledge collaboration process on open platforms,so as to help enterprises make more effective use of collaborative data.[Method/process]From the perspective of viewpoint dynamics,an individual decision-making model is established by considering factors such as knowledge level and negative emotions.Then a group viewpoint evolution model is established based on Markov chain,which is used to analyse the group viewpoint evolution process with arbitrary network structure and size.Finally,the heterogeneity index of group opinions is used to test whether there is an“echo chamber effect”and to explore the relationship between various factors and heterogeneity.[Result/conclusion]The results of simulation and empirical analyses prove the validity of the model.It is shown that the negative degree of initial comments and the level of group knowledge are positively and negatively correlated with heterogeneity,and the closer the proportion of group identity is to the mean value,the higher the heterogeneity is.It also confirms the existence of“echo chamber effect”in knowledge collaboration.