CAJ | 학술논문

多数观点动力学研究采用基于Agent的建模和仿真方法，与现实社会现象严重脱节。针对该问题，利用现实社会在线评分的统计数据验证和改进观点动力学模型的解释和预测能力。在评分过程中，个体的观点受到自身初始观点和群体观点的共同影响，产生的最终观点将决定个体是否加入评分群体，如果加入将产生评分行为，进而影响后续个体的观点及行为。据此过程建立一个连续观点动力学模型，对在线评分的人员数量进行预测。使用豆瓣网站的影片在线评分数据进行实验，分析各评分观点变化对在线评分数量的影响，结果表明，该模型能够有效预测在线评分人数；个体的最终观点主要受群体差-中-好评分观点的影响，而与自身初始观点基本无关；泊松参数值偏离最优值越远，预测准确率越低。
다수관점동역학연구채용기우Agent적건모화방진방법，여현실사회현상엄중탈절。침대해문제，이용현실사회재선평분적통계수거험증화개진관점동역학모형적해석화예측능력。재평분과정중，개체적관점수도자신초시관점화군체관점적공동영향，산생적최종관점장결정개체시부가입평분군체，여과가입장산생평분행위，진이영향후속개체적관점급행위。거차과정건립일개련속관점동역학모형，대재선평분적인원수량진행예측。사용두판망참적영편재선평분수거진행실험，분석각평분관점변화대재선평분수량적영향，결과표명，해모형능구유효예측재선평분인수；개체적최종관점주요수군체차-중-호평분관점적영향，이여자신초시관점기본무관；박송삼수치편리최우치월원，예측준학솔월저。
Most studies of opinion dynamics adopt Agent-based modeling and simulation for theoretical research and have serious gap with the real social problems. Aiming at this problem,this paper verifies and improves the interpretation and forecasting capabilities of the model with social statistical data of online rating. On the process of online rating,the individual opinion is influenced by its initial opinion and the group’ s opinions. The final opinion determines whether the individual to join the group and makes a rate or not. The rating of the individual affects the opinions and the behaviors of subsequent individuals. A simple dynamic model with continuous opinion based on this process is introduced to predict the number of personnel in online rating. It carries out experiments with the online rating data of film on the Internet website of Douban and analyses the effects of change of score proportion. Experimental results show that the model can effectively predict the number of online rating;Individual final opinion is mainly affected by the opinions of bad-normal-good in the group and almost has nothing to do with its initial opinion;The larger deviation of the Poisson parameter to optimum value leads to the lower accuracy of prediction.