摘要： 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 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。

关键词: 在线评分, 观点动力学, 模型预测, 连续观点, 泊松分布, 实验验证

Abstract: 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-normalgood 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.

Key words: online rating, opinion dynamics, model prediction, continuous opinion, Poisson distribution, experimental verification

中图分类号: 

• TP18