摘要
对百度指数、微指数在中国流感监测中的作用进行了比较和分析。相关性分析表明,相对于微指数,基于百度指数的关键词搜索数据与实际的流感流行的相关性更强,与流感的流行区间和峰值时间更相似,而且基于它们建立的回归模型能更准确地预测流感的流行。进一步,整合历史的流感流行数据能大大提高该回归模型的效果。因此,百度指数平台可以作为传统流感监测手段的一种有效补充。
This paper investigated and compared the role of Baidu index and Weibo index in the surveillance of influenza virus in China. Correlation analysis shows that the Baidu index of influenza-related keywords has a stronger correlation with the num- ber of influenza-like illness （ILl） in China than the Weibo index, although the correlation for both indexes is moderate. Be- sides, the epidemic period and peak time for the Baidu index is more similar to those of ILI than Weibo index. Regression a- nalysis further shows that the Baidu index could be used to predict ILI more accurately than Weibo index. Moreover, incorpo- ration of the historical ILl could significantly improve the performance of the regression model based on the Baidu index. Over- all, the Baidu index performs better than the Weibo index. It could be a useful tool for surveillance of influenza virus in Chi- na.
出处
《计算机应用研究》
CSCD
北大核心
2016年第2期392-395,共4页
Application Research of Computers
基金
国家自然科学基金资助项目(31371338)
国家传染病重大专项资助项目(2013ZX10004611-002
2014ZX10004002-001)
湖南大学青年教师成长计划资助项目(531107040720)
湖南大学生物医学超算资助项目(531106011004)
关键词
百度指数
微指数
流感监测
Baidu index
Weibo index
influenza surveillance
