With the rise of micro-blog and other social networking platforms,the phenomenon of the public participating in online life,obtaining information and communicating with each other is more widespread.Analysis of users influence in social network is paid more and more attention.Based on a large scale dataset provided by Sina,this paper used the effect from user's micro-blog to measure user influence.In order to predict user influence,this paper extracted features from user behavior and blog content,made regression analysis and used the method of the multi-view stacking ensemble.The experimental results indicate that this method can predict the change of user influence.With the increase of the features and using the multi-view stacking ensemble,the prediction accuracy is improved.

MOOC架构下的学习具有自组织和自适应的特点，学习者难以像传统课堂学习一样具有较高的持续性，课程学习退出率居高不下。本文基于对MOOC学习活动模型的分析，针对教师、学习者、MOOC平台三大主体提出了5类学习促进策略：资源策略、社交策略、情感策略、服务策略和机制策略，有助于增强学习者的教学体验，保持学习的黏度，提高MOOC课程学习的完成率。