关键词: 社会网络, 智慧校园, 启发式规则, 多标签判断, 集成学习

Abstract: Abstract: Home-school communication plays an important role in the construction of smart campus. At present there is a lack of a way to measure home-school communication on a smart campus. Aiming at the obvious identity characteristics of chatting in intelligent campus, a new Adaboost.ml algorithm is proposed based on Adaboost.mh. The heuristic rule is added to improve the accuracy of judgment, and the concept of time slice is discarded. Single data as the focus of analysis, reducing the inference time and the error caused by the edge of the time slice, integrated decision-making relationship between the chat users. The experimental results show that the false positive rate and false negative rate are obviously improved compared with the traditional algorithm, and also have good classification results based on the micro - data sets.

Key words: social network, smart campus, heuristic rules, multi label judgment, semble?learning