International Journal of Applied Mathematics and Machine LearningAuthor's: Qinfeng Li, Xiaofeng Zhou, Aihua Gu and Zonghua Li
Pages: [43] - [63]
Received Date: January 13, 2016; Revised February 15, 2016
Submitted by: Li Li.
DOI: http://dx.doi.org/10.18642/ijamml_7100121623
In recent years, WeChat App is used widely as a convenient communication tool, however most attention to WeChat is paid on the commercial value, few to the academic research. Moreover, there are very few studies about identifying adolescent character traits from WeChat data. For the above, a method of determining character traits is proposed. We discuss the characteristics of data from status, content and neighbour of account data, and extract features. Then Naive Bayes (NB), Support Vector Machine (SVM), K Nearest Neighbour (KNN), and Particle Swarm Optimization (PSO) algorithms are used to classify them according to their contributions to traits. Experimental results show that the means of classification based on data features can effectively identify character traits.
feature extraction, classification algorithms, dataset character traits.
