The invention provides a personality
recognition system and method for
social network users, and belongs to the field of
machine learning and subject
cognition. The
system comprises a
social network crawler module, a
social network user personality analysis module, a social network user
database module and an analysis result response module. The method comprises the following steps: firstly,
crawling network behavior data authorized by a user, and generating an offline
network behavior data set with a personality
label; extracting user behavior characteristics from the offline network behaviordata with the personality tags; Dividing the data into a
training set and a
test set, and finally selecting an optimal model by adopting different
machine learning algorithms; and finally, continuingmodel optimization until a personality analysis model meeting the standard is obtained, and further obtaining the personality
label of the user. According to the method, the on-line behavior of the social network user is analyzed, the strong correlation characteristics are mined, the optimal characteristic combination is selected according to the
swarm intelligence optimization
algorithm, the personality of the social network user is obtained through analysis, and a basis is provided for personalized recommendation and user psychological early warning.