Comprehensive Graph And Content Feature Based User Profiling

Nowadays, users post a lot of their ordinary life records to online social sites. Rich social content covers discussion, interaction and communication activities etc. The social data provides insights into users' interest, preference and communication aspects. An interesting problem is how to profile users' occupation,i.e., professional categories. It has great values for users' recommendation and personalized delivery services. However, it is very challenging, compared to gender or age prediction, due to the multiple categories and complex scenarios.This paper takes a new perspective to tackle the occupation prediction. We propose novel methods to transfer the commonly used social network feature and textual content feature into vector space representation. Specifically, we use the embedding method to transfer the social network feature into a low dimensional space. We then propose an integrated framework that combines the graph and content feature for the occupation classification problem. Empirical study on a large real social dataset verifies the effectiveness and usefulness of the proposed approach.