Study of Feature Extract on Microblog User Occupation Classification

摘要

In microblog services such as Sina Microblog, users may get overwhelmed by the raw data from every profession and trade. In this paper, we propose a classification method focus on user's occupation. It's of great use in user information filtering and targeting advertising. As short texts like tweets do not provide sufficient word occurrences, classification methods that use traditional approaches have limitations. To address this problem, we propose to use a small set of domain-specific features extracted from the text, user behavior and social network. The proposed approach effectively classify user to a predefined set of generic classes such as sports, entertainment, IT and house property.