Person attributes extraction in profiles based on SVM and pattern

This paper is an exploration to find a way to get the person attributes in profiles. Considering those attributes exists in large volume of unstructured data, and it is very difficult to gain in a short time. So, we use a method combing the pattern and SVM to extract the person attributes. Firstly, we collect many raw profiles in websites by our configurable crawler. Secondly, we use statistic methods to do pre-processing works include lexical analysis and name recognition. Thirdly, we build the patterns, which can use in model to extract the person attributes. Also we generalize those patterns to SVM features. Finally, we use SVM assisted with pattern-based method to predict the person attributes. The results prove the method is effective and the data we extracted is useful in building specific-areas´ expert database and information retrieval.