Extraction of Useful Information from Crude Job Descriptions

As we know, one of the essential social problems is unemployment. Hence, many job advertising agencies tend to consolidate various job offerings to assist the job seekers. As these job descriptions carry unstructured text, therefore, it makes the process of finding and grouping relevant jobs difficult. Hence, the aim of this paper is to automatically extract information from job descriptions. This involves application of text mining and information extraction approaches. To carry out this study, first various features are extracted and later Gradient Boosting classification algorithm is used to perform information extraction. Fields such as salary, required degree, required experience etc. are being extracted automatically. Results show that various features affect the overall result. This proposed model is currently evaluated with the help of precision, recall, receiver operating characteristics curve, and area under the curve (AUC). Experiments show that boosting classification tends to provide reasonable result with 77% of precision.