Convolutional Neural Network with Word Embedding Based Approach for Resume Classification

Document Classification is a very prominent area, it is applicable for adiversity of novel applications. ln this study, we focussed on classifying resumes to different classes. The proposed approach is for classifying resumes using Convolutional Neural Network with Glove-Word Embedding. We have segmented resumes into various levels and a hierarchy of classification levels is created. For each level, the CNN with word embedding model is used for classification. The output of each classifier is later combined to define the overall hierarchy of the resume category. Results are evaluated using the performance measures such as precision, recall, and f-score. The results obtained are promising and the proposed system is helpful in the recruitment and selection process of candidates.