Analysis of Patterns and Similarities in Service Tickets using Natural Language Processing

In this paper we propose an approach for classifying documents, embedding documents into feature vectors and using these embeddings for finding similarities between them. Our chosen domain for applying this method is the IT-Service Support branch, where the documents we try to analyse are support tickets and the potential of classifying and finding patterns between tickets is huge for optimizing the service process. We aim to tackle the problem with multiple methods of text classification and recognition, and data analysis, followed by comparison and interpretation of the results. Following our previous work in this field, we propose further means of validating our models, so we can describe and visualize several methods of feature extraction and recognition for service tickets that help the business process for Service Support.