A multi-label text message classification method designed for applications in call/contact centre systems

This paper presents a system for multi-label classification of text data processed in Call/Contact Centre (CC) systems. The solution presented herein constitutes a significant innovation and an advantage in relation to the solutions used so far in CC systems, as the contents can be automatically routed directly to even several agents with different competences (depending on the number of classes recognised in the message). The proposed approach combines a set of vectorisation methods, dimensionality reduction methods, and a classifier based on artificial neural networks. Analyses were performed using data from real databases of a large commercial CC system and data extracted from the publicly available Stackoverflow database to evaluate the effectiveness of the developed classification method. The proposed approach was compared with the existing text data classification methods. The method enables classification of text messages belonging to one or more classes and can be used to automatically route contents to agents with appropriate competences.& COPY; 2023 Elsevier B.V. All rights reserved.

Automated summary

This paper presents a system for multi-label classification of text data in Call/Contact Centre systems. The proposed approach allows automatic routing of contents to agents with different competences, which is an innovation and advantage over existing solutions. It combines vectorization methods, dimensionality reduction methods, and a classifier based on artificial neural networks. The effectiveness of the developed method was evaluated using data from real CC systems and the Stackoverflow database, and compared with other classification methods.