Resumo

BLANDON-ANDRADE, Juan Carlos; CASTANO-TORO, Alejandro; MORALES-RIOS, Alejandro  e  TANGARIFE, Nilton. Complaint Process Management in an Electric Power Company. Comp. y Sist. [online]. 2024, vol.28, n.3, pp.1143-1154.  Epub 21-Jan-2025. ISSN 2007-9737.  https://doi.org/10.13053/cys-28-3-4994.

The complaint process is a mechanism for citizen participation that provides the means to submit petitions, complaints, and claims to companies providing goods or services. These appeals arrive in large quantities, must be answered in the times established by law, and are costly to process manually. In this article, we propose a computational method to process the complaints written in natural language in Spanish arriving at the Pereira Electric Power Company in Colombia and then classify the complaints that belong to the area of energy solutions to respond in a faster and more effective way. Natural Language Processing and Machine Learning techniques are used to classify the text to construct the method. It starts with the reception of documents for prediction, performs a preprocessing phase, texts are vectorized, a Recurrent Neural Network is configured and trained, and finally, the prediction of each text is presented. The results show that the method processes and classifies the complaints corresponding to the area of electric power solutions and achieves an accuracy of 94.35%, a precision of 95%, a recall of 94%, an F-measure of 94.49% and 93.77% according to the ROC curve metric. The system was tested preliminarily and then with a more formal test in a real environment. Compared to the evaluation criteria of other approaches, the method shows promising results. It was developed under a Service Oriented Software Architecture (SOA) which allowed deployment on a web server and which helps the company to process real complaints efficiently.

Palavras-chave : Complaint process; computational methods; electric power company; machine learning; natural language processing.

        · texto em Inglês     · Inglês ( pdf )