Creation of a Callbot Module for Automatic Processing of a Customer Service Calls

Aattouri, Imad; Rida, Mohamed; Mouncif, Hicham

doi:10.1007/978-3-030-76508-8_30

Cited by 2 publications

(1 citation statement)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This paper is a continuation of our previous works [11] and [12] concerning the realization of our AI-based callbot project. In the literature, most of the research papers deal with the chatbot problem.…”

Section: Related Workmentioning

confidence: 67%

Modeling of an artificial intelligence based enterprise callbot with natural language processing and machine learning algorithms

Aattouri¹,

Mouncif

Rida³

2023

IJ-AI

View full text Add to dashboard Cite

<p>The management of customer services by telephone encounters several problems: an uncontrollable flow of calls, complicated resource management, a very high cost of service, and more. Opportunities to improve the quality of service, save time and money triggered the widespread implementation of artificial intelligence (AI) based callbot. This article outlines the straightforward workflow developed to model the architecture of the callbot. Therefore, several algorithms were evaluated and compared based on real knowledge of a call center of an insurance society. The algorithms considered are: k-nearest neighbours (KNN), support vector machine (SVM), random forests (RF), logistic regression (LR), and Na¨ıve Bayes (NB). The comparison criteria are: correct responses, response time, accuracy, Cohen’s kappa and F1 score using n-gram (1.1) and (2.2). The results obtained show that the SVM (accuracy=70.29%) presents the best results on all the comparison criteria. The comparison between the results of the human agents and the callbot shows an improvement in several levels: the cost savings are greater than 80% on all the tests carried out, the holding time decrease to 0 seconds, and the processing time (almost a third or more). The results obtained sufficiently meet the objectives of this project.</p>

show abstract

Section: Related Workmentioning

confidence: 67%