Home // International Journal On Advances in Life Sciences, volume 14, numbers 3 and 4, 2022 // View article

Performance Modeling for Call Centers Providing Online Mental Health Support

Authors:
Tim Rens de Boer
Saskia Mérelle
Sandjai Bhulai
Rob van der Mei

Keywords: call center models; queueing; mental health; helplines; data analytics; forecasting; staffing

Abstract:
Mental health helplines differ from other call centers, such as customer service call centers, in different aspects. Many of the agents handling conversations are volunteers, the conversations can be described as often more complex and/or emotional, and many of the mental health helplines use a triage system. More understanding is needed to improve staffing and/or service of mental health call helplines. Motivated by this, we propose a call center model that includes the specifics of online mental health helplines, including features such as a triage system for chats and the inclusion of service times consisting of warm-up, conversation, wrap-up and cool-down periods. This call center model is then validated using trace-driven simulation based on various months of real-life (anonymous) call and chat data provided by 113 Suicide Prevention. The model is validated by comparing the waiting times found in the data with the waiting times of the simulation. The results show that the model can simulate the waiting-time performance of the helpline accurately. Secondly, we focus on forecasting the number of arriving chats and telephone calls. Our results show that (Seasonal) Autoregressive Integrated Moving Average ((S)ARIMA) models trained on historical data perform better than other models in the case of short-term forecasting (five weeks or less ahead), while using linear regression works best for long-term forecasts (longer than five weeks). We propose a method on how these daily predictions can be quickly altered for hourly predictions, which can then be used together with the understanding of the model to obtain staffing advice.

Pages: 120 to 129

Copyright: Copyright (c) to authors, 2022. Used with permission.

Publication date: December 31, 2022

Published in: journal

ISSN: 1942-2660