Forecasting Call and Chat Volumes at Online Helplines for Mental Health

Abstract

Abstract BackgroundEach year, many help seekers in need contact health helplines for mental support. For this, it is crucial that they receive support immediately, and that waiting times are minimal. In order to minimize delay, it is necessary that helplines have adequate staffing levels, especially during peak hours. This has raised the need for means to accurately predict the call and chat volumes ahead of time. Motivated by this, in this paper we analyze real-life data to develop models for accurately forecasting call volumes, for both phone and chat conversations for online mental health support. MethodsThis research was conducted on real call and chat data (properly anonymized) provided by 113 Suicide Prevention [1] (throughout referred to as ‘113’), the online helpline for suicide prevention in the Netherlands. Chat and phone call data was analyzed to obtain a better understanding of the important factors that influence the call arrival process. These factors were then used as input to several Machine Learning (ML) models to forecast the number of arrivals. Next to that, senior counsellors of the helpline completed a web-based questionnaire after each shift to assess their perception of the workload.ResultsThis study has led to a number of remarkable and important insights. First, the most important factors that determine the call volumes for the helpline are the yearly trend and weekly and daily cyclic patterns (cycles), while monthly and yearly cycles were found to be non-significant predictors for the number of phone and chat conversations. Second, media events which were included in this study only have limited - and only short-term - impact on the call volumes. Third, so-called (S)ARIMA models are shown to lead to the most accurate prediction in case of short-term forecasting, while simple linear models work the best for long-term forecasting. Fourth, questionnaires filled in by senior counselors show that the experienced workload is mostly correlated to the number of chat conversations in comparison to phone calls and not to the staffing level. Conclusion(S)ARIMA models can best be used to forecast the number of chats and phone calls on daily basis with a MAPE of less than 10 in short-term forecasting. These models perform better than other models showing that the number of arrivals is dependent on historical data. These forecasts can be used as support for the planning of the number of counselors needed.