Data analytics of call log data to identify caller behaviour patterns from a mental health and wellbeing helpline

Siobhan O'Neill, RR Bond, A Grigorash, Colette Ramsey, C Armour, Maurice Mulvenna

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

This work presents an analysis of 3.5 million calls made to a mental health and wellbeing helpline. Calls were extracted from a telephony informatics system. Each call was logged with a date, time, duration and a unique identifier allowing for repeat caller analysis. We utilized data mining techniques to reveal new insights into help seeking behaviours. Analysis was carried out using unsupervised machine learning (K-means clustering) to discover the types of callers, and Fourier series was used to ascertain periodicity in calls. Callers can be clustered into 5 or 6 caller groups admitting a meaningful interpretation. Clusters are stable and re-emerge regardless of which year is considered. The volume of calls exhibit strong repetitive intra-day and intra-week patterns. Intra-month repetitions are absent. This work provides new data-driven findings to model the type and behaviour of callers seeking mental health support. It offers insights for computer-mediated and telephony-based helpline management.
LanguageEnglish
JournalHealth Informatics Journal
DOIs
Publication statusPublished - 17 Sep 2018

Fingerprint

Mental Health
Informatics
Data Mining
Periodicity
Fourier Analysis
Cluster Analysis
Unsupervised Machine Learning
Help-Seeking Behavior

Keywords

  • Telephony analysis
  • Machine learning
  • Fourier Series
  • Psychology
  • Healthcare service usage
  • Mental health
  • Wellbeing
  • Mental health and wellbeing helpline
  • Helpline
  • Help seeking behaviour
  • Suicide

Cite this

@article{807fd95291db410480a83649ef8133a4,
title = "Data analytics of call log data to identify caller behaviour patterns from a mental health and wellbeing helpline",
abstract = "This work presents an analysis of 3.5 million calls made to a mental health and wellbeing helpline. Calls were extracted from a telephony informatics system. Each call was logged with a date, time, duration and a unique identifier allowing for repeat caller analysis. We utilized data mining techniques to reveal new insights into help seeking behaviours. Analysis was carried out using unsupervised machine learning (K-means clustering) to discover the types of callers, and Fourier series was used to ascertain periodicity in calls. Callers can be clustered into 5 or 6 caller groups admitting a meaningful interpretation. Clusters are stable and re-emerge regardless of which year is considered. The volume of calls exhibit strong repetitive intra-day and intra-week patterns. Intra-month repetitions are absent. This work provides new data-driven findings to model the type and behaviour of callers seeking mental health support. It offers insights for computer-mediated and telephony-based helpline management.",
keywords = "Telephony analysis, Machine learning, Fourier Series, Psychology, Healthcare service usage, Mental health, Wellbeing, Mental health and wellbeing helpline, Helpline, Help seeking behaviour, Suicide",
author = "Siobhan O'Neill and RR Bond and A Grigorash and Colette Ramsey and C Armour and Maurice Mulvenna",
year = "2018",
month = "9",
day = "17",
doi = "10.1177/1460458218792668",
language = "English",
journal = "Health Informatics Journal",
issn = "1460-4582",

}

TY - JOUR

T1 - Data analytics of call log data to identify caller behaviour patterns from a mental health and wellbeing helpline

AU - O'Neill, Siobhan

AU - Bond, RR

AU - Grigorash, A

AU - Ramsey, Colette

AU - Armour, C

AU - Mulvenna, Maurice

PY - 2018/9/17

Y1 - 2018/9/17

N2 - This work presents an analysis of 3.5 million calls made to a mental health and wellbeing helpline. Calls were extracted from a telephony informatics system. Each call was logged with a date, time, duration and a unique identifier allowing for repeat caller analysis. We utilized data mining techniques to reveal new insights into help seeking behaviours. Analysis was carried out using unsupervised machine learning (K-means clustering) to discover the types of callers, and Fourier series was used to ascertain periodicity in calls. Callers can be clustered into 5 or 6 caller groups admitting a meaningful interpretation. Clusters are stable and re-emerge regardless of which year is considered. The volume of calls exhibit strong repetitive intra-day and intra-week patterns. Intra-month repetitions are absent. This work provides new data-driven findings to model the type and behaviour of callers seeking mental health support. It offers insights for computer-mediated and telephony-based helpline management.

AB - This work presents an analysis of 3.5 million calls made to a mental health and wellbeing helpline. Calls were extracted from a telephony informatics system. Each call was logged with a date, time, duration and a unique identifier allowing for repeat caller analysis. We utilized data mining techniques to reveal new insights into help seeking behaviours. Analysis was carried out using unsupervised machine learning (K-means clustering) to discover the types of callers, and Fourier series was used to ascertain periodicity in calls. Callers can be clustered into 5 or 6 caller groups admitting a meaningful interpretation. Clusters are stable and re-emerge regardless of which year is considered. The volume of calls exhibit strong repetitive intra-day and intra-week patterns. Intra-month repetitions are absent. This work provides new data-driven findings to model the type and behaviour of callers seeking mental health support. It offers insights for computer-mediated and telephony-based helpline management.

KW - Telephony analysis

KW - Machine learning

KW - Fourier Series

KW - Psychology

KW - Healthcare service usage

KW - Mental health

KW - Wellbeing

KW - Mental health and wellbeing helpline

KW - Helpline

KW - Help seeking behaviour

KW - Suicide

U2 - 10.1177/1460458218792668

DO - 10.1177/1460458218792668

M3 - Article

JO - Health Informatics Journal

T2 - Health Informatics Journal

JF - Health Informatics Journal

SN - 1460-4582

ER -