Frequent callers to telephone helplines: new evidence and a new service model

Tracking and Profiling Repeated Users Over Time in Text-Based Counseling: Longitudinal Observational Study With Hierarchical Clustering

BACKGROUND

Due to their accessibility and anonymity, web-based counseling services are expanding at an unprecedented rate. One of the most prominent challenges such services face is repeated users, who represent a small fraction of total users but consume significant resources by continually returning to the system and reiterating the same narrative and issues. A deeper understanding of repeated users and tailoring interventions may help improve service efficiency and effectiveness. Previous studies on repeated users were mainly on telephone counseling, and the classification of repeated users tended to be arbitrary and failed to capture the heterogeneity in this group of users.

OBJECTIVE

In this study, we aimed to develop a systematic method to profile repeated users and to understand what drives their use of the service. By doing so, we aimed to provide insight and practical implications that can inform the provision of service catering to different types of users and improve service effectiveness.

METHODS

We extracted session data from 29,400 users from a free 24/7 web-based counseling service from 2018 to 2021. To systematically investigate the heterogeneity of repeated users, hierarchical clustering was used to classify the users based on 3 indicators of service use behaviors, including the duration of their user journey, use frequency, and intensity. We then compared the psychological profile of the identified subgroups including their suicide risks and primary concerns to gain insights into the factors driving their patterns of service use.

RESULTS

Three clusters of repeated users with clear psychological profiles were detected: episodic, intermittent, and persistent-intensive users. Generally, compared with one-time users, repeated users showed higher suicide risks and more complicated backgrounds, including more severe presenting issues such as suicide or self-harm, bullying, and addictive behaviors. Higher frequency and intensity of service use were also associated with elevated suicide risk levels and a higher proportion of users citing mental disorders as their primary concerns.

CONCLUSIONS

This study presents a systematic method of identifying and classifying repeated users in web-based counseling services. The proposed bottom-up clustering method identified 3 subgroups of repeated users with distinct service behaviors and psychological profiles. The findings can facilitate frontline personnel in delivering more efficient interventions and the proposed method can also be meaningful to a wider range of services in improving service provision, resource allocation, and service effectiveness.

Predicting recurrent chat contact in a psychological intervention for the youth using natural language processing

Chat-based counseling hotlines emerged as a promising low-threshold intervention for youth mental health. However, despite the resulting availability of large text corpora, little work has investigated Natural Language Processing (NLP) applications within this setting. Therefore, this preregistered approach (OSF: XA4PN) utilizes a sample of approximately 19,000 children and young adults that received a chat consultation from a 24/7 crisis service in Germany. Around 800,000 messages were used to predict whether chatters would contact the service again, as this would allow the provision of or redirection to additional treatment. We trained an XGBoost Classifier on the words of the anonymized conversations, using repeated cross-validation and bayesian optimization for hyperparameter search. The best model was able to achieve an AUROC score of 0.68 (p < 0.01) on the previously unseen 3942 newest consultations. A shapely-based explainability approach revealed that words indicating younger age or female gender and terms related to self-harm and suicidal thoughts were associated with a higher chance of recontacting. We conclude that NLP-based predictions of recurrent contact are a promising path toward personalized care at chat hotlines.

Users' Perspectives on Crisis Helplines in Relation to Professional Mental Health Services

Background: Crisis helplines aim to provide a short-term intervention or guide users to professional mental health services, but many users return to helplines despite having professional mental health contacts. Aims: To contribute knowledge on users' perspectives on the role of crisis helplines in relation to their professional mental health contacts, we aimed to investigate how online helpline users describe such services. Methods: We used thematic analysis of 100 naturally occurring interactions from a Swedish online crisis helpline. Results: The users viewed the helpline as a safe space, a partner, or an alternative to bad professional services. Users oriented to ongoing helpline usage as crucial for their well-being while they described using professional mental health services to be able to stay alive. Limitations: The findings are limited to the nature of the different themes. Conclusion: The view on crisis helplines as a short-term intervention relies on an idealized view on crisis intervention that does not represent users' views. User control is at the core of the appeal of helplines, but it is also a key challenge for organizations and volunteers.

A Distress-Processing Model for Clients in Suicidal Crisis

Background: While crisis intervention frameworks have indicated the importance of clients in suicidal crisis better understanding their distress to decrease suicidality, it is unclear how clients in suicidal crisis process their distress. Aims: To develop (Study 1) and validate (Study 2) a sequential distress-processing model for clients in suicidal crisis. Methods: Applying task analysis, Study 1 consisted of three phases, which resulted in a theoretically and empirically informed model. In Study 2, we examined the distress-processing model's validity using a longitudinal design. In both studies, data were online crisis chats with adults in suicidal crisis. Results: In Study 1, we developed a sequential five-stage distress-processing model: (Stage 1) unengaged with distress, (Stage 2) distress awareness, (Stage 3) distress clarity, (Stage 4) distress insight, and (Stage 5) applying distress insight. In Study 2, the model's validity was supported via evidence that (H1) progression through the processing stages was sequential and (H2) clients with good outcomes had greater progression in their processing than clients with poor outcomes. Limitation: Clients who were suicidal but did not disclose their suicidality were not included. Conclusion: Our findings provide a framework for conceptualizing and operationalizing how clients move through suicidal crises, which can facilitate intervention and research developments.

International guidelines for the prevention of sexual violence: A systematic review and perspective of WHO, UN Women, UNESCO, and UNICEF's publications

BACKGROUND

Sexual violence is a major public health issue worldwide, with a high prevalence and extensive human and financial costs. Implementing prevention programs is complex, requiring not only evidence-based practices and high ethical standards, but also close collaboration with local governments and non-governmental organizations. In order to guide and support all stakeholders necessary to achieve large-scale prevention (e.g., politicians, decision-makers, in-field professionals), it is essential to establish international benchmarks for the prevention of sexual violence.

OBJECTIVE

The main goal of this collaborative study was to conduct a systematic review of the frameworks adopted by WHO, UN Women, UNESCO, and UNICEF to help prevent sexual violence worldwide, according to the PRISMA methodology. A secondary objective was to highlight the levels of prevention and determinants of health targeted by these organizations.

RESULTS

Overall, 1008 references were identified, of which 50 met the inclusion criteria. All international guidelines were limited to primary or tertiary prevention, and they were not specifically dedicated to sexual violence. In addition, each organization had developed idiosyncratic prevention strategies. Common primary prevention determinants of health were still found across organizations, including education, socio-economic inequalities, and life skills training. Tertiary prevention was poorly developed and polarized between victims and perpetrators. Secondary prevention was never addressed, however, despite the effectiveness of approaches such as helplines for people sexually attracted to children.

DISCUSSION

Given these results, an international French-speaking consortium of professional teams, all involved in the secondary prevention of sexual violence, was recently formed with a ratified charter presented here.

Who are frequent chatters? Characterization of frequent users in a 24/7 messenger-based psychological chat counseling service for children and adolescents

Background

Online helplines have shown a high acceptance, feasibility, and usability, especially with young people. Helplines usually aim to provide one-time crisis intervention; however, there are users who frequently use such services, tying a disproportionately large proportion of service capacities. To date, there is no research on the characterization of frequent users of online helplines. Therefore, the aim of the present study is to characterize frequent chatters in a chat-based counseling context.

Methods

This cross-sectional study retrospectively analyzed anonymous data of users who approached the German messenger-based psychological chat counseling service krisenchat between May 2020 and July 2021 (N = 6657), with a focus on frequent users - the "frequent chatters". Frequent chatters were defined as those who received an above average (M + 2 ∗ SD) amount of messages from counselors over a period of one week and had at least 7 days of contact with the service over the entire data collection period. Chi-square-tests and Mann-Whitney-U tests were conducted to identify differences between frequent users and the population of all users.

Results

In total, n = 99 (1.5 %) users met the definition for frequent chatters and accounted for roughly a tenth (9.85 %) of all chats of the service. The mean frequent chatter was 17 years old (M = 17.29, SD = 3.56), female (n = 78, 82.1 %), and approached the service in the late afternoon (M = 5:00 pm, SD = 5:25 h). Compared to the general user population, frequent chatters reported significantly more severe concerns to counselors, of which 81.8 % included psychiatric symptoms, such as suicidality (43.4 %) and non-suicidal self-injury (41.4 %). In addition, frequent chatters were significantly more likely to contact krisenchat alongside the use of other professional help services. Further, frequent chatters wrote significantly longer and more messages during the counseling process and within a session than the general user population of krisenchat. Compared to the general user population, frequent chatters did not differ in their satisfaction with the service.

Conclusion

Frequent users are known from telephone helplines and are also represented in a chat-based context. Compared to the general user population, they are more likely to report serious mental health conditions and half of them currently receive professional help, suggesting a high need for social support. In light of the increasing development of chat-based helplines, there is a need for further research on frequent chatters to develop tailored counseling strategies for their needs and to analyze options for an optimized service provision.

Study registration

DRKS00026671.

The Impact of COVID-19 on the Suicide Prevention Helpline in The Netherlands

Background: Although the number of suicides did not increase in 2020, there are concerns about the mental health consequences of the COVID-19 pandemic. Aims: To present the demand for the Dutch suicide prevention helpline during times of lockdown and to describe the coronavirus-related problems discussed. Methods: An observational and exploratory study analyzing the frequency of helpline requests and registration data (n = 893 conversations). Results: Demand for the helpline did increase, but with no distinctive relation with the lockdown measures. During the first lockdown, approximately a quarter of the analyzed helpline conversations were registered as coronavirus-related by the counselors. Most frequently mentioned conversation topics were the interruption to or changes in professional help, social isolation and loss of structure, and ways to find a distraction from suicidal thoughts/rumination. Limitations: Observational study design prevents causal inferences, and demand for the helpline is impacted by multiple factors. Conclusion: These coronavirus-related problems made help-seekers vulnerable to suicidal thoughts and a reduced desire to live. That many suffered from loneliness is concerning as this contributes to the risk of suicidal ideation. The distress among help-seekers due to the sudden loss of mental health care underscores the importance of maintaining contact with those in care and lowering the threshold for help.

Systematic Review of Research and Interventions With Frequent Callers to Suicide Prevention Helplines and Crisis Centers

Background: Helplines worldwide have frequent callers who may occupy a large proportion of call volume. Therapeutic gain from frequent calling has been questioned. We conducted this review to identify the characteristics of frequent callers and to compile recommendations about how best to help them. Method: Using preferred reporting items for systematic reviews and meta-analyses (PRISMA) standards, we searched for all empirical research in English and French from inception to May, 2020 in PubMed, PsycInfo, and the CRISE library. Results: We identified 738 manuscripts and retained 27 for analyses. Nine provided no definition of frequent callers; nine mixed frequent callers with repeat callers (>1 calls); nine concerned frequent callers (≥8 calls/month). The limited data suggest frequent callers are similar to other callers and often experience mental health problems, loneliness, and suicide risk. From recommendations in all 27 studies, we identified 10 suggestions to better manage and help frequent callers that merit validation. Limitations: The small number of empirical investigations and the diversity of their goals and methodologies limit generalizations. Although recommendations for helping callers may have face validity, empirical data on their effectiveness are scarce. Conclusion: Rather than focusing on reducing call frequency, we should empirically evaluate the benefits of interventions for frequent callers with different calling patterns, characteristics, and reasons for calling.

One for all or all for one? An integrative review of research on frequent callers

Objective

Telephone health services is an increasing and integral part of health care in several countries. Callers who call repeatedly, in the current study "frequent callers" are present in all kinds of healthcare services, often constitute a considerable proportion of the total amount of calls and are complicated to help. The aim was to provide a comprehensive overview of research on frequent callers at a variety of telephone health services.

Methods

An integrative literature review. Literature was searched for the period 2011-2020 in CINAHL Plus, MEDLINE, APA PsycArticles, APA PsycInfo, and PubMed, and resulted in the inclusion of 20 articles.

Results

Studies on frequent callers (FCs) were found in the context of emergency medical services, telephone helplines, primary healthcare, and specialist medicine clinics. Frequent calling was associated with psychiatric comorbidity, and the reasons for calling were often multifaceted.

Conclusion

The strategies suggested for handling calls involved an individual approach, which could be enabled through multidisciplinary work.

Innovation

The main findings indicate a need for a systematic approach and guidelines to enable optimal help for FCs. Cooperation among healthcare instances seems to contribute to a more individual care for FCs.

Acceptability and feasibility of a messenger-based psychological chat counselling service for children and young adults ("krisenchat"): A cross-sectional study

BACKGROUND

Adolescence represents a vulnerable period to experience personal crises or mental health problems. However, many concerns stay unnoticed due to the hesitance of young people to seek help and the unavailability and inaccessibility of appropriate help services. Contemporary interventions have been developed incorporating with target group specific needs and preferred modes of communication. krisenchat (German for "crisis chat") is a German low-threshold chat-based psychosocial crisis counselling service that is available around-the-clock. Despite the growing number of online support services, there is a dearth of research regarding the acceptability, usability, and feasibility.

METHODS

The present cross-sectional study analyzed retrospective anonymous data on sociodemographic variables, utilization behavior, and user satisfaction of all krisenchat users between May 2020 and July 2021. Predictors of user satisfaction were identified using exploratory multiple regression analysis. Subgroup analyses were conducted using chi-square-tests to identify differences in user satisfaction.

RESULTS

Data of N = 6962 users was included in the analysis. More than 50% of those reported not having contacted the professional health care system before. The mean user of krisenchat was 17 years old (M = 16.6, SD = 3.5), female (female: 83.4%, male: 14.7%, diverse: 1.8%), and first approached the service at 4 PM (M = 4:03 PM, SD = 5:44 h). More than 60% of the users contacted the service between 4 PM and 12 AM, 10% even between 12 AM and 8 AM. The most frequent chat topics were concerns regarding psychiatric symptoms (60.1%), psychosocial (34.0%) or emotional distress (30.2%). The majority of the users (64.7%) reported high levels of satisfaction and 88.3% a high likelihood (60% or more) of recommending krisenchat to others. Also, the results indicate that the number of messages and their respective length differed between users and counsellors, with users writing several, but shorter messages and counsellors replying with fewer, but longer messages.

CONCLUSION

The results of the present study imply a high acceptability and feasibility of krisenchat. Overall, there is a high need for a 24/7 messenger-based chat counselling service in crises for children and young adults. Currently, there is no other online service for youth that is available after 7 PM or at weekends, which indicates the great importance of krisenchat and its function to bridge a current gap in the mental health care system. A need for further research emerges e.g., for subgroup differences regarding utilization patterns and also for further insights regarding help-seeking behavior via social media in youth.

STUDY REGISTRATION

DRKS00026671.

Suicidal Ideation Among Children and Young Adults in a 24/7 Messenger-Based Psychological Chat Counseling Service

BACKGROUND

Suicidality in children and young adults is a pervasive problem: approximately 40% of respondents in epidemiological surveys in German schools reported suicidal ideation, while up to 9% reported a suicide attempt in the past. While there is compelling evidence for the effectiveness of telephone-based hotline services, an increasing preference of adolescents for messenger-based counseling services can be observed. Therefore, the present study aims to investigate the utilization behavior and user satisfaction of users contacting a German messenger-based chat counseling service ("krisenchat") regarding suicidal ideation.

METHODS

The present cross-sectional study analyzed retrospective anonymous data on sociodemographic variables, utilization behavior, and user satisfaction of krisenchat users who used the service between May 2020 and July 2021. Chi-square-tests were used to identify associations of sociodemographic characteristics and utilization behavior with suicidal ideation. Mann-Whitney-U-tests were used to compare the user satisfaction and the recommendation-to-others-rate between suicidal and non-suicidal krisenchat-users.

RESULTS

In total, chat data of N = 11,031 users were collected. Of the n = 6,962 users included in the final analysis, n = 1,444 (20.7%) contacted krisenchat because of suicidal ideation. The average user experiencing suicidal ideation was 17 years old, female and currently not receiving other treatment. Further, suicidal ideation was significantly and positively associated with age and non-suicidal self-injury. Regarding utilization patterns, there were significant positive associations between suicidal ideation and counseling session count, mean amount of messages sent, and mean amount of words used per message by the user. User satisfaction was high, with 64.7% (n = 413) of users that answered the feedback survey and experiencing suicidal ideation rating the help they received as at least "good" and a recommendation rate of 89.6% (n = 571). Most importantly, no differences were found between users reporting suicidal ideation and those that do not regarding satisfaction and the probability of recommending the service.

CONCLUSION

Results imply satisfaction with the counseling service among users with suicidal ideation. Nevertheless, there is a need for further research into messenger-based counseling services regarding the prevention of suicidal behavior in children, youths, and young adults. Longitudinal studies are especially needed to assess the effectiveness of messenger-based interventions.

STUDY REGISTRATION

DRKS00026671.

Mental wellbeing in crisis line volunteers: understanding emotional impact of the work, challenges and resources. A qualitative study

Background

: Crisis line volunteers are a valuable addition to formal care. Although there is growing evidence of decreased mental wellbeing of crisis line volunteers, a comprehensive overview of perceived emotional impact from the perspective of volunteers is lacking. Purpose: This study explores the emotional impact, the challenges that crisis line volunteers encounter, and the resources that they use to cope with these challenges.

Method

: A grounded theory approach was used to explore the subjective experiences of the participants. Four focus groups with twentytwo active volunteers and eight interviews with former volunteers were conducted.

Results

: Results provide an overview of emotions that volunteers experience in their work. (e.g., gratification, compassion, frustration, and powerlessness). Challenges are related to the characteristics of callers (e.g., inappropriate behaviour) and topics of the calls (e.g., suicidality). Resources to cope adequately with negative emotions are, among others, a self-compassionate attitude and good training.

Conclusion

: This study highlights the importance of training of volunteers in dealing with specific callers, and gives input for the development of interventions aimed at increasing personal resources, such as awareness of positive emotions and self-compassion. These resources can help to increase the mental wellbeing of crisis line volunteers and reduce turn-over rates.

Telephone nurses' perceived stress, self-efficacy and empathy in their work with frequent callers

Aim

To examine telephone nurses' perceived stress, self‐efficacy and empathy in their work with answering calls from frequent callers.

Design

The study is a quantitative questionnaire survey study with a comparative design.

Methods

Telephone nurses (N = 199) answered a survey containing three instruments: Perceived Stress Scale, General Self‐Efficacy Scale and Jefferson's Scale of Empathy. Correlation analysis, multiple regression analysis and analysis of variance were performed to test the research questions.

Results

Significant negative correlations were found between stress involving calls from FCs and self‐efficacy (r = −.238), and significant negative correlations between stress involving calls from frequent callers and empathy (r = −.185). It was further revealed that telephone nurses who had worked less than 30 years scored higher on Jefferson's Scale of empathy than those who had worked more than 30 years, F(1, 183) = 4.98, η² = 0.027.

How Demanding Is Volunteer Work at a Crisis Line? An Assessment of Work- and Organization-Related Demands and the Relation With Distress and Intention to Leave

Background: Crisis line services, run by volunteers, offer a listening ear 24/7 to people who cannot or do not want to use professional help. Although previous studies have identified various potential stressors crisis line volunteers face, as yet a comprehensive assessment is lacking with regards to the frequency and perceived stressfulness of work- and organization-related demands, and their relationship with distress and a volunteer's intention to leave. Objective: To identify the frequency and impact of particular stressful situations (demands). In addition, to examine the extent to which these demands are associated with volunteers' demographics, distress and intention to leave the crisis line service. Method: In a cross-sectional study among 543 volunteers of a Dutch crisis line service the participants filled out a questionnaire about their experience of a large number of work- and organization-related demands and their perceived stressfulness. To calculate the impact of demands, the occurrence and stressfulness were multiplied. In addition, work-related distress, intention to leave the crisis line service as well as a number of demographics and work-related characteristics were assessed. Results: Work-related demands with the highest impact on volunteers were calls from people with psychiatric problems and suicidal intentions. "Having no time for a break" was the organization-related demand with the highest impact on volunteers. Eighteen percentage of the volunteers scored moderate or high on distress and 4% had the intention to leave the crisis line service within 1 year. Most work- and organization-related demands were positively associated with volunteers' distress and intention to leave the organization. Being older, being male and spending more hours per week volunteering were significantly, positively correlated with work-related demands. The total explained variance for distress was 16% and for intention to leave 13%. Conclusion: Although most crisis line volunteers experienced low impact from work- and organization-related demands, these demands were significantly related to experienced distress and the intention to leave crisis line service. For volunteers with moderate to high distress it can be useful to implement interventions aimed at increasing personal resources to help them deal with the challenges of the work at the crisis line.

Adapting Service Delivery during COVID-19: Experiences of Domestic Violence Practitioners

COVID-19 rapidly altered patterns of domestic and family violence, increasing the complexity of women's needs, and presenting new barriers to service use. This article examines service responses in Australia, exploring practitioners' accounts of adapting service delivery models in the early months of the pandemic. Data from a qualitatively enriched online survey of practitioners (n = 100) show the ways services rapidly shifted to engage with clients via remote, technology-mediated modes, as physical distancing requirements triggered rapid expansion in the use of phone, email, video calls and messaging, and many face-to-face interventions temporarily ceased. Many practitioners and service managers found that remote service delivery improved accessibility and efficiency. Others expressed concerns about their capacity to assess risk without face-to-face contact, and were unsure whether new service modalities would meet the needs of all client groups and reflect best practice. Findings attest to practitioners' mixed experiences during this period of rapid service innovation and change, and underline the importance of monitoring emerging approaches to establish which service adaptations are effective for different groups of people, and to determine good practice for combining remote and face-to-face service options in the longer term.

Engagement With Crisis Text Line Among Subgroups of Users Who Reported Suicidality

OBJECTIVE

Despite the interest in technology-enhanced preventive interventions for suicidality, there is minimal peer-reviewed research on conversations of text message hotlines. In this large-scale study, the authors explored distinct classes of users of the Crisis Text Line who reported suicidality. Classes were based on texters' presenting psychosocial issues and were explored across frequency of hotline use and conversation number.

METHODS

Data included 153,514 conversations from 122,909 individuals collected by the Crisis Text Line (2013-2017). Analyses were restricted to conversations from users who mentioned current or previous suicidality and excluded texters who discussed a third party. The authors used latent class analysis to identify distinct classes of texters on the basis of crisis counselor-assigned issue tags and across subgroups reflecting whether the conversation was the first or last contact with the hotline and frequency of use (one-time, two-time, or ≥3-time texters).

RESULTS

Three classes emerged in all subsamples. The largest class, "lower distress," had the lowest prevalence of all issues. The second largest class, "anxious distress," had the highest prevalence of anxiety or stress and elevated depression. The smallest class, "relational distress," had the highest prevalence of depression and self-harm and higher probability of endorsing relational indicators.

CONCLUSIONS

Psychological and relational issues mostly distinguished the three classes. Despite differing frequency of hotline usage, most texters who reported suicidal ideation and behaviors endorsed similar issues, and these issues did not seem to vary across conversations. Yet there appeared to be distinct subgroups of texters with different presenting issues, which may inform how crisis counselors tailor strategies for both low- and high-volume texters.

Impact of Crisis Line Volunteering on Mental Wellbeing and the Associated Factors: A Systematic Review

Crisis line services, operated by volunteers, have been proven to be effective in decreasing psychological pain and preventing suicidality. Although working at the crisis line may be rewarding, for some the confrontation with highly complex topics (i.e., suicidality, abuse, and loneliness) in combination with inappropriate calls (i.e., sexually abusive calls), may lead to distress or vicarious trauma. The aim of this paper is to systematically review the studies that have examined mental wellbeing of crisis line volunteers and the factors associated with it. Thirteen published empirical studies on the topic were found. These showed that crisis line volunteers are at increased risk of declined mental wellbeing. However, a wide range of operationalizations were used and most studies did not use validated instruments. On the other hand, studies showed that many volunteers experience satisfaction and gratification from their work. This review gives insight into some of the work-related, organization-related, and volunteer-related factors that may be associated with the decrease of mental wellbeing. More high quality, comprehensive, and quantitative research using validated instruments is urgently needed to assess the impact of the work on mental wellbeing and the relative impact of influencing factors.

Caught Between Expectations and the Practice Field

Background: Volunteer crisis line responders are a valuable resource for suicide prevention crisis lines worldwide. Aim: The aim of this study was to gain a deeper understanding of how volunteers operating a diaconal crisis line in Norway experienced challenges and how these challenges were met. Method: A qualitative, explorative study was conducted. A total of 27 volunteers were interviewed through four focus groups. The material was analyzed using systematic text condensation. Results: The greatest challenge to the volunteers was the perception of a gap between their expectations and the practice field. The experience of many volunteers was that the crisis line primarily served a broad ongoing support function for loneliness or mental illness concerns, rather than a suicide prevention crisis intervention function. Limitations: The focus group design may have made the participants more reluctant to share experiences representing alternative perspectives or personally sensitive information. Conclusion: The findings of this study suggest that a uniform response to callers using crisis lines as a source of ongoing support is warranted and should be implemented in volunteer training programs.

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

This work presents an analysis of 3.5 million calls made to a mental health and well-being helpline, seeking to answer the question, what different groups of callers can be characterised by specific usage patterns? 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 transform was used to ascertain periodicity in calls. Callers can be clustered into five or six caller groups that offer a meaningful interpretation. Cluster groups are stable and re-emerge regardless of which year is considered. The volume of calls exhibits 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.

Predicting Caller Type From a Mental Health and Well-Being Helpline: Analysis of Call Log Data

BACKGROUND

This paper presents an analysis of call data records pertaining to a telephone helpline in Ireland among individuals seeking mental health and well-being support and among those who are in a suicidal crisis.

OBJECTIVE

The objective of our study was to examine whether rule sets generated from decision tree classification, trained using features derived from callers' several initial calls, could be used to predict what caller type they would become.

METHODS

Machine learning techniques were applied to the call log data, and five distinct patterns of caller behaviors were revealed, each impacting the helpline capacity in different ways.

RESULTS

The primary findings of this study indicate that a significant model (P<.001) for predicting caller type from call log data obtained from the first 8 calls is possible. This indicates an association between callers' behavior exhibited during initial calls and their behavior over the lifetime of using the service.

CONCLUSIONS

These data-driven findings contribute to advanced workload forecasting for operational management of the telephone-based helpline and inform the literature on helpline caller behavior in general.

Patterns of Signs That Telephone Crisis Support Workers Associate with Suicide Risk in Telephone Crisis Line Callers

Signs of suicide are commonly used in suicide intervention training to assist the identification of those at imminent risk for suicide. Signs of suicide may be particularly important to telephone crisis-line workers (TCWs), who have little background information to identify the presence of suicidality if the caller is unable or unwilling to express suicidal intent. Although signs of suicide are argued to be only meaningful as a pattern, there is a paucity of research that has examined whether TCWs use patterns of signs to decide whether a caller might be suicidal, and whether these are influenced by caller characteristics such as gender. The current study explored both possibilities. Data were collected using an online self-report survey in a Australian sample of 137 TCWs. Exploratory factor analysis uncovered three patterns of suicide signs that TCWs may use to identify if a caller might be at risk for suicide (mood, hopelessness, and anger), which were qualitatively different for male and female callers. These findings suggest that TCWs may recognise specific patterns of signs to identify suicide risk, which appear to be influenced to some extent by the callers’ inferred gender. Implications for the training of telephone crisis workers and others including mental-health and medical professionals, as well as and future research in suicide prevention are discussed.