Call Log Data Research Articles

Mobile/Telephone Contacts and Calls In Forensics Analysis

When tackling and preventing crime, the analysis of mobile or tele phone data, particularly contacts and calls among crime actors plays a significant role in both civil and criminal cases. Forensic analyst and investigators are able to reconstruct illegal and suspicious activities between specific individuals on the basis of the relationships connecting those individuals. This paper discusses mobile / tele phone contacts and calls in forensic analysis. By analysing the contacts and call log data among individuals related to a criminal activity, forensic analysts and investigators get a proper perspective about a particular criminal network. It is worth mentioning that not all mobile phones are smartphones. But they all have the same ability to store the names and phone numbers as well as call logs. When dealing with a digital device such as a mobile phone, the method used to extract data from it must have little impact on the memory for the evidence to be admissible in court. As such, the methods used to acquire data from a mobile phone will play an important part in an investigation which requires evidence to be extracted from a mobile phone. The investigator must be sure that the information acquired actually reflects that which is stored in the phone, and that the procedures used do not adversely affect the integrity of the information, or any other data stored in the device (McCarthy, 2005). Mobile or tele phone contacts and call data is important to law enforcement in tracking illegal activities and providing evidence for dismissals or acquittals. Keywords: Mobile, Telephone, Calls, Threats, Forensic Analysis, Cyber Security, BOOK Chapter ǀ Research Nexus in IT, Law, Cyber Security & Forensics. Open Access. Distributed Free Citation: Samuel Opoku Daniels (2022): Mobile/Telephone Contacts and Calls In Forensics Analysis Book Chapter Series on Research Nexus in IT, Law, Cyber Security & Forensics. Pp 315-320 www.isteams.net/ITlawbookchapter2022. dx.doi.org/10.22624/AIMS/CRP-BK3-P50

Leveraging unstructured call log data for customer churn prediction

Customer retention is important in the financial services industry. Machine learning has been incorporated into customer data analytics to predict client churn risks. Despite its success, existing approaches primarily use only structured data, e.g., demographics and account history. Data mining with unstructured data, e.g., customer interaction, can reveal more insights, which has not been adequately leveraged. In this research, we propose a customer churn prediction model utilizing the unstructured data, which is the spoken contents in phone communication. We collected a large-scale call center dataset with two million calls from more than two hundred thousand customers and conducted extensive experiments. The results show that our model can accurately predict the client churn risks and generate meaningful insights using interpretable machine learning with personality traits and customer segments. We discuss how these insights can help managers develop retention strategies customized for different customer segments.

Improving access to appointments at Laurie Pike Health Centre.

Rising demand makes it increasingly difficult for patients to access appointments. Laurie Pike Health Centre (LPHC) operates a predominantly same-day booking policy in order to manage appointment requests from its 18 000 patients. We sought to quantify the number of requests, in order to estimate the unmet demand. 1) To estimate the met and unmet demand for same-day appointments; 2) To assess how capacity for same-day appointments compares to demand; 3) To analyse how well LPHC is utilising its available appointment slots. We created a data collection tool to count the total number of patient requests by type. We grouped types into four categories: 1) medical appointment requests; 2) sick notes and results requests; 3) other appointment requests (such as healthcare assistant, nurse); and 4) admin/other. Category-specific percentages were applied to call log data to estimate the number of appointment requests per category. Capacity was measured by counting the total number of same-day GP/advanced nurse practitioner (ANP) appointment slots. Consultation records for GP/ANP appointments were analysed to assess the appropriateness of the booking. Estimated average demand for same-day GP/ANP appointments was 222 per day. Average same-day capacity was 112 slots. After introducing pharmacist and video consultations, average capacity increased to 194 slots per day, a shortfall of 28 appointments. Consultation records indicated that 41% of GP/ANP appointments could have been seen by other practitioners; for example, musculoskeletal practitioners (14%). GP/ANP appointments alone cannot meet patient demand but a diversified workforce might. Alongside this, efforts to improve care navigation may free up to 41% of GP/ANP appointment slots.

Why do people call crisis helplines? Identifying taxonomies of presenting reasons and discovering associations between these reasons.

The objective of this study is to identify the most common reasons for contacting a crisis helpline through analysing a large call log data set. Two taxonomies were identified within the call log data from a Northern Ireland telephone crisis helpline (Lifeline), categorising the cited reason for each call. One taxonomy categorised the reasons at a fine granular level; the other taxonomy used the relatively coarser International Classification of Diseases-10. Exploratory data analytic techniques were applied to discover insights into why individuals contact crisis helplines. Risk ratings of calls were also compared to assess the associations between presenting issue and of risk of suicide as assessed. Reasons for contacting the service were assessed across geolocations. Association rule mining was used to identify associations between the presenting reasons for client's calls. Results demonstrate that both taxonomies show that calls with reasons relating to suicide are the most common reasons for contacting Lifeline and were a prominent feature of the discovered association rules. There were significant differences between reasons in both taxonomies concerning risk ratings. Reasons for calling helplines that are associated with higher risk ratings include those calling with a personality disorder, mental disorders, delusional disorders and drugs (legal). In conclusion, employing two differing taxonomy approaches to analyse call log data reveals the prevalence of main presenting reasons for contacting a crisis helpline. The association rule mining using each taxonomy provided insights into the associations between presenting reasons. Practical and research applications are discussed.

Patients' and Doctors' Perceptions of a Mobile Phone-Based Consultation Service for Maternal, Neonatal, and Infant Health Care in Bangladesh: A Mixed-Methods Study.

BackgroundA mobile-based consultation service, or telehealth, can be used for remote consultations with health care professionals for screening, self-care management, and referral. In rural Bangladesh, where there is high demand for scarce male and even scarcer female doctors, remote consultations may help women seeking maternal and child health care. Aponjon is a mHealth service in Bangladesh that provides weekly voice or text messages to pregnant women, new mothers, and family members on various aspects of maternal, neonatal, and infant health. Subscribers can also access a dedicated 24*7 call center to discuss maternal, neonatal, and infant health or emergencies with medically trained doctors. The service provides advice, primary diagnoses, prescriptions, and referrals to subscriber callers.ObjectiveWe investigated the Aponjon service to understand access, acceptability, usability, benefits, and challenges of a mobile phone-based consultation service.MethodsWe conducted call log data analysis for September to November 2015 to understand how many unique subscribers accessed the service, who accessed the service, the geographical distribution of callers, and the purpose of the calls. We also conducted a qualitative exploratory substudy of eight married women and eight married men who were subscribers to and accessed the service during this time to understand their experiences. We interviewed 11 doctors from the same service who provided phone consultations to subscribers.ResultsApproximately 3894 unique subscribers accessed the service for single or multiple consultations during the study period; 68.36% (2662/3894) of subscribers were from rural households, and 53.00% (2064/3894) of calls were made by pregnant women or new mothers. Approximately 96.08% (5081/5288) calls were nonurgent, 2.69% (142/5288) semiurgent, and 1.23% (65/5288) urgent. Almost 64.7% (134/207) semiurgent or urgent calls came between 8 PM and 8 AM. Callers found the consultation service trustworthy, cost-effective, and convenient. The doctors dispelled misconceptions and promoted good health care practices, regular health check-ups, and responsible use of medicine. They helped families understand the severity of sicknesses and advised them to seek care at health facilities for semiurgent or urgent conditions. The service lacked a pro-poor policy to support talk times of subscribers from poor households and a proper referral system to help patients find the right care at the right facilities.ConclusionsAlthough a regular messaging service is constrained by a one-way communication system, this service using the same platform, gave subscribers access to an abbreviated “consultation” with medical doctors. The consultations provided subscribers with valued medical advice and support, although they were limited in their population reach and their integration into the wider medical system. Further research is required to understand the impact of advice and referral, cost-effectiveness, and willingness to pay for mHealth consultation services, but this research suggests that these services should be supported or even expanded.

E-governance diffusion: Population level e-service adoption rates and usage patterns

This paper investigates how e-governance diffuses in population. Specifically, the cumulative and peak adoption rates of e-governance, the usage patterns of duration (number of days services were used) and depth (number of services used) of usage were analyzed. The data comprised 2.1 billion rows of anonymized service call log data of the entire Estonian e-governance ecosystem, the X-Road, from 2003 to 2015. The results showed that e-governance diffusion was linear, not sigmoid-shape, as literature suggests. In general, cumulative adoption rate grows faster and peak adoption rate increases as user age decreases, and is higher among women. E-service usage duration does not increase faster than usage depth. Usage depth and duration increased with age, though not linearly, and were higher in women. This is the first study to use the behavioral data logs of the entire population across more than 10 years to study technology diffusion on the example of e-governance. The results complement the contemporary technology adoption and diffusion theories, and this study could be of practical relevance to other nations implementing their own e-services for governance.

I think someone is walking with me: the use of mobile phone for social capital development among women in four refugee communities

Purpose The purpose of this paper is to present a mixed method study of social capital development and use, based on an intervention which provided women from refugee backgrounds with social capital development skills and tools. Design/methodology/approach In total, 111 Afghan, Burmese and Sudanese women living in Melbourne, Australia, received peer-support training and a free unlimited fixed-dial mobile phone for one year. Findings Interview and call log data suggest that the training sessions and mobile phones played important roles in bonding social capital development, resulting in a complex support network among participants. To a lesser extent, there was also evidence of bridging social capital creation. By providing linkages to government institutions through an interpreter service, the mobile phones gave participants easy access to linking social capital, in their heritage language. Originality/value The program supplements existing community resources with mobile phone technology to create social capital rich networks within these disadvantaged communities, and the authors describe the community characteristics that make participants amenable to such an intervention.

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.

BackgroundThis 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.ObjectiveThe 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.MethodsMachine 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.ResultsThe 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.ConclusionsThese 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.

Check and Report Ebola (CARE) Hotline: The User Perspective of an Innovative Tool for Postarrival Monitoring of Ebola in the United States.

BackgroundThe response to the 2014-2016 Ebola epidemic included an unprecedented effort from federal, state, and local public health authorities to monitor the health of travelers entering the United States from countries with Ebola outbreaks. The Check and Report Ebola (CARE) Hotline, a novel approach to monitoring, was designed to enable travelers to report their health status daily to an interactive voice recognition (IVR) system. The system was tested with 70 Centers for Disease Control and Prevention (CDC) federal employees returning from deployments in outbreak countries.ObjectiveThe objective of this study was to describe the development of the CARE Hotline as a tool for postarrival monitoring and examine the usage characteristics and user experience of the tool during a public health emergency.MethodsData were obtained from two sources. First, the CARE Hotline system produced a call log which summarized the usage characteristics of all 70 users’ daily health reports. Second, we surveyed federal employees (n=70) who used the CARE Hotline to engage in monitoring. A total of 21 (21/70, 30%) respondents were included in the survey analytic sample.ResultsWhile the CARE Hotline was used for monitoring, 70 users completed a total of 1313 calls. We found that 94.06% (1235/1313) of calls were successful, and the average call time significantly decreased from the beginning of the monitoring period to the end by 32 seconds (Z score=−6.52, P<.001). CARE Hotline call log data were confirmed by user feedback; survey results indicated that users became more familiar with the system and found the system easier to use, from the beginning to the end of their monitoring period. The majority of the users were highly satisfied (90%, 19/21) with the system, indicating ease of use and convenience as primary reasons, and would recommend it for future monitoring efforts (90%, 19/21).ConclusionsThe CARE Hotline garnered high user satisfaction, required minimal reporting time from users, and was an easily learned tool for monitoring. This phone-based technology can be modified for future public health emergencies.

Évaluation des troubles thymiques par l’étude des données passives : le concept de phénotype digital à l’épreuve de la culture de métier de psychiatre

ObjectivesThe search for objective clinical signs is a constant practitioners’ and researchers’ concern in psychiatry. New technologies (embedded sensors, artificial intelligence) give an easier access to untapped information such as passive data (i.e. that do not require patient intervention). The concept of “digital phenotype” is emerging in psychiatry: a psychomotor alteration translated by accelerometer's modifications contrasting with the usual functioning of the subject, or the graphorrhea of patients presenting a manic episode which is replaced by an increase of SMS sent. Our main objective is to highlight the digital phenotype of mood disorders by means of a selective review of the literature. MethodWe conducted a selective review of the literature by querying the PubMed database until February 2017 with the terms [Computer] [Computerized] [Machine] [Automatic] [Automated] [Heart rate variability] [HRV] [actigraphy] [actimetry] [digital] [motion] [temperature] [Mood] [Bipolar] [Depression] [Depressive]. Eight hundred and forty-nine articles were submitted for evaluation, 37 articles were included. ResultsFor unipolar disorders, smartphones can diagnose depression with excellent accuracy by combining GPS and call log data. Actigraphic measurements showing daytime alteration in basal function while ECG sensors assessing variation in heart rate variability (HRV) and body temperature appear to be useful tools to diagnose a depressive episode. For bipolar disorders, systems which combine several sensors are described: MONARCA, PRIORI, SIMBA and PSYCHE. All these systems combine passive and active data on smartphones. From a synthesis of these data, a digital phenotype of the disorders is proposed based on the accelerometer and the GPS, the ECG, the body temperature, the use of the smartphone and the voice. This digital phenotype thus brings into question certain clinical paradigms in which psychiatrists evolve. ConclusionAll these systems can be used to computerize the clinical characteristics of the various mental states studied, sometimes with greater precision than a clinician could do. Most authors recommend the use of passive data rather than active data in the context of bipolar disorders because automatically generated data reduce biases and limit the feeling of intrusion that self-questionnaires may cause. The impact of these technologies questions the psychiatrist's professional culture, defined as a specific language and a set of common values. We address issues related to these changes. Impact on psychiatrists could be important because their unity seems to be questioned due to technologies that profoundly modify the collect and process of clinical data.

Modelling trip generation using mobile phone data: A latent demographics approach

Traditional approaches to trip generation modelling rely on household travel surveys which are expensive and prone to reporting errors. On the other hand, mobile phone data, where spatio-temporal trajectories of millions of users are passively recorded has recently emerged as a promising input for transport analyses. However, such data has primarily been used for the development of human mobility models, extraction of statistics on human mobility behaviour, and origin-destination matrix estimation as opposed to the development of econometric models of travel demand. This is primarily due to the exclusion of user demographics from mobile phone data made available for research (owing to privacy reasons). In this study, we address this limitation by proposing a hybrid trip generation model framework where demographic groups are treated as latent or unobserved. The proposed model first predicts the demographic group membership probabilities of individuals based on their phone usage characteristics and then uses these probabilities as weights inside a latent class model for trip generation, with different classes representing different socio-demographic groups. The model is calibrated using the call log data of a sub-sample of users with known demographics and trip rates extracted from their GSM mobility data. The performance of the hybrid model is compared with that of a traditional trip generation model which uses observed demographic variables to validate the proposed methodology. This comparative analysis shows that the model fit and the prediction results of the hybrid model are close to those of the traditional model. The research thus serves as a proof-of-concept that the mobile phone data can be successfully used to develop econometric models of transport planning by having additional information for a subset of the users.

Novel Unsupervised SPITters Detection Scheme by Automatically Solving Unbalanced Situation

Spam over Internet telephony (SPIT) is recognized as a new threat for voice communication services such as voice over Internet protocol (VoIP). Due to the privacy reason, it is desired to detect SPITters (SPIT callers) in a VoIP service without training data. Although a clustering-based unsupervised SPITters detection scheme has been proposed, it does not work well when the SPITters account for a small fraction of the entire caller. In this paper, we propose an unsupervised SPITters detection scheme by adding artificial SPITters data to solve the unbalanced situation. The key contribution is to propose a novel way to automatically decide how much artificial data should be added. We show that classification performance is improved by means of computer simulation with real and artificial call log data sets.

Beyond access: barriers to internet health information seeking among the urban poor.

Communication inequalities deepen health disparities even when internet access is achieved. The goal of this study is to understand how a range of barriers may inhibit individuals from low socioeconomic position (SEP) from engaging with online health information even when it is freely available. Detailed data were collected from 118 low-SEP individuals from a randomized controlled trial providing internet access. Measures triangulated the health-seeking experience through internet use tracked in real-time, call log data, and self-reported barriers. Negative binomial regression models were fitted with technology and perceived predictors, and our outcome, health information seeking, and then stratified by medical status. Participants experienced a median of two computer issues (median 6 days) and two internet issues (median 6.5 days). Duration of internet problems was associated with a decrease in the rate of internet health information seeking by a factor of 0.990 (P = .03) for each additional day. Participants with a medical problem who were frustrated in their search for health information had half the rate of health information seeking of those who were not frustrated (incidence rate ratio = 0.395, P = .030). Despite IT support, participants still experienced internet connectivity issues that negatively impacted their health information seeking. Frustration in their search to find information may serve as an additional barrier to those who have medical issues. After initial internet access, a second-level digital divide emerged due to connectivity issues, highlighting the need to understand the complex network of barriers experienced by low-SEP internet users.

Quantifying socio-economic indicators in developing countries from mobile phone communication data: applications to Côte d’Ivoire

The widespread adoption of mobile devices that record the communications, social relations, and movements of billions of individuals in great detail presents unique opportunities for the study of social structures and human dynamics at very large scales. This is particularly the case for developing countries where social and economic data can be hard to obtain and is often too sparse for real-time analytics. Here we leverage mobile call log data from Côte d’Ivoire to analyze the relations between its nation-wide communications network and the socio-economic dynamics of its regional economies. We introduce the CallRank indicator to quantify the relative importance of an area on the basis of call records, and show that a region’s ratio of in- and out-going calls can predict its income level. We detect a communication divide between rich and poor regions of Côte d’Ivoire, which corresponds to existing socio-economic data. Our results demonstrate the potential of mobile communication data to monitor the economic development and social dynamics of low-income developing countries in the absence of extensive econometric and social data. Our work may support efforts to stimulate sustainable economic development and to reduce poverty and inequality.

Using capacity alert calls to reduce overcrowding in a major public hospital.

To investigate the efficacy of capacity alert calls in reducing acute hospital overcrowding through addressing rising occupancy, high patient throughput and increased access block. Retrospective analysis of 24 months of in-patient, emergency department, and capacity alert call log data from a large metropolitan public hospital in Australia. The analysis explored statistical differences in patient flow parameters between capacity alert call days and other days including a control case set of days with statistically similar levels of occupancy. The study identified a significant (P<0.05) reduction in occupancy, patient throughput and access block on capacity alert call days. Capacity alert call days reversed rising occupancy trends, with 6 out of 7 flow parameters reporting significant improvement (P<0.05) over the 48 h following the call. Only 3 of these 7 flow parameters were significantly improved 48 h after control case days, confirming value in the alert mechanism and that the results are not a regression toward the mean phenomenon. CONCLUSIONS Escalation processes that alert and engage the whole hospital in tackling overcrowding can successfully deliver sustained improvements in occupancy, patient throughput and access block. The findings support and validate the use of capacity alert escalation calls to manage overcrowding, but suggest the need to improve the consistency of trigger mechanisms and the efficiency of the processes initiated by the capacity alert call.

The Social Amplifier—Reaction of Human Communities to Emergencies

This paper develops a methodology to aggregate signals in a network regarding some hidden state of the world. We argue that focusing on edges around hubs will under certain circumstances amplify the faint signals disseminating in a network, allowing for more efficient detection of that hidden state. We apply this method to detecting emergencies in mobile phone data, demonstrating that under a broad range of cases and a constraint in how many edges can be observed at a time, focusing on the egocentric networks around key hubs will be more effective than sampling random edges. We support this conclusion analytically, through simulations, and with analysis of a dataset containing the call log data from a major mobile carrier in a European nation.

Mobile Phone Support for Rural Health Workers in Nepal through ‘Celemedicine’

Globally, there is a shortage of health workers in rural areas. Effective health systems depend on having sufficient, accessible health workers with the right skills. In countries like Nepal, highly skilled health workers often prefer to work overseas or in urban centres, and therefore, in the short term, it may be pragmatic to focus on ensuring support and skills development of mid level or paramedical health workers. Information technology has the potential to support these health workers. We describe a pilot intervention undertaken in Gulmi District, whereby all mid level health workers in the district have been provided with a free phone number to call three General Practitioner Doctors (GPs) in the District Hospital. The intervention aims to increase appropriate referral, and increase connectivity between the District centre and peripheral health facilities. We hope that our intervention will provide support to rural health workers, and, if implemented as part of a package of interventions, may increase retention. We present some initial findings from discussions with health workers and analysis of call-log data, and describe our next phase evaluation and possible scale-up.

The Advanced Paramedic Clinical Activity Study (APCAS): an insight into the work of advanced paramedics in the mid-west of Ireland

The Advanced Paramedic (AP) is a relatively recent role in Ireland and refers to a prehospital practitioner with Advanced Life Support (ALS) skills and training. The Advanced Paramedic Clinical Activity Study (APCAS) was initiated to provide an evaluation of the impact of the AP programme on patient care in Ireland. The aim of this study is to provide an insight into the clinical activity of APs over a 6-month period in the mid-west region of Ireland. A prospective study was initiated whereby all ambulance calls dispatched by the regional Ambulance Control Centre were recorded by the attending AP, including calls received via the statutory 999/112 system. Participating APs were asked to complete a separate call log data sheet recording all demographic and clinical information for every call attended during the study period. A total of 17 APs participated and 1,969 ambulance calls were recorded in APCAS. The Mid-Western Regional Hospital, Limerick was the busiest receiving facility. Activity peaked at weekends and was lowest on Tuesdays. Crew response, on-scene times and transport times agree with previous reports. Most common emergencies include medical (12 %), cardiovascular (10%) and altered level of consciousness and seizures (10%). Least common calls include airway and ventilation and environmental emergencies (<1%). This study provides an insight into the work of APs in the mid-west region of Ireland. It would appear that despite the relative recency of the Irish AP programme, the findings of this study are in line with previous international studies.