Phone Metadata Research Articles

Comparing sources of mobility for modelling the epidemic spread of Zika virus in Colombia.

Timely, accurate, and comparative data on human mobility is of paramount importance for epidemic preparedness and response, but generally not available or easily accessible. Mobile phone metadata, typically in the form of Call Detail Records (CDRs), represents a powerful source of information on human movements at an unprecedented scale. In this work, we investigate the potential benefits of harnessing aggregated CDR-derived mobility to predict the 2015-2016 Zika virus (ZIKV) outbreak in Colombia, when compared to other traditional data sources. To simulate the spread of ZIKV at sub-national level in Colombia, we employ a stochastic metapopulation epidemic model for vector-borne diseases. Our model integrates detailed data on the key drivers of ZIKV spread, including the spatial heterogeneity of the mosquito abundance, and the exposure of the population to the virus due to environmental and socio-economic factors. Given the same modelling settings (i.e. initial conditions and epidemiological parameters), we perform in-silico simulations for each mobility network and assess their ability in reproducing the local outbreak as reported by the official surveillance data. We assess the performance of our epidemic modelling approach in capturing the ZIKV outbreak both nationally and sub-nationally. Our model estimates are strongly correlated with the surveillance data at the country level (Pearson's r = 0.92 for the CDR-informed network). Moreover, we found strong performance of the model estimates generated by the CDR-informed mobility networks in reproducing the local outbreak observed at the sub-national level. Compared to the CDR-informed networks, the performance of the other mobility networks is either comparatively similar or substantially lower, with no added value in predicting the local epidemic. This suggests that mobile phone data captures a better picture of human mobility patterns. This work contributes to the ongoing discussion on the value of aggregated mobility estimates from CDRs data that, with appropriate data protection and privacy safeguards, can be used for social impact applications and humanitarian action.

Interaction data are identifiable even across long periods of time

Fine-grained records of people’s interactions, both offline and online, are collected at large scale. These data contain sensitive information about whom we meet, talk to, and when. We demonstrate here how people’s interaction behavior is stable over long periods of time and can be used to identify individuals in anonymous datasets. Our attack learns the profile of an individual using geometric deep learning and triplet loss optimization. In a mobile phone metadata dataset of more than 40k people, it correctly identifies 52% of individuals based on their 2-hop interaction graph. We further show that the profiles learned by our method are stable over time and that 24% of people are still identifiable after 20 weeks. Our results suggest that people with well-balanced interaction graphs are more identifiable. Applying our attack to Bluetooth close-proximity networks, we show that even 1-hop interaction graphs are enough to identify people more than 26% of the time. Our results provide strong evidence that disconnected and even re-pseudonymized interaction data can be linked together making them personal data under the European Union’s General Data Protection Regulation.

Screening for Bipolar Disorder With Passively Collected Mobile Phone Metadata

Research by our group and others have demonstrated the feasibility of using passively collected mobile phone usage data to model mood and cognitive function. Here we investigate the feasibility of such an approach to screen for bipolar disorder.

The case against the constitutional validity of mass surveillance programmes

ABSTRACTIn recent years, we have seen a rise in digital technology. In response to the tempestuous nature of technology and its manifold “threats”, the State has adopted fresh armoury. It has inducted mass surveillance programmes, which collect information on every citizen. In India, these measures were adopted in 2007. India’s bulk phone metadata collection programme, equivalent to the National Security Agency is called the Central Monitoring System. Additionally, India has created the Crime and Criminal Tracking and Network System, a nation-wide reposity of criminal data. This paper delves into a constitutional analysis of the validity of these programmes by identifying the key constitutional concerns and reviewing whether these programmes satisfy the test of proportionality. Finally, this paper critiques the ramifications of these measures on democracy. It argues that these measures stifle the exchange of information in the public sphere and reduce public space for reasoning.

Scoot over Smart Devices: The Invisible Costs of Rental Scooters

In the past year, transportation rental companies, including Bird, Lime, and Spin, have dropped hundreds of thousands of rental scooters across North America. Relying on mobile apps and scooter-mounted GPS units, these devices have access to a wide-variety of consumer data, including location, phone number, phone metadata, and more. Pairing corroborated phone and scooter GPS data with a last-mile transportation business model, scooter companies are able to collect a unique, highly identifying dataset on users. Data collected by these companies can be utilized by internal researchers or sold to advertisers and data brokers. Access to so much consumer data, however, poses serious security risks. ­Although Bird, Lime, and Spin posit electric scooters as environmentally friendly and accessible transportation, they also allow for unethical uses of user data through vaguely-worded terms of service. To promote more equitable transportation practices, this article will explore the implications of dockless scooter geotracking, as well as related infrastructure, privacy, and data security ramifications.

Phones, privacy, and predictions

PurposeMobile phones have become one of the most favored devices to maintain social connections as well as logging digital information about personal lives. The privacy of the metadata being generated in this process has been a topic of intense debate over the last few years, but most of the debate has been focused on stonewalling such data. At the same time, such metadata is already being used to automatically infer a user’s preferences for commercial products, media, or political agencies. The purpose of this paper is to understand the predictive power of phone usage features on individual privacy attitudes.Design/methodology/approachThe present study uses a mixed-method approach, involving analysis of mobile phone metadata, self-reported survey on privacy attitudes and semi-structured interviews. This paper analyzes the interconnections between user’s social and behavioral data as obtained via their phone with their self-reported privacy attitudes and interprets them based on the semi-structured interviews.FindingsThe findings from the study suggest that an analysis of mobile phone metadata reveals vital clues to a person’s privacy attitudes. This study finds that multiple phone signals have significant predictive power on an individual’s privacy attitudes. The results motivate a newer direction of automatically inferring a user’s privacy attitudes by leveraging their phone usage information.Practical implicationsAn ability to automatically infer a user’s privacy attitudes could allow users to utilize their own phone metadata to get automatic recommendations for privacy settings appropriate for them. This study offers information scientists, government agencies and mobile app developers, an understanding of user privacy needs, helping them create apps that take these traits into account.Originality/valueThe primary value of this paper lies in providing a better understanding of the predictive power of phone usage features on individual privacy attitudes.

Automatic assessment of mental health using phone metadata

ABSTRACTAn accurate and timely assessment of mental health of individuals is an important building block toward healthy well‐functioning societies. Traditional methods for assessing mental health and wellbeing are surveys administered by health‐care professionals. Such surveys are labor intensive, costly, and typically intermittent. With the growth in mobile sensing, health informatics, and data science, this work argues a case for using mobile phone meta‐data and data analytics to automatically infer an individual's mental health. Specifically, based on a clinically utilized health measure as ground truth (MHI‐5) and ten‐week phone usage metadata corpus for 45 participants we report that automated machine learning algorithms utilizing phone based features can achieve reasonable accuracy (around 80%) at automatically classifying the level of mental health of an individual. Results could pave way for cheaper, automated, health assessments with timely escalations to mental health professionals and interventions when required.

Modeling social support scores using phone use patterns

ABSTRACTSocial support is a fundamental concept of interactional behavior and has been consistently linked with higher levels of emotional and physical well‐being. Social support has been shown to be an effective coping mechanism in managing stress and depression and to provide positive experiences that directly enhance overall well‐being and quality of life. The measurement and quantification of social support has generated a great deal of interest in the behavioral science community over the past 10 years. The dominant approach for quantifying individual social support remains self‐reported surveys and generator‐methods, which are costly, attention‐consuming, and fraught with biases. Given the important role played by mobile phones in mediating human social lives, this study explores the use of phone metadata (call and SMS logs) to automatically infer an individual's social support. Based on Sherbourne and Stewart's Modified Social Support survey (MSSS) as ground truth and ten‐week phone data collection for 55 participants, we report that multiple call and SMS based social features are intrinsically associated with social support and perform better than DEMOGRAPHY‐BASED models.

Inferring Individual Social Capital Automatically via Phone Logs

Social capital is one of the most fundamental concepts in social computing. Individual social capital is often connected with one's happiness levels, well-being, and propensity to cooperate with others. The dominant approach for quantifying individual social capital remains self-reported surveys and generator-methods, which are costly, attention-consuming, and fraught with biases. Given the important role played by mobile phones in mediating human social lives, this study explores the use of phone metadata (call and SMS logs) to automatically infer an individual's social capital. Based on Williams' Social Capital survey as ground truth and ten-week phone data collection for 55 participants, we report that (1) multiple phone-based social features are intrinsically associated with social capital; and (2) analytics algorithms utilizing phone data can achieve high accuracy at automatically inferring an individual's bridging, bonding, and overall social capital scores. Results pave way for studying social capital and its temporal dynamics at an unprecedented scale.

The Backdoor that Leads to the Trap Door: The Unusual Effects of 18 U.S.C 2703 (D) and Stingrays

“Sometimes I feel like somebody’s watching me!” Today, we’re all being watched, most times incidentally. Take for instance traffic cameras. They’re meant to keep us safe, right? Wrong. Although traffic cameras take photos of license plates, the photos do not prevent the accidents that occur from running red lights. Traffic lights are one new means of governmental surveillance. Although, not as invasive as Stingrays. The license plate of each commuter is captured and the face of every pedestrian who passes the block is recorded and saved in a database run by the local government. The author illustrates how the Fourth Amendment has eroded because of back-door requests that grant use of International Mobile Subscriber Identity devices (Stingrays). The use of Stingrays is at an all-time high. A Stingray operates as a fictitious “cell phone tower” and forces cell phones in about a 200-yard radius to send it private information. If not properly regulated on a state or federal level, illegal searches and seizures of cell-phone data will become a norm. Law-abiding citizens’ cell phone metadata, phone calls, and digital footprints are caught in the cross-fire of seeking out crime. The second part of this note draws parallels between the California ECPA statute and Louisiana’s Stingray statute.

Privacy and metadata: The hidden threat to whistle-blowers in public health systems

Summary A high quality public health system relies as much on a robust, accountable and transparent governance framework as it does on the integrity, professionalism and skill of its practitioners and administrators. Patients have an expectation, grounded in human rights entrenched in international law, to a reasonable quality of care and to not be exposed to exploitation, abuse or unreasonable risks of harm. A well-functioning public health system will deliver therapeutic outcomes accordingly, but must also provide a front-line defence for the public against communicable diseases or pandemics, and should also strive to facilitate medical research and innovation. The modern age of digitized personal health information, facilitated by rapid advances in telecommunications and computing technologies, presents both opportunities and hazards for public health systems. Digital collection of data assists healthcare providers by facilitating instant access to consolidated health records, and provides an abundance of information for epidemiologists and health economists alike. However, such systems have also exposed individuals to significant breaches of privacy, and threaten the viability of the doctor–patient relationship upon which a public health system depends. In Australia, the medical profession and healthcare consumers have voiced concerns regarding the general collection, use and secure storage of personal information, including data and metadata. Both forms of personal information have been the subject of high profile privacy breaches, raising questions about the legal protection of confidences between healthcare providers and patients, and whether surveillance of a physician's actions burdens their fidelity to patients in their care. For example, a data breach of the Red Cross Blood Service exposed the names, gender, addresses, dates of birth and responses to questions about ‘at-risk sexual behaviour’ of over half a million Australian blood donors. Regarding metadata, the tension between individual privacy and regulatory overreach is illustrated by powers previously granted under the Telecommunications (Interception and Access) Act 1979 (Cth) (commonly referred to as Australia's Metadata Retention Laws ) to the Australian Health Practitioner Regulatory Agency to examine the metadata of health practitioners under investigation, thus encompassing communication with all their patients, not simply those pertaining to a given complaint. This tension is also readily evident in the case study presented in this article of the Australian Federal Police's alleged warrantless access to a doctor's phone metadata to determine the identity of a suspected whistle-blower. In this case, an Australian doctor was being investigated on suspicion of having disclosed details without authorization pertaining to circumstances surrounding the death of an Iranian asylum seeker in August 2014 who was being held in an offshore detention centre on Manus Island. Media reports on evidence presented at the coronial inquest into the man's death in late 2016 allege that there were unreasonable delays in transporting the patient to a healthcare facility in Brisbane where he could have received life-saving treatment. While this example did not result in a prosecution, detention centre staff, including healthcare workers, who disclosed information about operations or matters within detention centres without authorization at that time, were potentially subject to a two-year jail term under the Border Force Act 2015 (Cth). As this case study illustrates, misuse of metadata for investigating and prosecuting doctors who act as whistle-blowers within the public health system is not an isolated concern and merits careful consideration. Doctors have an ethical duty to act as whistle-blowers (i.e., grounded in virtue ethics) in a range of situations, such as to report systemic failures, review clinical outcomes of both departments and individuals, or avoid catastrophic events. Indeed, whistle-blowing serves a crucial function to promote transparency of processes in health governance and thereby improve quality of care and patient safety. As such, doctors present a special case for legal protection when they act as whistle-blowers in good faith. Legal disincentives, such as punitive measures that purport to advance the aims of secrecy in government agencies, should be avoided. A failure to do so risks undermining the very foundations of the doctor–patient relationship, with consequent negative implications for patient safety and quality of care in public health systems.

A “Massive and Unprecedented Intrusion”

In May 13, 2013, the Associated Press announced that the United States Department of Justice had secretly subpoenaed phone records from Associated Press phone lines over a two-month period in early 2012. A few days later, on May 17, the Washington Post revealed that the Department of Justice had also been tracking the activities of Fox News’ chief Washington correspondent, James Rosen. These two stories caused large scandals in the United States, and the majority of American journalists denounced the surveillance. As these scandals were still unfolding, yet another government surveillance scandal broke: former National Security Agency contractor Edward Snowden revealed that the federal government had been collecting the cell phone metadata of American citizens for several years. Journalists’ responses to this scandal were more nuanced; editorials expressed a wider spectrum of views about the ethics of government surveillance practices, and more complex opinions about the legitimacy and necessity of government surveillance. Drawing on approaches to journalistic professionalism, this study uses qualitative textual analysis to assess editorials written in response to these three revelations. The analysis suggests that journalists see their speech as something deserving of unique protections, above and beyond those protections afforded to the general public.

Analysis shows that U.S. intelligence agencies see less phone metadata [News

For years, the U.S. National Security Agency amassed metadata from the private phone lines of millions of people in the United States. This included information about whom a person called, when those calls were placed, and how long they lasted. When former NSA contractor Edward Snowden divulged this practice in 2013, his revelations undermined public trust and eventually led to nationwide privacy reforms.

Top stories: Modern human evolution, the problem with ‘three-parent embryos,’ and what your phone metadata say about you

Top stories: Modern human evolution, the problem with ‘three-parent embryos,’ and what your phone metadata say about you

Having a conversation about bulk surveillance

Considering a controversial subject that extends far beyond the collection of phone metadata.

Predicting poverty and wealth from mobile phone metadata.

Accurate and timely estimates of population characteristics are a critical input to social and economic research and policy. In industrialized economies, novel sources of data are enabling new approaches to demographic profiling, but in developing countries, fewer sources of big data exist. We show that an individual's past history of mobile phone use can be used to infer his or her socioeconomic status. Furthermore, we demonstrate that the predicted attributes of millions of individuals can, in turn, accurately reconstruct the distribution of wealth of an entire nation or to infer the asset distribution of microregions composed of just a few households. In resource-constrained environments where censuses and household surveys are rare, this approach creates an option for gathering localized and timely information at a fraction of the cost of traditional methods.

Predicting unmeasurable wealth

Economics In developing countries, collecting data on basic economic quantities, such as wealth and income, is costly, time-consuming, and unreliable. Taking advantage of the ubiquity of mobile phones in Rwanda, Blumenstock et al. mapped mobile phone metadata inputs to individual phone subscriber

Communications interception: UK report seeks legal reform

British spies’ bulk collection of citizens’ phone and internet metadata doesn't breach EU law, a new government report says. However, the document does recommend an overhaul of the complex UK law governing the field.

Protecting Privacy in Signal Processing

While not explicitly stated in the U.S. Constitution, the rights of privacy for many aspects of our lives including religious beliefs, personal possession, and personal information are protected under the Bill of Rights. Nonetheless, news about different forms of privacy invasion has become a daily affair. From the sale of personal information to identity theft, from Google and YouTube surrendering user data to the mining of phone metadata by the National Security Agency, the number of ways that our privacy can be invaded seems to increase at an alarming rate.

Spies, data and research

The revelation by Edward Snowden that the US National Security Agency (NSA) and the UK Government Communications Headquarters (GCHQ) have been gathering the email and mobile phone metadata of millions of European citizens, including politicians, has drawn public attention to the inherent risks of a globally connected information society. The level of public concern and outrage risks triggering a political overreaction that could be detrimental to biomedical research that crucially relies on sharing data and samples, if the balance is tipped too far in favour of strict privacy regulation. The discussion over spying has also drawn attention to the ongoing reform of the EU's legal framework to protect the private data of citizens. The law in the European Union is based on the Data Protection Directive 95/46/EC that was passed in 1995. In 2012, the European Commission presented the first draft of a Data Protection Regulation intended to supersede the former, and the latest amendments were released on October 21, 2013. The advantage of a Regulation is that it is directly applicable in its entirety by all member …