Patty Kostkova

Modeling User Preferences in Recommender Systems: A Classification Framework for Explicit and Implicit User Feedback

Recommender systems are firmly established as a standard technology for assisting users with their choices; however, little attention has been paid to the application of the user model in recommender systems, particularly the variability and noise that are an intrinsic part of human behavior and activity. To enable recommender systems to suggest items that are useful to a particular user, it can be essential to understand the user and his or her interactions with the system. These interactions typically manifest themselves as explicit and implicit user feedback that provides the key indicators for modeling users’ preferences for items and essential information for personalizing recommendations. In this article, we propose a classification framework for the use of explicit and implicit user feedback in recommender systems based on a set of distinct properties that include Cognitive Effort, User Model, Scale of Measurement, and Domain Relevance. We develop a set of comparison criteria for explicit and implicit user feedback to emphasize the key properties. Using our framework, we provide a classification of recommender systems that have addressed questions about user feedback, and we review state-of-the-art techniques to improve such user feedback and thereby improve the performance of the recommender system. Finally, we formulate challenges for future research on improvement of user feedback.

Who Owns the Data? Open Data for Healthcare.

Research on large shared medical datasets and data-driven research are gaining fast momentum and provide major opportunities for improving health systems as well as individual care. Such open data can shed light on the causes of disease and effects of treatment, including adverse reactions side-effects of treatments, while also facilitating analyses tailored to an individual’s characteristics, known as personalized or “stratified medicine.” Developments, such as crowdsourcing, participatory surveillance, and individuals pledging to become “data donors” and the “quantified self” movement (where citizens share data through mobile device-connected technologies), have great potential to contribute to our knowledge of disease, improving diagnostics, and delivery of healthcare and treatment. There is not only a great potential but also major concerns over privacy, confidentiality, and control of data about individuals once it is shared. Issues, such as user trust, data privacy, transparency over the control of data ownership, and the implications of data analytics for personal privacy with potentially intrusive inferences, are becoming increasingly scrutinized at national and international levels. This can be seen in the recent backlash over the proposed implementation of care.data, which enables individuals’ NHS data to be linked, retained, and shared for other uses, such as research and, more controversially, with businesses for commercial exploitation. By way of contrast, through increasing popularity of social media, GPS-enabled mobile apps and tracking/wearable devices, the IT industry and MedTech giants are pursuing new projects without clear public and policy discussion about ownership and responsibility for user-generated data. In the absence of transparent regulation, this paper addresses the opportunities of Big Data in healthcare together with issues of responsibility and accountability. It also aims to pave the way for public policy to support a balanced agenda that safeguards personal information while enabling the use of data to improve public health.

Grand challenges in digital health

Today, everything is affected by the digital revolution – the impact of new technology on improving the health and well-being of individuals, communities, and populations is unprecedented. Recent technological achievements have revolutionized clinical practice, from prevention through diagnosis, monitoring to disease management, and enabled unprecedented public interest and engagement in self-management and well-being. Digital health is defined as the “use of information and communications technologies to improve human health, healthcare services, and wellness for individuals and across populations.” n nDozens of digital health projects have been conducted in Europe alone (1) and with the growth of mobile technology for improving health and well-being (mHealth). There is an unprecedented opportunity to transform the healthcare sector and empower citizens in taking charge of their own health (2). n nHowever, the successful development, integration and implementation of new technology and methods require a radical shift from traditional and single-disciplinary academic and clinical approaches. In order to truly embrace these opportunities and transform healthcare and improve well-being, we need a new approach to science and health research. Only when investigated together, aimed at solving real-world problems, will health and technology be in a position to create results with significant impact on the delivery of clinical and social care and improve the well-being of individuals and populations. n nFirst, recent technological advances enabled by the creation of real-time big data streams, social media, and infectious disease modeling are the focus of public health computer science, aiming to strengthen disease surveillance, early-warning, preparedness, and response through integration of traditional surveillance systems with new big data sources. Second, advances in reliability and accuracy of medical devices and personalized technology, together with booming wearable and tracking technology (MedTech), have rapidly become established as the mainstream enhancing opportunities for personalized care, improving self-management, and bringing the desirable outcome: behavior change. Third, with over 4.55 billion people worldwide using a mobile phone in 2014, mHealth apps and interventions empower users in the developed world and are accelerating unprecedented access to best evidence and healthcare service in the low and middle income settings. Fourth, more than a decade ago, Sir Muir Gray forecasted that “knowledge is the best enemy of disease – the application of what we know already will have a bigger impact on health and disease than any drug or technology likely to be introduced in the next decade” (3). Better use of technology for capturing, understanding, and disseminating knowledge is paramount for fulfilling this vision. The recent research achievements in web science, data mining and analytics, medical ontologies, and recommender systems provide further opportunities for better evidence dissemination, medical advice, and development of personalized persuasive intelligent systems. Fifth, serious games for health- and game-based learning have crossed the rubicon from entertainment technology to education and health interventions, and are getting firmly established as health educational and intervention tools. Finally, in light of the speed of data sharing technologies and the absence of a legal framework, we must engage in policy debates safeguarding individual privacy, regulation usage of data for commercial purposes, while enabling transparent data sharing for research. n nHowever, these challenges are only achievable through truly multi-disciplinary research collaborations.

#swineflu: The Use of Twitter as an Early Warning and Risk Communication Tool in the 2009 Swine Flu Pandemic

The need to improve population monitoring and enhance surveillance of infectious diseases has never been more pressing. Factors such as air travel act as a catalyst in the spread of new and existing viruses. The unprecedented user-generated activity on social networks over the last few years has created real-time streams of personal data that provide an invaluable tool for monitoring and sampling large populations. Epidemic intelligence relies on constant monitoring of online media sources for early warning, detection, and rapid response; however, the real-time information available in social networks provides a new paradigm for the early warning function. The communication of risk in any public health emergency is a complex task for governments and healthcare agencies. This task is made more challenging in the current situation when the public has access to a wide range of online resources, ranging from traditional news channels to information posted on blogs and social networks. Twitter’s strength is its two-way communication nature --- both as an information source but also as a central hub for publishing, disseminating and discovering online media. This study addresses these two challenges by investigating the role of Twitter during the 2009 swine flu pandemic by analysing data collected from the SN, and by Twitter using the opposite way for dissemination information through the network. First, we demonstrate the role of the social network for early warning by detecting an upcoming spike in an epidemic before the official surveillance systems by up to two weeks in the U.K. and up to two to three weeks in the U.S. Second, we illustrate how online resources are propagated through Twitter at the time of the WHO’s declaration of the swine flu “pandemic”. Our findings indicate that Twitter does favour reputable t bogus information can still leak into the network.

Major Infection Events Over 5 Years: How Is Media Coverage Influencing Online Information Needs of Health Care Professionals and the Public?

Background The last decade witnessed turbulent events in public health. Emerging infections, increase of antimicrobial resistance, deliberately released threats and ongoing battles with common illnesses were amplified by the spread of disease through increased international travel. The Internet has dramatically changed the availability of information about outbreaks; however, little research has been done in comparing the online behavior of public and professionals around the same events and the effect of media coverage of outbreaks on information needs. Objective To investigate professional and public online information needs around major infection outbreaks and correlate these with media coverage. Questions include (1) How do health care professionals’ online needs for public health and infection control information differ from those of the public?, (2) Does dramatic media coverage of outbreaks contribute to the information needs among the public?, and (3) How do incidents of diseases and major policy events relate to the information needs of professionals? Methods We used three longitudinal time-based datasets from mid-2006 until end of 2010: (1) a unique record of professional online behavior on UK infection portals: National electronic Library of Infection and National Resource of Infection Control (NeLI/NRIC), (2) equivalent public online information needs (Google Trends), and (3) relevant media coverage (LexisNexis). Analysis of NeLI/NRIC logs identified the highest interest around six major infectious diseases: Clostridium difficile (C difficile)/Methicillin-resistant Staphylococcus aureus (MRSA), tuberculosis, meningitis, norovirus, and influenza. After pre-processing, the datasets were analyzed and triangulated with each other. Results Public information needs were more static, following the actual disease occurrence less than those of professionals, whose needs increase with public health events (eg, MRSA/C difficile) and the release of major national policies or important documents. Media coverage of events resulted in major public interest (eg, the 2007/2008 UK outbreak of C difficile/MRSA). An exception was norovirus, showing a seasonal pattern for both public and professionals, which matched the periodic disease occurrence. Meningitis was a clear example of a disease with heightened media coverage tending to focus on individual and celebrity cases. Influenza was a major concern during the 2009 H1N1 outbreak creating massive public interest in line with the spring and autumn peaks in cases; although in autumn 2009, there was no corresponding increase in media coverage. Online resources play an increasing role in fulfilling professionals’ and public information needs. Conclusions Significant factors related to a surge of professional interest around a disease were typically key publications and major policy changes. Public interests seem more static and correlate with media influence but to a lesser extent than expected. The only exception was norovirus, exhibiting online public and professional interest correlating with seasonal occurrences of the disease. Public health agencies with responsibility for risk communication of public health events, in particular during outbreaks and emergencies, need to collaborate with media in order to ensure the coverage is high quality and evidence-based, while professionals’ information needs remain mainly fulfilled by online open access to key resources.

Gaming to master the game - Game usability and game mechanics

Health intervention aimed at children using serious games are starting to grow on popularity, however, Interactive Digital Storytelling (IDS) paradigm for serious games is in its infancy. In this article, we present a series of IDS educational games developed with the aim of promoting responsible antibiotic use and hygiene part of the edugames4all project. Despite commercial success and market popularity of IDS games one of the major challenges we encountered when the games were distributed to schools for evaluation was that many children never played a similar game before and found the concept challenging. As a result, some of the children enjoyed the game while others were frustrated and gave up at a certain point. Although the phenomenon is not new, and it present even in commercial games, we proposed a new approach to ensure that all children understand the message delivered and at the same time, they enjoy playing the game. This paper proposes the introduction of a training mission that teaches children in a game like environment the basic concepts necessary to progress through the game. The training mission was evaluated in experimental settings with two groups of children, one playing the training mission before playing the game and another one who did not. The results showed that there is no statistically significant difference in terms of usability between the two groups, however the group that did not play the training mission found the game more “awkward” to play, and the difference between the groups in this case was statistically significant.

A roadmap to integrated digital public health surveillance: the vision and the challenges

The exponentially increasing stream of real time big data produced by Web 2.0 Internet and mobile networks created radically new interdisciplinary challenges for public health and computer science. Traditional public health disease surveillance systems have to utilize the potential created by new situation-aware realtime signals from social media, mobile/sensor networks and citizens? participatory surveillance systems providing invaluable free realtime event-based signals for epidemic intelligence. However, rather than improving existing isolated systems, an integrated solution bringing together existing epidemic intelligence systems scanning news media (e.g., GPHIN, MedISys) with real-time social media intelligence (e.g., Twitter, participatory systems) is required to substantially improve and automate early warning, outbreak detection and preparedness operations. However, automatic monitoring and novel verification methods for these multichannel event-based real time signals has to be integrated with traditional case-based surveillance systems from microbiological laboratories and clinical reporting. Finally, the system needs effectively support coordination of epidemiological teams, risk communication with citizens and implementation of prevention measures.n However, from computational perspective, signal detection, analysis and verification of very high noise realtime big data provide a number of interdisciplinary challenges for computer science. Novel approaches integrating current systems into a digital public health dashboard can enhance signal verification methods and automate the processes assisting public health experts in providing better informed and more timely response. In this paper, we describe the roadmap to such a system, components of an integrated public health surveillance services and computing challenges to be resolved to create an integrated real world solution.

On Effective Integration of Educational Content in Serious Games: Text vs. Game Mechanics

As serious games are emerging as a new educational paradigm, it is increasingly important to understand how to integrate educational content into the games, and what elements of the game make learning more effective. This research proposes to add to the work in the area by examining whether learning objectives delivered through the game narratives as text, or learning objectives delivered through game mechanics provide a more effective way of integrating educational content in a game. In order to investigate this question, we designed a study to evaluate two types of participants that were divided into two groups to take part in complementary versions of the game. Participants are asked to play a game in which learning objectives are delivered either through text or game mechanics. An evaluation was performed with 60 participants. The results show that for one of the learning objectives, the participants learn more when the educational content was integrated through the game mechanics and that the difference between the group that learns through text and the one that learned through the game mechanics is statistically significant. For the rest of the learning objectives covered, no statistically significant difference was obtained between the two ways of integrating the learning objectives.

Integration and visualization public health dashboard: the medi+board pilot project

Traditional public health surveillance systems would benefit from integration with knowledge created by new situation-aware realtime signals from social media, online searches, mobile/sensor networks and citizens participatory surveillance systems. However, the challenge of threat validation, cross-verification and information integration for risk assessment has so far been largely untackled. In this paper, we propose a new system, medi+board, monitoring epidemic intelligence sources and traditional case-based surveillance to better automate early warning, cross-validation of signals for outbreak detection and visualization of results on an interactive dashboard. This enables public health professionals to see all essential information at a glance. Modular and configurable to any event defined by public health experts, medi+board scans multiple data sources, detects changing patterns and uses a configurable analysis module for signal detection to identify a threat. These can be validated by an analysis module and correlated with other sources to assess the reliability of the event classified as the reliability coefficient which is a real number between zero and one. Events are reported and visualized on the medi+board dashboard which integrates all information sources and can be navigated by a timescale widget. Simulation with three datasets from the swine flu 2009 pandemic (HPA surveillance, Google news, Twitter) demonstrates the potential of medi+board to automate data processing and visualization to assist public health experts in decision making on control and response measures.

Who is Spreading Rumours about Vaccines?: Influential User Impact Modelling in Social Networks

Vaccine hesitancy, traditionally linked to issues of trust, misinformation and prior beliefs, has been increasingly fuelled by influential groups on social media (SM) and the Internet. Analysis of news media and social networks (SN) accessible in real-time provides a new opportunity for detecting changes in public confidence in vaccines. However, different concerns are important in different regions, and reasons for hesitancy and the role of opinion leaders vary between sub-controversies in the broader vaccination debates. It is therefore important for public health professionals to gain an overview of the emerging debates in cyberspace, identify influential users and rumours, and assess their impact in order to know how to respond. The VAC Medi+Board project aims to visualise the diffusion of rumours through SN and assess the impact of key individuals. We include, as a case study, discussions during winter 2015-16 pertaining to the alleged side-effects of the HPV vaccine.