Solving the problem of cooperation is fundamentally important for the creation and maintenance of functional societies. Problems of cooperation are omnipresent within human society, with examples ranging from navigating busy road junctions to negotiating treaties. As the use of AI becomes more pervasive throughout society, the need for socially intelligent agents capable of navigating these complex cooperative dilemmas is becoming increasingly evident. Direct punishment is a ubiquitous social mechanism that has been shown to foster the emergence of cooperation in both humans and non-humans. In the natural world, direct punishment is often strongly coupled with partner selection and reputation and used in conjunction with third-party punishment. The interactions between these mechanisms could potentially enhance the emergence of cooperation within populations. However, no previous work has evaluated the learning dynamics and outcomes emerging from multi-agent reinforcement learning populations that combine these mechanisms. This paper addresses this gap. It presents a comprehensive analysis and evaluation of the behaviors and learning dynamics associated with direct punishment, third-party punishment, partner selection, and reputation. Finally, we discuss the implications of using these mechanisms on the design of cooperative AI systems.

Cooperation among independent learning agents is desirable as it enables reaching collectively rewarding states. Recent work has shown that artificial agents can learn to act pro-socially without the need for predefined cooperative preferences or behavioural heuristics, provided that they can observe others' actions or policies and select them as partners accordingly. This paper relaxes this constraint, studying reinforcement learning (RL) agents operating with only minimal information about others' behaviour. We propose a novel `Observer Model', where agents gain insights from direct experience and limited, indirect observations. We show that direct experience alone cannot sustain cooperation, particularly in large societies. However, even minimal observations of third-party interactions, allowing as few as one observer per gameplay, lead to significant improvements, enabling the population to achieve and sustain robust cooperation across varying population sizes. Through numerical analysis, we show the co-evolution of strategy and interaction structure and disentangle how learning happens under various settings. Analysing the partner selection graph, we identify the reasons for cooperation to emerge, and we explore how different learning and exploration rates affect the outcome of social dilemmas played among RL agents.

Ensuring the reliability of voice services in 5G networks requires effective detection of anomalies in IMS signaling. However, this task remains challenging due to the architectural complexity of IMS and the large volume of signaling data. In this paper, we propose SIP-Classifier, an unsupervised methodology that combines Transformer-based representation learning with clustering to identify anomalous SIP sequences. The approach encodes SIP messages through protocol-aware tokenization, learns latent representations via an autoregressive Transformer, and clusters them to distinguish valid from anomalous flows. We evaluate the method on real-world IMS data collected from operational 5G networks. It achieves 98% accuracy, 98% precision, 95% recall, and a 96% F1-score, significantly outperforming state-of-the-art approaches.

In this paper, we introduce Partial Information Decomposition of Features (PIDF), a new paradigm for simultaneous data interpretability and feature selection. Contrary to traditional methods that assign a single importance value, our approach is based on three metrics per feature: the mutual information shared with the target variable, the feature’s contribution to synergistic information, and the amount of this information that is redundant. In particular, we develop a novel procedure based on these three metrics, which reveals not only how features are correlated with the target but also the additional and overlapping information provided by considering them in combination with other features. We extensively evaluate PIDF using both synthetic and real-world data, demonstrating its potential applications and effectiveness, by considering case studies from genetics and neuroscience.

Decision-making agents based on pre-trained Large Language Models (LLMs) are increasingly being deployed across various domains of human activity. While their applications are currently rather specialized, several research efforts are underway to develop more generalist agents. As LLM-based systems become more agentic, their influence on human activity will grow and their transparency will decrease. Consequently, developing effective methods for aligning them to human values is vital. The prevailing practice in alignment often relies on human preference data (e.g., in RLHF or DPO), in which values are implicit, opaque and are essentially deduced from relative preferences over different model outputs. In this work, instead of relying on human feedback, we introduce the design of reward functions that explicitly and transparently encode core human values for Reinforcement Learning-based fine-tuning of foundation agent models. Specifically, we use intrinsic rewards for the moral alignment of LLM agents. We evaluate our approach using the traditional philosophical frameworks of Deontological Ethics and Utilitarianism, quantifying moral rewards for agents in terms of actions and consequences on the Iterated Prisoner's Dilemma (IPD) environment. We also show how moral fine-tuning can be deployed to enable an agent to unlearn a previously developed selfish strategy. Finally, we find that certain moral strategies learned on the IPD game generalize to several other matrix game environments. In summary, we demonstrate that fine-tuning with intrinsic rewards is a promising general solution for aligning LLM agents to human values, and it might represent a more transparent and cost-effective alternative to currently predominant alignment techniques.

Network Intrusion Detection (NID) remains a key area of research within the information security community, while also being relevant to Machine Learning (ML) practitioners. The latter generally aim to detect attacks using network features, which have been extracted from raw network data typically using dimensionality reduction methods, such as principal component analysis (PCA). However, PCA is not able to assess the relevance of features for the task at hand. Consequently, the features available are of varying quality, with some being entirely non-informative. From this, two major drawbacks arise. Firstly, trained and deployed models have to process large amounts of unnecessary data, therefore draining potentially costly resources. Secondly, the noise caused by the presence of irrelevant features can, in some cases, impede a model's ability to detect an attack. In order to deal with these challenges, we present Feature Selection for Network Intrusion Detection (FSNID) a novel information-theoretic method that facilitates the exclusion of non-informative features when detecting network intrusions. The proposed method is based on function approximation using a neural network, which enables a version of our approach that incorporates a recurrent layer. Consequently, this version uniquely enables the integration of temporal dependencies. Through an extensive set of experiments, we demonstrate that the proposed method selects a significantly reduced feature set, while maintaining NID performance. Code available at https://github.com/c-s-westphal/FSNID.

Abstract Solving the problem of cooperation is fundamentally important for the creation and maintenance of functional societies. Problems of cooperation are omnipresent within human society, with examples ranging from navigating busy road junctions to negotiating treaties. As the use of AI becomes more pervasive throughout society, the need for socially intelligent agents capable of navigating these complex cooperative dilemmas is becoming increasingly evident. Direct punishment is a ubiquitous social mechanism that has been shown to foster the emergence of cooperation in both humans and non-humans. In the natural world, direct punishment is often strongly coupled with partner selection and reputation and used in conjunction with third-party punishment. The interactions between these mechanisms could potentially enhance the emergence of cooperation within populations. However, no previous work has evaluated the learning dynamics and outcomes emerging from multi-agent reinforcement learning populations that combine these mechanisms. This paper addresses this gap. It presents a comprehensive analysis and evaluation of the behaviors and learning dynamics associated with direct punishment, third-party punishment, partner selection, and reputation. Finally, we discuss the implications of using these mechanisms on the design of cooperative AI systems.

Machine Learning (ML) is increasingly accessible to users with limited knowledge of its theoretical foundations. However, misapplying it can lead to negative consequences. This paper reports on a qualitative study designed to reveal challenges that novices encounter when learning about basic ML concepts and building their first models. Twenty participants were introduced to fundamental ML concepts for classification through an interactive tutorial involving an off-the-shelf GUI application, built their own ML model for a shape gesture dataset, and participated in a semi-structured interview. A thematic analysis revealed insights into these challenges, particularly around problem selection and multi-dimensionality, but also around what constitutes ML, algorithm selection , cross-validation, and interpreting visualizations. Despite these and other misconceptions, participants reflected on good model building practices, discussing that algorithm selection might require knowledge and context and that input features may introduce bias. We discuss the findings’ implications for the design of ML tools for novices.

Interactive Machine Learning (IML) enables users, including non-experts in ML, to iteratively train and improve ML models. However, limited research has been reported on how non-experts interact with these systems. Focusing on thematic analysis as a practical application, we report on a user study where 20 participants interacted with TACA, a functioning IML tool. Thematic analysis involves individual interpretation of ambiguous data, hence it is suited for and can benefit from the iterative customization of models supported by IML. Through a combination of interaction logs and semi-structured interviews, our findings revealed that, by using TACA, participants critically reflected on their analysis, gained new thematic insights, and adapted their interpretative stance. We also document misconceptions of ML concepts, positivist views, and personal blame for poor model performance. We then discuss how applications could be designed to improve the understanding of IML concepts and foster reflexive work practices.

The coevolution of signalling is a complex problem within animal behaviour, and is also central to communication between artificial agents. The Sir Philip Sidney game was designed to model this dyadic interaction from an evolutionary biology perspective, and was formulated to demonstrate the emergence of honest signalling. We use Multi-Agent Reinforcement Learning (MARL) to show that in the majority of cases, the resulting behaviour adopted by agents is not that shown in the original derivation of the model. This paper demonstrates that MARL can be a powerful tool to study evolutionary dynamics and understand the underlying mechanisms of learning over generations; particularly advantageous is the interpretability of this type of approach, as well as the fact that it allows us to study emergent behaviour without the need to constrain the strategy space from the outset. Although it originally set out to exemplify honest signalling, we show that the game provides no incentive for such behaviour. In the majority of cases, the optimal outcome is one that does not require a signal for the resource to be given. This type of interaction is observed within animal behaviour and is sometimes referred to as proactive prosociality. High learning and low discount rates of the reinforcement learning model are shown to be optimal in order to achieve the outcome that maximises both agents' reward, and proximity to the given threshold leads to suboptimal learning.

The increasing adoption of machine learning (ML) raises ethical concerns, particularly regarding bias. This study explores how ML practitioners with limited experience in bias understand and apply bias definitions, detection measures, and mitigation methods. Through a take-home task, exercises, and interviews with 22 participants, we identified five key themes: sources of bias, selecting bias metrics, detecting bias, mitigating bias, and ethical considerations. Participants faced unresolved conflicts, such as applying fairness definitions in practice, selecting context-dependent bias metrics, addressing real-world biases, balancing model performance with bias mitigation, and relying on personal perspectives over data-driven metrics. While bias mitigation techniques helped identify biases in two datasets, participants could not fully eliminate bias, citing the oversimplification of complex processes into models with limited variables. We propose designing bias detection tools that encourage practitioners to focus on the underlying assumptions and integrating bias concepts into ML practices, such as using a harmonic mean-based approach, akin to the F1 score, to balance bias and accuracy.

Bike Sharing Systems (BSS) represent a sustainable and efficient urban transportation solution. A major challenge in BSS is repositioning bikes to avoid shortage events when users encounter empty or full bike lockers. Existing algorithms unrealistically rely on precise demand forecasts and tend to overlook substantial operational costs associated with reallocations. This paper introduces a novel Cost-aware Adaptive Bike Repositioning Agent (CABRA), which harnesses advanced deep reinforcement learning techniques in dock-based BSS. By analyzing demand patterns, CABRA learns adaptive repositioning strategies aimed at reducing shortages and enhancing truck route planning efficiency, significantly lowering operational costs. We perform an extensive experimental evaluation of CABRA utilizing real-world data from Dublin, London, Paris, and New York. The reported results show that CABRA achieves operational efficiency that outperforms or matches very challenging baselines, obtaining a significant cost reduction. Its performance on the largest city comprising 1765 docking stations highlights the efficiency and scalability of the proposed solution even when applied to BSS with a great number of docking stations.

Growing concerns about safety and alignment of AI systems highlight the importance of embedding moral capabilities in artificial agents: a promising solution is the use of learning from experience, i.e., Reinforcement Learning. In multi-agent (social) environments, complex population-level phenomena may emerge from interactions between individual learning agents. Many of the existing studies rely on simulated social dilemma environments to study the interactions of independent learning agents; however, they tend to ignore the moral heterogeneity that is likely to be present in societies of agents in practice. For example, at different points in time a single learning agent may face opponents who are consequentialist (i.e., focused on maximizing outcomes over time), norm-based (i.e., conforming to specific norms), or virtue-based (i.e., considering a combination of different virtues). The extent to which agents' co-development may be impacted by such moral heterogeneity in populations is not well understood. In this paper, we present a study of the learning dynamics of morally heterogeneous populations interacting in a social dilemma setting. Using an Iterated Prisoner's Dilemma environment with a partner selection mechanism, we investigate the extent to which the prevalence of diverse moral agents in populations affects individual agents' learning behaviors and emergent population-level outcomes. We observe several types of non-trivial interactions between pro-social and anti-social agents, and find that certain types of moral agents are able to steer selfish agents towards more cooperative behavior.

Generative Artificial Intelligence (AI) is one of the most exciting developments in Computer Science of the last decade. At the same time, Reinforcement Learning (RL) has emerged as a very successful paradigm for a variety of machine learning tasks. In this survey, we discuss the state of the art, opportunities and open research questions in applying RL to generative AI. In particular, we will discuss three types of applications, namely, RL as an alternative way for generation without specified objectives; as a way for generating outputs while concurrently maximizing an objective function; and, finally, as a way of embedding desired characteristics, which cannot be easily captured by means of an objective function, into the generative process. We conclude the survey with an in-depth discussion of the opportunities and challenges in this fascinating emerging area.

Border Theory suggests individuals create borders to manage the transitions between work and family (or, more generally, life) domains. The degree of separation or integration of domains across borders has an impact on the balance between work and life. Previous studies have shown individuals who perceive balance between work and life domains tend to be more satisfied with their lives, reporting higher physical and mental health. At times of crisis, such as during a pandemic, borders can be disrupted, affecting work-life balance and leading to a short- or long-term negative impact on well-being. Border theory provides a systematic lens through which to study these changes. However, changes cannot be studied using interviews or diaries as these are not at the scale required when societal disruptions occur. In this paper, we explore the feasibility of using a computational linguistic approach to operationalize border theory at scale, using readily available social media data. In particular, we make two main contributions. First, we design metrics to measure key characteristics of borders. This involves the application of a transformer-based topic modeling technique, BERTopic, to detect topics from social media data. Second, we apply this operationalization to a case study of around a million tweets posted by nearly two hundred teachers and journalists in the UK from the beginning of 2019 to the end of 2022. In so doing, we longitudinally study and compare the changes in borders between work and life before, during, and after COVID-19 lockdown periods.

Open Radio Access Network (O-RAN) is an emerging paradigm proposed for enhancing the 5G network infrastructure. O-RAN promotes open vendor-neutral interfaces and virtualized network functions that enable the decoupling of network components and their optimization through intelligent controllers. The decomposition of base station functions enables better resource usage, but also opens new technical challenges concerning their efficient orchestration and allocation. In this paper, we propose Proactive Resource Orchestrator based on Reinforcement Learning (PRORL), a novel solution for the efficient and dynamic allocation of resources in O-RAN infrastructures. We frame the problem as a Markov Decision Process and solve it using Deep Reinforcement Learning; one relevant feature of PRORL is that it learns demand patterns from experience for proactive resource allocation. We extensively evaluate our proposal by using both synthetic and real-world data, showing that we can significantly outperform the existing algorithms, which are typically based on the analysis of static demands. More specifically, we achieve an improvement of 90% over greedy baselines and deal with complex trade-offs in terms of competing objectives such as demand satisfaction, resource utilization, and the inherent cost associated with allocating resources.

Practical uses of Artificial Intelligence (AI) in the real world have demonstrated the importance of embedding moral choices into intelligent agents. They have also highlighted that defining top-down ethical constraints on AI according to any one type of morality is extremely challenging and can pose risks. A bottom-up learning approach may be more appropriate for studying and developing ethical behavior in AI agents. In particular, we believe that an interesting and insightful starting point is the analysis of emergent behavior of Reinforcement Learning (RL) agents that act according to a predefined set of moral rewards in social dilemmas. In this work, we present a systematic analysis of the choices made by intrinsically-motivated RL agents whose rewards are based on moral theories. We aim to design reward structures that are simplified yet representative of a set of key ethical systems. Therefore, we first define moral reward functions that distinguish between consequence- and norm-based agents, between morality based on societal norms or internal virtues, and between single- and mixed-virtue (e.g., multi-objective) methodologies. Then, we evaluate our approach by modeling repeated dyadic interactions between learning moral agents in three iterated social dilemma games (Prisoner's Dilemma, Volunteer's Dilemma and Stag Hunt). We analyze the impact of different types of morality on the emergence of cooperation, defection or exploitation, and the corresponding social outcomes. Finally, we discuss the implications of these findings for the development of moral agents in artificial and mixed human-AI societies.

Distributed workload queues are nowadays widely used due to their significant advantages in terms of decoupling, resilience, and scaling. Task allocation to worker nodes in distributed queue systems is typically simplistic (e.g., Least Recently Used) or uses hand-crafted heuristics that require task-specific information (e.g., task resource demands or expected time of execution). When such task information is not available and worker node capabilities are not homogeneous, the existing placement strategies may lead to unnecessarily large execution timings and usage costs. In this work, we formulate the task allocation problem in theMarkov Decision Processframework, in which an agent assigns tasks to an available resource, and receives a numerical reward signal upon task completion. Our adaptive and learning-based task allocation solution, Reinforcement Learning based Queues (RLQ), is implemented and integrated with the popular Celery task queuing system for Python. We compareRLQagainst traditional solutions using both synthetic and real workload traces. On average, using synthetic workloads,RLQreduces the execution cost by approximately 70%, the execution time by a factor of at least 3×, and the waiting time by almost 7×. Using real traces, we observe an improvement of about 20% for execution cost, around 70% improvement for execution time, and a reduction of approximately 20× in waiting time. We also compareRLQwith a strategy inspired by E-PVM, a state-of-the-art solution used in Google's Borg cluster manager, showing we are able to outperform it in five out of six scenarios.

Sensor-based sleep monitoring systems can be used to track sleep behavior on a daily basis and provide feedback to their users to promote health and well-being. Such systems can provide data visualizations to enable self-reflection on sleep habits or a sleep coaching service to improve sleep quality. To provide useful feedback, sleep monitoring systems must be able to recognize whether an individual is sleeping or awake. Existing approaches to infer sleep-wake phases, however, typically assume continuous streams of data to be available at inference time. In real-world settings, though, data streams or data samples may be missing, causing severe performance degradation of models trained on complete data streams. In this paper, we investigate the impact of missing data to recognize sleep and wake, and use regression- and interpolation-based imputation strategies to mitigate the errors that might be caused by incomplete data. To evaluate our approach, we use a data set that includes physiological traces - collected using wristbands -, behavioral data - gathered using smartphones - and self-reports from 16 participants over 30 days. Our results show that the presence of missing sensor data degrades the balanced accuracy of the classifier on average by 10–35 percentage points for detecting sleep and wake depending on the missing data rate. The impu-tation strategies explored in this work increase the performance of the classifier by 4–30 percentage points. These results open up new opportunities to improve the robustness of sleep monitoring systems against missing data.

Public goods games represent insightful settings for studying incentives for individual agents to make contributions that, while costly for each of them, benefit the wider society. In this work, we adopt the perspective of a central planner with a global view of a network of self-interested agents and the goal of maximizing some desired property in the context of a best-shot public goods game. Existing algorithms for this known NP-complete problem find solutions that are sub-optimal and cannot optimize for criteria other than social welfare.In order to efficiently solve public goods games, our proposed method directly exploits the correspondence between equilibria and the Maximal Independent Set (mIS) structural property of graphs. In particular, we define a Markov Decision Process which incrementally generates an mIS, and adopt a planning method to search for equilibria, outperforming existing methods. Furthermore, we devise a graph imitation learning technique that uses demonstrations of the search to obtain a graph neural network parametrized policy which quickly generalizes to unseen game instances. Our evaluation results show that this policy is able to reach 99.5\% of the performance of the planning method while being three orders of magnitude faster to evaluate on the largest graphs tested. The methods presented in this work can be applied to a large class of public goods games of potentially high societal impact and more broadly to other graph combinatorial optimization problems.

Understanding in which circumstances office workers take rest breaks is important for delivering effective mobile notifications and make inferences about their daily lifestyle, e.g., whether they are active and/or have a sedentary life. Previous studies designed for office workers show the effectiveness of rest breaks for preventing work-related conditions. In this article, we propose a hybrid personalised model involving a kernel density estimation model and a generalised linear mixed model to model office workers’ available moments for rest breaks during working hours. We adopt the experience-based sampling method through which we collected office workers’ responses regarding their availability through a mobile application with contextual information extracted by means of the mobile phone sensors. The experiment lasted 10 workdays and involved 19 office workers with a total of 528 responses. Our results show that time, location, ringer mode, and activity are effective features for predicting office workers’ availability. Our method can address sparse sample issues for building individual predictive behavioural models based on limited and unbalanced data. In particular, the proposed method can be considered as a potential solution to the “cold-start problem,” i.e., the negative impact of the lack of individual data when a new application is installed.

Ubiquitous computing is moving from context-awareness to context-prediction. In order to build truly anticipatory systems developers have to deal with many challenges, from multimodal sensing to modeling context from sensed data, and, when necessary, coordinating multiple predictive models across devices. Novel expressive programming interfaces and paradigms are needed for this new class of mobile and ubiquitous applications. In this paper we present FutureWare, a middleware for seamless development of mobile applications that rely on context prediction. FutureWare exposes an expressive API to lift the burden of mobile sensing, individual and group behavior modeling, and future context querying, from an application developer. We implement FutureWare as an Android library, and through a scenario-based testing and a demo app we show that it represents an efficient way of supporting anticipatory applications, reducing the necessary coding effort by two orders of magnitude.

Social dilemmas have been widely studied to explain how humans are able to cooperate in society. Considerable effort has been invested in designing artificial agents for social dilemmas that incorporate explicit agent motivations that are chosen to favor coordinated or cooperative responses. The prevalence of this general approach points towards the importance of achieving an understanding of both an agent's internal design and external environment dynamics that facilitate cooperative behavior. In this paper, we investigate how partner selection can promote cooperative behavior between agents who are trained to maximize a purely selfish objective function. Our experiments reveal that agents trained with this dynamic learn a strategy that retaliates against defectors while promoting cooperation with other agents resulting in a prosocial society.

In mobile crowd-sourcing systems, simply relying on people to opportunistically select and perform tasks typically leads to drawbacks such as low task acceptance/completion rates and undesirable spatial skews. In this paper, we utilize data from TASKer, a campus-based mobile crowd-sourcing platform, to empirically study and discover whether and how various context-aware notification strategies can help overcome such drawbacks. We first study worker interactions, in the absence of any notifications, to discover some spatio-temporal properties of task acceptance and completion. Based on these insights, we then experimentally demonstrate the effectiveness of two novel, non-personal, context-driven notification strategies, comparing the outcomes to two different baselines (no-notification and random-notification). Finally, using the data from the random-notification mechanism, we derive a classification model, incorporating several novel contextual features, that can predict a worker's responsiveness to notifications with high accuracy. Our work extends the crowd-sourcing literature by emphasizing the power of smart notifications for greater worker engagement.

Personal interactions and information access are happening more and more through the mediation of computing devices of various types all around us. In our daily life we use many computing devices running different versions of the same application such as email clients or social media platforms, which alert users about a new piece of information or event on all devices. In this paper we first present a study investigating the factors influencing users' decisions in handling notifications in a multi-device environment. We collected 57,242 in-the-wild notifications from 24 users over a period of 21 days. We found that users' decisions in handling notifications are impacted by their physical activity, location, network connectivity, application category and the device used for handling the previous notification. Finally, we show that an individualized model can predict the device on which the user will handle a notification in the given context with 82% specificity and 91% sensitivity.

Smartphones are increasingly augmented with sensors for a variety of purposes. In this paper, we show how magnetic field emissions can be used to fingerprint smartphones. Previous work on identification rely on specific characteristics that vary with the settings and components available on a device. This limits the number of devices on which one approach is effective. By contrast, all electronic devices emit a magnetic field which is accessible either through the API or measured through an external device.

While mobile apps have become an integral part of everyday life, little is known about the factors that govern their usage. Particularly the role of geographic and cultural factors has been understudied. This article contributes by carrying out a large-scale analysis of geographic, cultural, and demographic factors in mobile usage. We consider app usage gathered from 25,323 Android users from 44 countries and 54,776 apps in 55 categories, and demographics information collected through a user survey. Our analysis reveals significant differences in app category usage across countries and we show that these differences, to large degree, reflect geographic boundaries. We also demonstrate that country gives more information about application usage than any demographic, but that there also are geographic and socio-economic subgroups in the data. Finally, we demonstrate that app usage correlates with cultural values using the Value Survey Model of Hofstede as a reference of cross-cultural differences.

Estimating revenue and business demand of a newly opened venue is paramount as these early stages often involve critical decisions such as first rounds of staffing and resource allocation. Traditionally, this estimation has been performed through coarse measures such as observing numbers in local venues. The advent of crowdsourced data from devices and services has opened the door to better predictions of temporal visitation patterns for locations and venues. In this paper, using mobility data from the location-based service Foursquare, we treat venue categories as proxies for urban activities and analyze how they become popular over time. The main contribution of this work is a prediction framework able to use characteristic temporal signatures of places together with k-nearest neighbor metrics capturing similarities among urban regions to forecast weekly popularity dynamics of a new venue establishment. Our evaluation shows that temporally similar areas of a city can be valuable predictors, decreasing error by 41%. Our findings have the potential to impact the design of location-based technologies and decisions made by new business owners.

The abundance of data produced daily from large variety of sources has boosted the need of novel approaches on causal inference analysis from observational data. Observational data often contain noisy or missing entries. Moreover, causal inference studies may require unobserved high-level information which needs to be inferred from other observed attributes. In such cases, inaccuracies of the applied inference methods will result in noisy outputs. In this study, we propose a novel approach for causal inference when one or more key variables are noisy. Our method utilizes the knowledge about the uncertainty of the real values of key variables in order to reduce the bias induced by noisy measurements. We evaluate our approach in comparison with existing methods both on simulated and real scenarios and we demonstrate that our method reduces the bias and avoids false causal inference conclusions in most cases.

The wide adoption of mobile devices and social media platforms have dramatically increased the collection and sharing of personal information. More and more frequently, users are called to make decisions concerning the disclosure of their personal information. In this study, we investigate the factors affecting users’ choices toward the disclosure of their personal data, including not only their demographic and self-reported individual characteristics, but also their social interactions and their mobility patterns inferred from months of mobile phone data activity. We report the findings of a field study conducted with a community of 63 subjects provided with (i) a smart-phone and (ii) a Personal Data Store (PDS) enabling them to control the disclosure of their data. We monitor the sharing behavior of our participants through the PDS and evaluate the contribution of different factors affecting their disclosing choices of location and social interaction data. Our analysis shows that social interaction inferred by mobile phones is an important factor revealing willingness to share, regardless of the data type. In addition, we provide further insights on the individual traits relevant to the prediction of sharing behavior.

Notifications are extremely beneficial to users, but they often demand their attention at inappropriate moments. In this paper we present an in-situ study of mobile interruptibility focusing on the effect of cognitive and physical factors on the response time and the disruption perceived from a notification. Through a mixed method of automated smartphone logging and experience sampling we collected 10372 in-the-wild notifications and 474 questionnaire responses on notification perception from 20 users. We found that the response time and the perceived disruption from a notification can be influenced by its presentation, alert type, sender-recipient relationship as well as the type, completion level and complexity of the task in which the user is engaged. We found that even a notification that contains important or useful content can cause disruption. Finally, we observe the substantial role of the psychological traits of the individuals on the response time and the disruption perceived from a notification.

Mobile notifications are increasingly used by a variety of applications to inform users about events, news or just to send alerts and reminders to them. However, many notifications are neither useful nor relevant to users' interests and, also for this reason, they are considered disruptive and potentially annoying.

Large metropolitan cities bring together diverse individuals, creating opportunities for cultural and intellectual exchanges, which can ultimately lead to social and economic enrichment. In this work, we present a novel network perspective on the interconnected nature of people and places, allowing us to capture the social diversity of urban locations through the social network and mobility patterns of their visitors. We use a dataset of approximately 37K users and 42K venues in London to build a network of Foursquare places and the parallel Twitter social network of visitors through check-ins. We define four metrics of the social diversity of places which relate to their social brokerage role, their entropy, the homogeneity of their visitors and the amount of serendipitous encounters they are able to induce. This allows us to distinguish between places that bring together strangers versus those which tend to bring together friends, as well as places that attract diverse individuals as opposed to those which attract regulars. We correlate these properties with wellbeing indicators for London neighbourhoods and discover signals of gentrification in deprived areas with high entropy and brokerage, where an influx of more affluent and diverse visitors points to an overall improvement of their rank according to the UK Index of Multiple Deprivation for the area over the five-year census period. Our analysis sheds light on the relationship between the prosperity of people and places, distinguishing between different categories and urban geographies of consequence to the development of urban policy and the next generation of socially-aware location-based applications.

Sharing economy platforms have become extremely popular in the last few years, and they have changed the way in which we commute, travel, and borrow among many other activities. Despite their popularity among consumers, such companies are poorly regulated. For example, Airbnb, one of the most successful examples of sharing economy platform, is often criticized by regulators and policy makers. While, in theory, municipalities should regulate the emergence of Airbnb through evidence-based policy making, in practice, they engage in a false dichotomy: some municipalities allow the business without imposing any regulation, while others ban it altogether. That is because there is no evidence upon which to draft policies. Here we propose to gather evidence from the Web. After crawling Airbnb data for the entire city of London, we find out where and when Airbnb listings are offered and, by matching such listing information with census and hotel data, we determine the socio-economic conditions of the areas that actually benefit from the hospitality platform. The reality is more nuanced than one would expect, and it has changed over the years. Airbnb demand and offering have changed over time, and traditional regulations have not been able to respond to those changes. That is why, finally, we rely on our data analysis to envision regulations that are responsive to real-time demands, contributing to the emerging idea of ``algorithmic regulation''.

Module identification or community detection in complex networks has become increasingly important in many scientific fields because it provides insight into the relationship and interaction between network function and topology. In recent years, module identification algorithms based on stochastic optimization algorithms such as evolutionary algorithms have been demonstrated to be superior to other algorithms on small- to medium-scale networks. However, the scalability and resolution limit (RL) problems of these module identification algorithms have not been fully addressed, which impeded their application to real-world networks. This paper proposes a novel module identification algorithm called cooperative co-evolutionary module identification to address these two problems. The proposed algorithm employs a cooperative co-evolutionary framework to handle large-scale networks. We also incorporate a recursive partitioning scheme into the algorithm to effectively address the RL problem. The performance of our algorithm is evaluated on 12 benchmark complex networks. As a medical application, we apply our algorithm to identify disease modules that differentiate low- and high-grade glioma tumors to gain insights into the molecular mechanisms that underpin the progression of glioma. Experimental results show that the proposed algorithm has a very competitive performance compared with other state-of-the-art module identification algorithms.

One of the most interesting applications of mobile sensing is monitoring of individual behavior, especially in the area of mental health care. Most existing systems require an interaction with the device, for example they may require the user to input his/her mood state at regular intervals. In this paper we seek to answer whether mobile phones can be used to unobtrusively monitor individuals affected by depressive mood disorders by analyzing only their mobility patterns from GPS traces. In order to get ground-truth measurements, we have developed a smartphone application that periodically collects the locations of the users and the answers to daily questionnaires that quantify their depressive mood. We demonstrate that there exists a significant correlation between mobility trace characteristics and the depressive moods. Finally, we present the design of models that are able to successfully predict changes in the depressive mood of individuals by analyzing their movements.

An increasing number of notifications demanding the smartphone user's attention, often arrive at an inappropriate moment, or carry irrelevant content. In this paper we present a study of mobile user interruptibility with respect to notification content, its sender, and the context in which a notification is received. In a real-world study we collect around 70,000 instances of notifications from 35 users. We group notifications according to the applications that initiated them, and the social relationship between the sender and the receiver. Then, by considering both content and context information, such as the current activity of a user, we discuss the design of classifiers for learning the most opportune moment for the delivery of a notification carrying a specific type of information. Our results show that such classifiers lead to a more accurate prediction of users' interruptibility than an alternative approach based on user-defined rules of their own interruptibility.

The mobile phone represents a unique platform for interactive applications that can harness the opportunity of an immediate contact with a user in order to increase the impact of the delivered information. However, this accessibility does not necessarily translate to reachability, as recipients might refuse an initiated contact or disfavor a message that comes in an inappropriate moment.

Smartphone sensing enables inference of physical context, while online social networks (OSNs) allow mobile applications to harness users' interpersonal relationships. However, OSNs and smartphone sensing remain disconnected, since obstacles, including the synchronization of mobile sensing and OSN monitoring, inefficiency of smartphone sensors, and privacy concerns, stand in the way of merging the information from these two sources.

People manage a spectrum of identities in cyber domains. Profiling individuals and assigning them to distinct groups or classes have potential applications in targeted services, online fraud detection, extensive social sorting, and cyber-security. This paper presents the Uncertainty of Identity Toolset, a framework for the identification and profiling of users from their social media accounts and e-mail addresses. More specifically, in this paper we discuss the design and implementation of two tools of the framework. The Twitter Geographic Profiler tool builds a map of the ethno-cultural communities of a person's friends on Twitter social media service. The E-mail Address Profiler tool identifies the probable identities of individuals from their e-mail addresses and maps their geographical distribution across the UK. To this end, this paper presents a framework for profiling the digital traces of individuals.

The importance of spatial information in Online Social Networks is increasing at a fast pace. The number of users regularly accessing services from their phones is rising and, therefore, local information is becoming more and more important, for example in targeted marketing and personalized services. In particular, news, from gossips to security alerts, are daily spread across cities through social networks. Content produced by users is consumed by their friends or followers, whose locations can be known or inferred. The spatial location of users' social connections strongly affects the areas where such information will be disseminated. As a consequence, some users can deliver content to a certain geographic area more easily and efficiently than others, for example because they have a larger number of friends in that area.

Mobile phones are integral to everyday life with emails, social networking, online banking and other applications; however, the wealth of private information accessible increases economic incentives for attackers. Compared with fixed networks, mobile malware can replicate through both long range messaging and short range radio technologies; the former can be filtered by the network operator but determining the best method of containing short range malware is an open problem. While global software updates are sometimes possible, they are often not practical. An alternative and more efficient strategy is to distribute the patch to the key nodes so that they can opportunistically disseminate it to the rest of the network via short range encounters; but how can these key nodes be identified in a highly dynamic network topology? In this paper, we address these questions by presenting Socio- Temporal Opportunistic Patching (STOP), a two-tier predictive mobile malware containment system: devices collect co-location data in a decentralized manner and report to a central server which processes and targets delivery of hot fixes to a small subset of k devices at runtime; in turn mobile devices spread the patch opportunistically. The STOP system is underpinned by a recent theoretical framework for analysing dynamic networks that takes into account temporal information of links. Using empirical contact traces, we find firstly, the top-k ranking temporal centrality nodes are highly correlated with past time windows; and secondly, simple prediction functions can be designed to select the set of top-k nodes that are optimal for patch spreading.

The interactions and social relations among users in workplaces have been studied by many generations of social psychologists. There is evidence that groups of users that interact more in workplaces are more productive. However, it is still hard for social scientists to capture fine-grained data about phenomena of this kind and to find the right means to facilitate interaction. It is also difficult for users to keep track of their level of sociability with colleagues. While mobile phones offer a fantastic platform for harvesting long term and fine grained data, they also pose challenges: battery power is limited and needs to be traded-off for sensor reading accuracy and data transmission, while energy costs in processing computationally intensive tasks are high.

Malicious mobile phone worms spread between devices via short-range Bluetooth contacts, similar to the propagation of human and other biological viruses. Recent work has employed models from epidemiology and complex networks to analyse the spread of malware and the effect of patching specific nodes. These approaches have adopted a static view of the mobile networks, i.e., by aggregating all the edges that appear over time, which leads to an approximate representation of the real interactions: instead, these networks are inherently dynamic and the edge appearance and disappearance are highly influenced by the ordering of the human contacts, something which is not captured at all by existing complex network measures. In this paper we first study how the blocking of malware propagation through immunisation of key nodes (even if carefully chosen through static or temporal betweenness centrality metrics) is ineffective: this is due to the richness of alternative paths in these networks. Then we introduce a time-aware containment strategy that spreads a patch message starting from nodes with high temporal closeness centrality and show its effectiveness using three real-world datasets. Temporal closeness allows the identification of nodes able to reach most nodes quickly: we show that this scheme reduces the cellular network resource consumption and associated costs, achieving, at the same time, complete containment of malware in a limited amount of time.

Providers such as YouTube offer easy access to multimedia content to millions, generating high bandwidth and storage demand on the Content Delivery Networks they rely upon. More and more, the diffusion of this content happens on online social networks such as Facebook and Twitter, where social cascades can be observed when users increasingly repost links they have received from others. In this paper we describe how geographic information extracted from social cascades can be exploited to improve caching of multimedia files in a Content Delivery Network. We take advantage of the fact that social cascades can propagate in a geographically limited area to discern whether an item is spreading locally or globally. This informs cache replacement policies, which utilize this information to ensure that content relevant to a cascade is kept close to the users who may be interested in it. We validate our approach by using a novel dataset which combines social interaction data with geographic information: we track social cascades of YouTube links over Twitter and build a proof-of-concept geographic model of a realistic distributed Content Delivery Network. Our performance evaluation shows that we are able to improve cache hits with respect to cache policies without geographic and social information.

Today's mobile phones represent a rich and powerful computing platform, given their sensing, processing and communication capabilities. Phones are also part of the everyday life of billions of people, and therefore represent an exceptionally suitable tool for conducting social and psychological experiments in an unobtrusive way.

Most of the existing research work in mobile ad hoc networking is based on the assumption that a path exists between the sender and the receiver. On the other hand, applications of decentralised mobile systems are often characterised by network partitions. As a consequence delay tolerant networking research has received considerable attention in the recent years as a means to obviate to the gap between ad hoc network research and real applications. In this paper we present the design, implementation and evaluation of the context-aware adaptive routing (CAR) protocol for delay tolerant unicast communication in intermittently connected mobile ad hoc networks. The protocol is based on the idea of exploiting nodes as carriers of messages among network partitions to achieve delivery. The choice of the best carrier is made using Kalman filter based prediction techniques and utility theory. We discuss the implementation of CAR over an opportunistic networking framework, outlining possible applications of the general principles at the basis of the proposed approach. The large scale performance of the CAR protocol are evaluated using simulations based on a social network founded mobility model, a purely random one and real traces from Dartmouth College.

We present the design, implementation, evaluation, and user ex periences of theCenceMe application, which represents the first system that combines the inference of the presence of individuals using off-the-shelf, sensor-enabled mobile phones with sharing of this information through social networking applications such as Facebook and MySpace. We discuss the system challenges for the development of software on the Nokia N95 mobile phone. We present the design and tradeoffs of split-level classification, whereby personal sensing presence (e.g., walking, in conversation, at the gym) is derived from classifiers which execute in part on the phones and in part on the backend servers to achieve scalable inference. We report performance measurements that characterize the computational requirements of the software and the energy consumption of the CenceMe phone client. We validate the system through a user study where twenty two people, including undergraduates, graduates and faculty, used CenceMe continuously over a three week period in a campus town. From this user study we learn how the system performs in a production environment and what uses people find for a personal sensing system.

No abstract available.

Developing protocols and applications for opportunistic networking can represent a daunting task given the many aspects that must be taken into consideration, such as intermittent connectivity, smart choice among multiple interfaces and intelligent data storage. The implementation of these protocols can be based on generic layer-less communication frameworks that provide programming abstractions for the extraction and analysis of social, colocation and mobility information and allows data exchange by means of heterogeneous devices. We propose Gently, a novel fully implemented solution which combines techniques of context awareness and social knowledge to concretely solve issues related to opportunistic forwarding. More precisely, Gently is born as the combination of the Context-aware Adaptive Routing (CAR) and the socially aware LABEL protocol. We discuss the implementation of our solution on top of the layer-less Haggle framework presenting the key design choices and the lessons learnt.

Applications involving the dissemination of information directly relevant to humans (e.g., service advertising, news spreading, environmental alerts) often rely on publish-subscribe, in which the network delivers a published message only to the nodes whose subscribed interests match it. In principle, publish- subscribe is particularly useful in mobile environments, since it minimizes the coupling among communication parties. However, to the best of our knowledge, none of the (few) works that tackled publish-subscribe in mobile environments has yet addressed intermittently-connected human networks. Socially-related people tend to be co-located quite regularly. This characteristic can be exploited to drive forwarding decisions in the interest-based routing layer supporting the publish-subscribe network, yielding not only improved performance but also the ability to overcome high rates of mobility and long-lasting disconnections. In this paper we propose SocialCast, a routing framework for publish-subscribe that exploits predictions based on metrics of social interaction (e.g., patterns of movements among communities) to identify the best information carriers. We highlight the principles underlying our protocol, illustrate its operation, and evaluate its performance using a mobility model based on a social network validated with real human mobility traces. The evaluation shows that prediction of colocation and node mobility allow for maintaining a very high and steady event delivery with low overhead and latency, despite the variation in density, number of replicas per message or speed.

The integration of clusters of computers into computational grids has recently gained the attention of many computational scientists. While considerable progress has been made in building middleware and workflow tools that facilitate the sharing of compute resources, little attention has been paid to grid scheduling and load balancing techniques to reduce job waiting time. Based on a detailed analysis of usage characteristics of an existing grid that involves a large CPU cluster, we observe that grid scheduling decisions can be significantly improved if the characteristics of current usage patterns are understood and extrapolated into the future. The paper describes an architecture and an implementation for a predictive grid scheduling framework which relies on Kalman filter theory to predict future CPU resource utilisation. By way of replicated experiments we demonstrate that the prediction achieves a precision within 15-20% of the utilisation later observed and can significantly improve scheduling quality, compared to approaches that only take into account current load indicators.

Sensors are now embedded in all sorts of devices (such as phones and PDAs) and attached to many moving things such as robots, vehicles and animals. The collection of data from these mobile sensors presents challenges related to the variability of the topology of the sensor network and the need to limit communication (for energy or bandwidth saving). Fortunately, the data collected, despite considerable, is often delay tolerant and its delivery to the sinks is, in most cases, not time critical. We have devised SCAR, a context aware opportunistic routing protocol which allows efficient routing of sensor data to sinks, through selection of best paths by prediction over movement patterns and current battery level of nodes. In this paper we present the implementation of the protocol in Contiki and validate the approach through the use of the COOJA simulator with mobility traces provided by the ZebraNet Project. We compare the performance with respect to random choice based dissemination.

The testing of the performance of opportunistic communication protocols and applications is usually done through simulation as i) deployments are expensive and should be left to the final stage of the development process, and ii) the number of varying parameters in thesesystems is so high that it would be very hard to conduct thorough testing of all the functionality within a single deployment. Therefore, protocols and applications are often plugged into mobility simulators to test their performance; however, until recently, most of the testing has been conducted with random mobility models which do not mirror reality. Furthermore, despite disconnections playing a veryprominent role in the performance of any opportunistic mobile system, most models do not really account for it. A different approach to testing is the use of real traces of movement collected in specific domains as test cases. These cases, however, do not allow for flexible performance testing, as they are specific for a given scenario withfixed connectivity properties.

In recent years, various trust management models based on the human notion of trust have been proposed to support trust-aware decision making in pervasive systems. However, the degree of subjectivity embedded in human trust often clashes with the requirements imposed by the target scenario: on one hand, pervasive computing calls for autonomic and light-weight systems that impose minimum burden on the user of the device (and on the device itself); on the other hand, computational models of human trust seem to demand a large amount of user input and physical resources. The result is often a computational trust model that does not 'compute': either the degree of subjectivity it offers is limited, or its complexity compromises its usability. In this paper, we present an accurate and efficient trust prediction model that is based on a basic Kalman filter. We discuss simulation results to demonstrate that the predictor is capable of capturing the natural disposition to trust of the user of the device, while being autonomic and light-weight.

Sensor devices are being embedded in all sorts of items including vehicles, furniture but also animal and human bodies through health monitors and tagging techniques. The collection of the information generated by these devices is a challenging task as the data results in enormous amounts and the sensors have scarce resources (especially in terms of energy for the forwarding of the data). Fortunately, the data is often delay tolerant and its delivery to the sinks is, in most cases, not time critical.This paper tackles the problem of the delivery of mobile sensor data to sinks. We devise a Sensor Context-Aware Routing protocol (SCAR), which exploits movement and resource prediction techniques to smartly forward data towards the right direction at any point in time. In order to cope with the possibly frequent sensor faults, we also adopt a multi-path routing approach which increases the reliability.

Traditional middleware primitives offer very elementary information dissemination mechanisms, which, in the case of a decentralized and dynamic network such as a mobile ad hoc network, do not offer the ability to control the information spreading. Control over information dissemination could instead be very critical especially in terms of lifetime of the network. Gossip-based communication and epidemic-style algorithms, which are based on a store and forward approach, have been proposed to obtain message dissemination with probabilistic guarantees and lower overheads. However, epidemic algorithms have never been used to allow designers to control the spreading of the information depending on the desired reliability and the network structure. In this paper, we present a middleware for ad hoc networking, which uses epidemic-style information dissemination techniques to tune the reliability of the communication in mobile ad hoc networks. The approach is based on recent results of complex networks theory; the novelty of our idea resides in the evaluation and the exploitation of the structure of the underlying network for the automatic tuning of the dissemination process and its use in the design of the API offered by the middleware. We present a detailed analytical model supported by several simulation results

No abstract available.

Delay tolerant and mobile ad hoc networks present considerable challenges to the development of protocols and systems. In particular, the challenge of being able to cope with their variability is an important one: sometimes the rate at which these systems change in terms of context (such as topology, collocation duration and availability and quality of the local resources) is very high and these changes are unpredictable. Knowledge of context could be used to improve the performance of such systems. For example, context information may be extremely useful to make routing decisions. Some recent approaches have successfully exploited context and prediction on future context condition to improve performance, for instance in terms of delivery ratio and delay. In this paper, we present a model of predictability of context information and the design of a generic component implementing it. The component can be used to decide if (or in which measure) context is predictable. The model is based on the analysis of the time series representing the context information. In order to show how the component can be used in practice, we describe its integration in our context-aware adaptive routing (CAR) protocol

The vast majority of mobile ad hoc networking research makes a very large assumption - that communication can only take place between nodes that are simultaneously accessible within the same connected cloud (i.e., that communication is synchronous). In reality, this assumption is likely to be a poor one, particularly for sparsely or irregularly populated environments. We present the context-aware routing (CAR) algorithm. CAR is a novel approach to the provision of asynchronous communication in partially-connected mobile ad hoc networks, based on the intelligent placement of messages. We discuss the details of the algorithm, and then present simulation results demonstrating that it is possible for nodes to exploit context information in making local decisions that lead to good delivery ratios and latencies with small overheads.

Almost all work on mobile ad hoc networks relies on simulations, which, in turn, rely on realistic movement models for their credibility. Since there is a total absence of realistic data in the public domain, synthetic models for movement pattern generation must be used and the most widely used models are currently very simplistic, the focus being ease of implementation rather than soundness of foundation. Whilst it would be preferable to have models that better reflect the movement of real users, it is currently impossible to validate any movement model against real data. However, it is lazy to conclude from this that all models are equally likely to be invalid so any will do.We note that movement is strongly affected by the needs of humans to socialise in one form or another. Fortunately, humans are known to associate in particular ways that can be mathematically modelled, and that are likely to bias their movement patterns. Thus, we propose a new mobility model that is founded on social network theory, because this has empirically been shown to be useful as a means of describing human relationships. In particular, the model allows collections of hosts to be grouped together in a way that is based on social relationships among the individuals. This grouping is only then mapped to a topographical space, with topography biased by the strength of social tie.We discuss the implementation of this mobility model and we evaluate emergent properties of the generated networks. In particular, we show that grouping mechanism strongly influences the probability distribution of the average degree (i.e., the average number of neighbours of a host) in the simulated network.