In recent years, there has been growing interest in leveraging machine learning for homeless service assignment. However, the categorical nature of administrative data recorded for homeless individuals hinders the development of accurate machine learning methods for this task. This work asserts that deriving latent representations of such features, while at the same time leveraging underlying relationships between instances is crucial in algorithmically enhancing the existing assignment decision-making process. Our proposed approach learns temporal and functional relationships between services from historical data, as well as unobserved but relevant relationships between individuals to generate features that significantly improve the prediction of the next service assignment compared to the state-of-the-art.

A burgeoning body of research seeks to develop ever more accurate automated credit evaluation systems. At the same time, reject inference can help financial institutions identify applicants who are mistakenly deemed non–creditworthy, or whose applications are approved even though they end up defaulting. However, both machine learning models and reject inference methods assume perfect decisions, the former for training and the latter for inference. In this work, we challenge this assumption, and explore the feasibility of identifying erroneously rejected (or accepted) loan applications using noisy and counterfactual learning. Experiments on a small benchmark and a large, real– world dataset, demonstrate the effectiveness of our approach.

RDF2Vec has emerged as a popular method for unsupervised feature extraction from RDF graphs. However, RDF2Vec cannot handle large graphs efficiently, due to (i) the size of RDF graphs or intermediate results being prohibitively large, and (ii) the high computational complexity associated with graph walks of increasing breadth and depth, which makes their processing difficult, if not impossible, on a single machine. We address this limitation by introducing SERE, a scalable and distributed framework for unsupervised embeddings computation on large–scale Knowledge Graphs. SERE is open–source, well–documented, and fully integrated into the SparkKG–ML Python library. Our experiments demonstrate that SEREis able to compute embeddings over Knowledge Graphs with millions of edges within hours, and is up to 7 times faster than RDF2Vec even for small Knowledge Graphs, all while achieving comparable accuracy to RDF2Vec in a benchmark classification task.

Homelessness, a long-standing societal problem, appears to be on the rise, fueled in part by the Covid-19 pandemic. Looking at the homelessness system as a network of interconnected services which individuals traverse over time, we seek to shed light on their progression toward securing stable housing. We formalize the concept of stability upon exit and show that regardless of starting conditions, the ultimate goal is either reached quickly or not at all, indicating the importance of addressing the homeless’ needs early on to avoid them “giving up.” To better understand the causes that may contribute to positive outcomes for certain individuals versus others, we computationally analyze their pathways through the network of homeless services. We confirm the intuition that some individuals face more challenges than others based on their initial living conditions and initial placement to homelessness services. At the same time, we discover that simple signals can act as good indicators of individuals at risk of “falling through the cracks.” Being able to predict such outcomes is critical to design assistive technology that can retain individuals who would otherwise falter.

Machine learning models for hierarchical multilabel classification (HMC) typically achieve low accuracy. This is because such models need not only predict multiple labels for each data instance, but also ensure that predicted labels conform to a given hierarchical structure. Existing state-of the-art strategies for HMC decouple the learning process from ensuring that predicted labels reside in a path of the hierarchy, thus inevitably degrading the overall classification accuracy. To address this limitation, we propose a novel loss function, which enables a model to encode both a global perspective of the class hierarchy, as well local class-relationships in adjacent hierarchical levels, to ensure that predictions align with the class hierarchy, both during training and testing. We demonstrate the superiority of the proposed approach against multiple state–of–the–art methods for HMC on 20 real-world datasets.

Existing approaches for multi–label classification are trained offline, missing the opportunity to adapt to new data instances as they become available. To address this gap, an online multi–label classification method was proposed recently, to learn from data instances sequentially. In this work, we focus on multi–label classification tasks, in which the labels are organized in a hierarchy. We formulate online hierarchical multi–labeled classification as an online optimization task that jointly learns individual label predictors and a label threshold, and propose a novel hierarchy constraint to penalize predictions that are inconsistent with the label hierarchy structure. Experimental results on three benchmark datasets show that the proposed approach outperforms online multi–label classification methods, and achieves comparable to, or even better performance than offline hierarchical classification frameworks with respect to hierarchical evaluation metrics.

We introduce a supervised machine learning framework for sequential datum–wise joint feature selection and classification. Our proposed approach sequentially acquires features one at a time during testing until it decides that acquiring more features will not improve label assignment. At that point, and in contrast to prior art, it assigns a label to the example under consideration by selecting between a simple internal and a more powerful external classifier. Easy–to–classify examples are handled by the internal classifier, which assigns labels based on the lowest expected misclassification cost. On the other hand, difficult–to–classify examples are forwarded to the external classifier to be assigned a label based on the acquired features. We demonstrate the performance of the proposed approach compared to existing methods using six publicly available datasets. Experiments indicate that the proposed approach improves accuracy up to 50% with respect to existing sequential methods, while acquiring up to 85% less number of features on average.

Administrative data collected by homeless service providers offer a unique opportunity to understand how homeless individuals navigate the homeless system towards securing stable housing. However, the literature on predictive models in the context of homeless service provision has neglected the sequential nature of services that an individual receives over time. Our work addresses this gap by learning, from administrative data, a Bayesian network, which in turn can be used to accurately predict whether an individual will exit the system, or alternatively, the service she would be assigned to the next time she experiences homelessness. Experimental evaluation shows that the proposed approach outperforms prior art not only at predicting exit, but also the less frequent services (and thus more challenging to predict).

People increasingly use the Internet to make food-related choices, prompting research on food recommendation systems. Recently, works that incorporate nutritional constraints into the recommendation process have been proposed to promote healthier recipes. Ingredient substitution is also used, particularly by people motivated to reduce the intake of a specific nutrient or in order to avoid a particular category of ingredients due for instance to allergies. This study takes a complementary approach towards empowering people to make healthier food choices by simplifying the process of identifying plausible recipe substitutions. To achieve this goal, this work constructs a large-scale network of similar recipes, and analyzes this network to reveal interesting properties that have important implications to the development of food recommendation systems.

On behalf of all the members of the organizing Committee, we are pleased to welcome all of you to IEEE/ACM ASONAM 2022.

This study infers the unobserved underlying network of homeless services from administrative data collected by homeless service providers. Both the structure of the inferred network, and historical observations, are used to identify individuals with similar trajectories so that their next assignments can be predicted. Experimental evaluation shows that the proposed approach performs well not only on predicting exit from the system, or simply guessing high frequency services (as most baselines), but is also successful in less frequent scenarios.

Data quality is of paramount importance in the training process of any machine learning model. Recently proposed methods for noisy learning focus on detecting noisy labeled data instances by using a fixed loss value threshold, and exclude detected noisy data instances in subsequent training steps. However, a predefined, fixed loss value threshold may not always be optimal, and excluding the detected noisy data instances can hurt the size of the training set. In this paper, we propose a new method, NDCC, that automatically selects a loss threshold to identify noisy labeled data instance, and uses counterfactual learning to repair them. To the best of our knowledge, NDCC is the first work to explore the feasibility of using counterfactual learning in the noisy learning domain. We demonstrate the performance of NDCC on Fashion–MNIST and CIFAR–10 datasets under a variety of label noise environments. Experimental results show the superiority of the proposed method compared to the state–of–the–art, especially in the presence of severe label noise.

Most supervised classification methods assume perfect training data, although this is not usually the case in the real–world. Meanwhile, counterfactual data generation approaches have emerged as a way to provide post–hoc explanation of decisions made by classification models. However, such approaches highly rely on the classification model output since different outputs lead to alternative, or even contradicting explanations. This work proposes a plug–and–play framework to learn a robust classification model in the presence of noisy labeled data and provide actionable suggestions for undesirable decisions (e.g., loan application rejection) made by a given classification model. The framework’s generalizability is demonstrated by considering alternative noisy label detection and counterfactual explanation methods, as well as diverse supervised classification models. The framework’s superiority against several baselines is demonstrated using three benchmark datasets.

In this paper, the problem of detecting accidents using speed sensors distributed spatially on a freeway is considered. Due to the significant impact of road accidents on health and development, early and accurate detection of accidents is crucial. To address this issue, a novel Bayesian quickest change detection formulation is introduced, which considers both average detection delay and false alarm rate. The optimum strategy is derived via dynamic programming and shown to compare a recursively computed statistic with a function of false alarm to identify accidents as they happen. Considering that post–accident conditions are typically not known, two methods are proposed that recursively estimate multiple unknown parameters during the accident detection process. Further, four aggregation methods are proposed to improve performance exploiting spatial correlations between sensors. Extensive evaluation results demonstrate improvement up to 65.2% and 87.2% in average detection delay and false alarm rate, respectively, against prior work.

This paper models, for the first time, the homelessness system as a network of interconnected services which individuals traverse over time towards securing stable housing, and formalizes the concept of stability upon exit of the system. A computational analysis of individual-level longitudinal homelessness data shows that the ultimate goal is either reached quickly or not at all, regardless of starting conditions, indicating the importance of addressing the homeless' needs early on.

One of the most challenging machine learning problems is a particular case of classification in which classes are hierarchically structured and data instances can be assigned multiple labels residing in a path of the hierarchy. In this paper, we propose hierarchy–aware multiclass AdaBoost, allowing for the first time weak classifiers in an ensemble learning setting to be trained for hierarchical multiclass classification while incorporating a hierarchy–aware loss function directly into the training process. Experimental results on numerous real–world datasets show that, despite its simplicity, the proposed algorithm outperforms all baselines, arising as the state of the art in hierarchical multiclass classification.

Although data quality is of paramount importance in algorithmic decision–making, most existing methods for supervised classification use training data without ever questioning their fidelity. At the same time, counterfactual explanation approaches widely used for post–hoc explanation of algorithmic decisions may result in unrealistic recommendations when left unconstrained. This work highlights a significant research problem, and introduces a novel framework to improve supervised classification in the presence of untrustworthy data, while offering actionable suggestions when an undesirable decision has been made (e.g., loan application rejection). Evaluation results spanning datasets from different domains demonstrate the superiority of the proposed approach, and its comparative advantage as the percentage of mislabeled instances increases.

The potentially detrimental effects of cyberbullying have led to the development of numerous automated, data-driven approaches, with emphasis on classification accuracy. Cyberbullying, as a form of abusive online behavior, although not well-defined, is a repetitive process, i.e., a sequence of aggressive messages sent from a bully to a victim over a period of time with the intent to harm the victim. Existing work has focused on harassment (i.e., using profanity to classify toxic comments independently) as an indicator of cyberbullying, disregarding the repetitive nature of this harassing process. However, raising a cyberbullying alert immediately after an aggressive comment is detected can lead to a high number of false positives. At the same time, two key practical challenges remain unaddressed: (i) detection timeliness, which is necessary to support victims as early as possible, and (ii) scalability to the staggering rates at which content is generated in online social networks. In this work, we introduce CONcISE , a novel approach for timely and accurate Cyberbullying detectiON in online social media SEssions. CONcISE is a two-stage online approach designed to reduce the time to raise a cyberbullying alert by sequentially examining comments as they become available over time, and minimizing the number of feature evaluations necessary for a decision to be made for each comment. Extensive experiments on a real-world Instagram dataset with users and comments demonstrate the effectiveness, scalability, and timeliness of our approach and its benefits over existing methods. Additional experiments using a Twitter dataset offer evidence in support of the potential generalizability of CONcISE to other social media platforms.

Online feature selection and classification is crucial for time sensitive decision making. Existing work however either assumes that features are independent or produces a fixed number of features for classification. Instead, we propose an optimal framework to perform joint feature selection and classification on-the-fly while relaxing the assumption on feature independence. The effectiveness of the proposed approach is showed by classifying urban issue reports on the SeeClickFix civic engagement platform. A significant reduction in the average number of features used is observed without a drop in the classification accuracy.

Human service organizations (HSOs) operate in an environment considered to be prohibitive of collaboration. To understand how HSOs come together to address the grand challenges associated with meeting human needs, we attempted to automatically construct the network of HSOs based on the information publicly available through each organization's website-the medium that people use to find relevant information to access services. Our analysis of the the complex system of relationships among HSOs in Albany, New York suggests that the network of HSOs in this area exhibits a multipolar structure with few super connectors, and strong relations between organizations that serve similar functions. We quantitatively evaluate the quality of the constructed HSOs' network from Web data based on structured, in-person interviews we conducted with HSOs.

The relationship between local governments and the general public is being redefined by the increasing use of online platforms that enable participatory reporting of non-emergency urban issues, such as potholes and illegal graffiti by concerned citizens to their local authorities. In this work, we study, for the first time, participatory reporting data together with neighborhood-level demographics, socioeconomic indicators, and pedestrian friendliness and transit and bike scores, across multiple neighborhoods in the Capital District of the New York State. Our data-driven approach offers a large-scale, low-cost alternative to traditional survey methods, and provides insights on citizen participation and satisfaction, and public value creation on such platforms. Our findings can be used to guide government service departments to work more closely with each neighborhood to improve the offline and online communication channels through which citizens can report urban issues.

To improve the reliability of content shared on social media, effective strategies for mitigating the diffusion of fake news are increasingly necessary. Traditionally, to counter false belief a competing cascade approach is used. This approach assumes that the opposite belief is already known, and thus, not applicable to newly spreading fake news. Another approach is to block nodes and links of the network to impede the flow of fake news (rumor/influence blocking). However, a more active way to battle the dissemination of fake news is to propagate the corresponding real news, since people who receive the real news in tandem with the fake news are less likely to believe in fake news. Such a setting is especially useful on a messaging platform such as WhatsApp, where the news item flows as a private message and the correction of fake news and its propagation must be performed by the users within the network as they receive it. To achieve this goal, we propose network-based recruitment for active fake news correction (RecANt) to find a set of individuals of a pre-defined size to be incentivized for actively fact-checking and passing on the real news so as to reach the maximum number of nodes in the network. These individuals should be such that they are likely to receive the fake news so that they can test its credibility, and when they propagate the corresponding real news, it reaches a large number of individuals. We prove that RecANt is NP-Hard with a monotone and submodular objective, leading to a polynomial time greedy algorithm (AFC) which provides a (1 - 1/e - ε)-approximation. We further optimize the runtime of AFC by developing a fast graph-pruning heuristic (RAFC) that performs as well as AFC in checking the spread of fake news while reducing the runtime significantly. Simulations on several networks demonstrate that our approach outperforms popular social network centrality measures and state-of-the-art information diffusion algorithm.

In this paper, the problem of detecting freeway accidents in real-time based on speed readings from spatially distributed road sensors of variable accuracy is addressed. To ensure robust decision-making, a novel two-stage approach is proposed. Specifically, in the first stage, each sensor generates decisions using a Bayesian quickest change detection framework. In the second stage, individual sensor decisions are aggregated via an optimal stopping approach that optimizes the tradeoff between the costs of aggregation and misclassification. Evaluation of the proposed two-stage approach on a real-world traffic dataset collected from the I405 freeway that passes through the Los Angeles County demonstrates improvements up to 65.2% and 87.2% in average detection delay and probability of false alarm, respectively, as compared to the state-of-the-art.

Empowering citizens to interact directly with their local governments through civic engagement platforms has emerged as an easy way to resolve urban issues. However, for authorities to manually process reported issues is both impractical and inefficient; accurate, online and near-real-time processing methods are necessary to maintain citizens’ satisfaction with their local governments. Herein, an optimal stopping framework is proposed to process urban issue requests quickly and accurately. The optimal classification and stopping rules are derived, and significant reduction in time-to-decision without sacrificing accuracy is demonstrated on a real-world dataset from SeeClickFix.

The potentially detrimental effects of cyberbullying have led to the development of numerous automated, data-driven approaches, with emphasis on classification accuracy. Cyberbullying, as a form of abusive online behavior, although not well-defined, is a repetitive process, i.e., a sequence of aggressive messages sent from a bully to a victim over a period of time with the intent to harm the victim. Existing work has focused on harassment (i.e., using profanity to classify toxic comments independently) as an indicator of cyberbullying, disregarding the repetitive nature of this harassing process. However, raising a cyberbullying alert immediately after an aggressive comment is detected can lead to a high number of false positives. At the same time, two key practical challenges remain unaddressed: (i) detection timeliness, which is necessary to support victims as early as possible, and (ii) scalability to the staggering rates at which content is generated in online social networks.

Cyberbullying has emerged as a large-scale societal problem that demands accurate methods for its detection in an effort to mitigate its detrimental consequences. While automated, data-driven techniques for analyzing and detecting cyberbullying incidents have been developed, the scalability of existing approaches has largely been ignored. At the same time, the complexities underlying cyberbullying behavior (e.g., social context and changing language) make the automatic identification of “the best subset of features” to use challenging. We address this gap by formulating cyberbullying detection as a sequential hypothesis testing problem. Based on this formulation, we propose a novel algorithm to drastically reduce the number of features used in classification. We demonstrate the utility, scalability and responsiveness of our approach using a real-world dataset from Instagram, the online social media platform with the highest percentage of users reporting experiencing cyberbullying. Our approach improves recall by a staggering 700%, while at the same time reducing the average number of features by up to 99.82% compared to state-of-the-art supervised cyberbullying detection methods, learning approaches that require weak supervision, and traditional offline feature selection and dimensionality reduction techniques.

The increase of motor vehicle accidents over the past decades has made their early and accurate detection crucial not only for saving human lives, but also for decreasing time and energy wasted due to congestion. Unlike existing work that has thus far focused on accident detection, this work recognizes the problem of accident localization as an equally important challenge to be addressed. A novel algorithm is proposed to optimally detect the time of an accident and subsequently estimate its geographic location in near-real-time based on speed sensor readings. Evaluation on a large-scale real-world dataset demonstrates that the proposed approach achieves significant gains compared to state-of-the-art with respect to false alarm rate and average detection delay, while at the same time being capable of pinpointing the exact location of accidents within less than 2 miles on average.

Cyberbullying has emerged as a serious societal and public health problem that demands accurate methods for the detection of cyber-bullying instances in an effort to mitigate the consequences. While techniques to automatically detect cyberbullying incidents have been developed, the scalability and timeliness of existing cyberbullying detection approaches have largely been ignored. We address this gap by formulating cyberbullying detection as a sequential hypothesis testing problem. Based on this formulation, we propose a novel algorithm designed to reduce the time to raise a cyberbullying alert by drastically reducing the number of feature evaluations necessary for a decision to be made. We demonstrate the effectiveness of our approach using a real-world dataset from Twitter, one of the top five networks with the highest percentage of users reporting cyberbullying instances. We show that our approach is highly scalable while not sacrificing accuracy for scalability.

Subgraph isomorphism is a fundamental graph problem with many applications. Due to its NP-Hard nature, subgraph isomorphism in large dynamic graphs is considered as a challenging problem. In this paper, we present a distributed graph pruning algorithm (D-IDS) for dynamic graphs to enable efficient subgraph isomorphism. D-IDS continuously maintains the maximum dual simulation match in a dynamic graph. We develop D-ISI, a distributed incremental algorithm for subgraph isomorphism that utilizes D-IDS. We evaluated our algorithms on a commodity cluster in Amazon EC2 using real world graph datasets. Our evaluation results show that the graph pruning technique is highly effective on graphs with small diameter where it achieves over 60% reduction in graph size.

In this paper, we propose a novel design for large-scale graph processing on FPGA. Our design uses large external memory for storing massive graph data and FPGA for acceleration, and leverages edge-centric computing principles. We propose a data layout which optimizes the external memory performance and leads to an efficient memory activation schedule to reduce on-chip memory power consumption. Further, we develop a parallel architecture on FPGA which can saturate the external memory bandwidth and concurrently process multiple input data to increase throughput. We use our design to accelerate several classic graph algorithms, including single-source shortest path, weakly connected component, and minimum spanning tree. Experimental results show that for all the considered graph algorithms, our design achieves high throughput of over 600 million traversed edges per second (MTEPS) and high energy-efficiency of over 30 MTEPS/W. Compared with a baseline design, our optimizations result in over 3.6× throughput and 5.8× energy-efficiency improvements, respectively. Our design achieves 32% throughput improvement when compared with state-of-the-art FPGA designs, and up to 7.8× speedup when compared with state-of-the-art multi-core implementation.

Prosumers or proactive consumers are steadily on the rise in emerging Smart Grid systems. These consumers, apart from their traditonal role of using energy from the grid, also are actively involved in individually transferring stored energy from renewable sources such as wind and solar, to the grid. The large-scale integration of renewable generation in the emerging grid will re-define ways of meeting consumer energy demands, and more importantly drive greener and cost-effective utility operations. In this paper, we investigate the problem of matching consumer demand with the grid supply in real-time, and in the presence of renewables. We formulate this problem as a stochastic optimization problem and propose MATCH, a fast distributed real-time algorithm that accounts for the uncertainties in (i) renewable generation, (ii) the latter's transmission through the grid network, (iii) loads, and (iv) energy prices, and balances power in the Smart Grid at all times. MATCH is based on the Lyapunov stochastic optimization framework and scales to localities with a large number of networked renewable generation sources. We validate the efficacy of MATCH through experiments conducted using data modelled on proprietary data obtained from two public utilities. As part of the main results of this work, we show that (a) MATCH outputs unique approximate-optimal grid parameter configuration vectors in real-time that ensure perennial supplydemand balance in the grid at a minimum cost, and (b) mesh transmission network topologies lead to better MATCH outputs when compared to other existing transmission network topologies.

The widespread monitoring of electricity consumption due to increasingly pervasive deployment of networked sensors in urban environments has resulted in an unprecedentedly large volume of data being collected. Particularly, with the emerging Smart Grid technologies becoming more ubiquitous, real-time and online analytics for discovering the underlying structure of increasing-dimensional (w.r.t. time) consumer time series data are crucial to convert the massive amount of fine-grained energy information gathered from residential smart meters into appropriate demand response (DR) insights. In this paper we propose READER and OPTIC, that are real-time and online algorithmic pre-processing frameworks respectively, for effective DR in the Smart Grid. READER (OPTIC) helps discover underlying structure from increasing-dimensional consumer consumption time series data in aprovably optimalreal-time (online) fashion. READER (OPTIC) catalyzes the efficacy of DR programs by systematically and efficiently managing the energy consumption data deluge, at the same time capturing in real-time (online), specific behavior, i.e., households or time instants with similar consumption patterns. The primary feature of READER (OPTIC) is a real-time (online)randomized approximation algorithmfor grouping consumers based on their electricity consumption time series data, and provides two crucial benefits: (i) time efficiently tackles high volume, increasing-dimensional time series data and (ii) provides provable worst case grouping performance guarantees. We validate the grouping and DR efficacy of READER and OPTIC via extensive experiments conducted on both, a USC microgrid dataset as well as a synthetically generated dataset.

Applications in sustainability domains such as in energy, transportation, and natural resource and environment monitoring, increasingly use sensors for collecting data and sending it back to centrally located processing nodes. While data can usually be collected by the sensors at a very high speed, in many cases, it can not be sent back to central nodes at a frequency that is required for fast and real-time modeling and decision-making. This may be due to physical limitations of the transmission networks, or due to consumers limiting frequent transmission of data from sensors located at their premises for security and privacy concerns. We propose a novel solution to the problem of making short term predictions in absence of real-time data from sensors. A key implication of our work is that by using real-time data from only a small subset of influential sensors, we are able to make predictions for all sen- sors. We evaluated our approach with a large real-world electricity consumption data collected from smart meters in Los Angeles and the results show that between prediction horizons of 2 to 8 hours, despite lack of real time data, our influence model outperforms the baseline model that uses real-time data. Also, when using partial real-time data from only ≈ 7% influential smart meters, we witness prediction error increase by only ≈ 0.5% over the baseline, thus demonstrating the usefulness of our method for practical scenarios.

Often in marketing, political campaigns and social media, two competing products or opinions propagate over a social network. Studying social influence in such competing cascades scenarios enables building effective strategies for maximizing the propagation of one process by targeting the most "influential" nodes in the network. The majority of prior work however, focuses on unsigned networks where individuals adopt the opinion of their neighbors with certain probability. In real life, relationships between individuals can be positive (e.g., friend of relationship) or negative (e.g. connection between "foes"). According to social theory, people tend to have similar opinions to their friends but opposite of their foes. In this work, we study the problem of competing cascades on signed networks, which has been relatively unexplored. Particularly, we study the progressive propagation of two competing cascades in a signed network under the Independent Cascade Model, and provide an approximate analytical solution to compute the probability of infection of a node at any given time. We leverage our analytical solution to the problem of competing cascades in signed networks to develop a heuristic for the influence maximization problem. Unlike prior work, we allow the seed-set to be initialized with populations of both cascades with the end goal of maximizing the spread of one cascade. We validate our approach on several large-scale real-world and synthetic networks. Our experiments demonstrate that our influence maximization heuristic significantly outperforms state-of-the-art methods, particularly when the network is dominated by distrust relationships.

The pervasive deployment of advanced sensing infrastructure in Cyber-Physical systems, such as the Smart Grid, has resulted in an unprecedented data explosion. Such data exhibit both large volumes and high velocity characteristics, two of the three pillars of Big Data, and have a time-series notion as datasets in this context typically consist of successive measurements made over a time interval. Time-series data can be valuable for data mining and analytics tasks such as identifying the "right" customers among a diverse population, to target for Demand Response programs. However, time series are challenging to mine due to their high dimensionality. In this paper, we motivate this problem using a real application from the smart grid domain. We explore novel representations of time-series data for BigData analytics, and propose a clustering technique for determining natural segmentation of customers and identification of temporal consumption patterns. Our method is generizable to large-scale, real-world scenarios, without making any assumptions about the data. We evaluate our technique using real datasets from smart meters, totaling ∼ 18,200,000 data points, and show the efficacy of our technique in efficiency detecting the number of optimal number of clusters.

Existing Big Data streams coming from social and other connected sensor networks exhibit intrinsic inter-dependency enabling unique challenges to scalable graph analytics. Data from these graphs is usually collected in different geographically located data servers making it suitable for distributed processing on clouds. While numerous solutions for large scale static graph analysis have been proposed, addressing in real-time the dynamics of social interactions requires novel approaches that leverage incremental stream processing and graph analytics on elastic clouds. We propose a scalable solution based on our stream processing engine, Floe, on top of which we perform real-time data processing and graph updates to enable low latency graph analytics on large evolving social networks. We demonstrate the platform on a large Twitter data set by performing several fast graph and non-graph analytics to extract in real-time the top k influential nodes, with different metrics, during key events such as the US NFL playoffs. This information allows advertisers to maximize their exposure to the public by always targeting the continuously changing set of most influential nodes. Its applicability spans multiple domains including surveillance, counter-terrorism, or disease spread monitoring. The evaluation will be performed on a combination our local cluster of 16 eight-core nodes running Eucalyptus fabric and 100s of virtual machines on the Amazon AWS public cloud. We will showcase the low latency in detecting changes in the graph under variable data streams, and also the efficiency of the platform to utilize resources and to elastically scale to meet demand.

Understanding how information flows in online social networks is of great importance. It is generally difficult to obtain accurate prediction results of cascades over such networks, therefore a variety of diffusion models have been proposed in the literature to simulate diffusion processes instead. We argue that such models require extensive simulation results to produce good estimates of future spreads. In this work, we take a complimentary approach. We present a generalized, analytical model of influence in social networks that captures social influence at various levels of granularity, ranging from pairwise influence, to local neighborhood, to the general population, and external events, therefore capturing the complex dynamics of human behavior. We demonstrate that our model can integrate a variety of diffusion models. Particularly, we show that commonly used diffusion models in social networks can be reduced to special cases of our model, by carefully defining their parameters. Our goal is to provide a closed-form expression to approximate the probability of infection for every node in an arbitrary, directed network at any time t. We quantitatively evaluate the approximation quality of our analytical solution as compared to numerous popular diffusion models on a real-world dataset and a series of synthetic graphs.

Big data applications such as in smart electric grids, transportation, and remote environment monitoring involve geographically dispersed sensors that periodically send back information to central nodes. In many cases, data from sensors is not available at central nodes at a frequency that is required for real-time modeling and decision-making. This may be due to physical limitations of the transmission networks, or due to consumers limiting frequent transmission of data from sensors located at their premises for security and privacy concerns. Such scenarios lead to partial data problem and raise the issue of data veracity in big data applications. We describe a novel solution to the problem of making short term predictions (up to a few hours ahead) in absence of real-time data from sensors in Smart Grid. A key implication of our work is that by using real-time data from only a small subset of influential sensors, we are able to make predictions for all sensors. We thus reduce the communication complexity involved in transmitting sensory data in Smart Grids. We use real-world electricity consumption data from smart meters to empirically demonstrate the usefulness of our method. Our dataset consists of data collected at 15-min intervals from 170 smart meters in the USC Microgrid for 7 years, totaling 41,697,600 data points.

Smart grids are becoming popular with the advent of sophisticated smart meters. They allow utilities to optimize energy consumption during peak hours by applying various demand response techniques including voluntary curtailment, direct control and price incentives. To sustain the curtailment over long periods of time of up to several hours utilities need to make fast and accurate consumption predictions on a large set of customers based on a continuous flow of real time data and huge historical data sets. Given the numerous consumption patterns customers exhibit, different prediction methods need to be used to reduce the prediction error. The straightforward approach of testing each customer against every method is unfeasible in this large volume and high velocity environment. To this aim, we propose a neural network based approach for automatically selecting the best prediction method per customer by relying only on a small subset of customers. We also introduce two historical averaging methods for consumption prediction that take advantage of the variability of the data and continuously update the results based on a sliding window technique. We show that once trained, the proposed neural network does not require frequent retraining, ensuring its applicability in online scenarios such as the sustainable demand response.

Popular social networking sites have revolutionized the way people interact on the Web, enabling rapid information dissemination and search. In an enterprise, understanding how information flows within and between organizational levels and business units is of great importance. Despite numerous studies in information diffusion in online social networks, little is known about factors that affect the dynamics of technological adoption at the workplace. Here, we address this problem, by examining the impact of organizational hierarchy in adopting new technologies in the enterprise. Our study suggests that middle-level managers are more successful in influencing employees into adopting a new microblogging service. Further, we reveal two distinct patterns of peer pressure, based on which employees are not only more likely to adopt the service, but the rate at which they do so quickens as the popularity of the new technology increases. We integrate our findings into two intuitive, realistic agent-based computational models that capture the dynamics of adoption at both microscopic and macroscopic levels. We evaluate our models in a real-world dataset we collected from a multinational Fortune 500 company. Prediction results show that our models provide great improvements over commonly used diffusion models. Our findings provide significant insights to managers seeking to realize the dynamics of adoption of new technologies in their company, and could assist in designing better strategies for rapid and efficient technology adoption and information dissemination at the workplace.

To enhance human resource management and personalized information acquisition, employee ontology is used to model business concepts and relations between them for enterprises. In this paper, we propose an employee ontology that integrates user static properties from formal structures with dynamic interests and expertise extracted from informal communication signals. We mine user's interests at both personal and professional level from informal interactions on communication platforms at the workplace. We show how complex semantic queries enable granular analysis. At the microscopic level, enterprises can utilize the results to better understand how their employees work together to complete tasks or produce innovative ideas, identify experts and influential individuals. At the macroscopic level, conclusions can be drawn, among others, about collective behavior and expertise in varying granularities (i.e. single employee to the company as a whole).

Social networks have become a popular medium for people to communicate and distribute ideas, content, news, and advertisements. Social content annotation has naturally emerged as a method of categorization and filtering of online information. The unrestricted vocabulary users choose from to annotate content has often lead to an explosion of the size of space in which search is performed. In this article, we propose latent topic models as a principled way of reducing the dimensionality of such data and capturing the dynamics of collaborative annotation process. We propose three generative processes to model latent user tastes with respect to resources they annotate with metadata. We show that latent user interests combined with social clues from the immediate neighborhood of users can significantly improve social link prediction in the online music social media site Last.fm. Most link prediction methods suffer from the high class imbalance problem, resulting in low precision and/or recall. In contrast, our proposed classification schemes for social link recommendation achieve high precision and recall with respect to not only the dominant class (nonexistence of a link), but also with respect to sparse positive instances, which are the most vital in social tie prediction.

Popular social networking sites have revolutionized the way people interact on the Web. Researchers have studied social networks from numerous perspectives, mostly focusing on publicly available social networks and microblogging sites. Enterprises however have recently being adopting and utilizing microblogging services as part of their day to day operations. The goal of this paper is to study the topological properties of a corporate microblogging service, its dynamics and characteristics. Through an extensive analysis of enterprise microblogging data, we provide insights on the structural properties of the extracted network of directed messages sent between users of a corporate microblogging service, as well as the lexical and topical alignment of users. We compare our results to traditional, general purpose, online social networks and discuss the implications of our findings. To the best of our knowledge, this work is the first quantitative study of an enterprise microblogging service, its usage characteristics, and its derived social network based on replies between users.

Data availability in online social networks as well as the business world has lately not been an issue. Vast amounts of data are being generated by social networking users in the form of informal interactions. What has been an issue, is the transformation of data into useful information, that in time and with appropriate processing becomes knowledge. In this paper we examine knowledge generation under informal social communications, based on semantically enriched user-generated data and associated metadata. We dynamically capture users' interests and expertise using such semantically enriched content. Knowledge networks of users emerge, exhibiting collective intelligence. To capture such collective knowledge, we propose a novel knowledge base paradigm, which seamlessly integrates information from multiple platforms and facilitates knowledge extraction, mining, discovery and inferencing. Using semantically enriched user profiles, we compute semantic similarity between users and content in a joint semantic space, driving numerous applications.