Conference Paper

Complementing Amber Alert: Increasing the social sensors' effectiveness through focused communication channels

Authors:
To read the full-text of this research, you can request a copy directly from the authors.

Abstract

The general idea of the AMBER/Child Alert System is that by broadcasting and distributing information about a missing child to the community, the public’s involvement can trigger critical feedback that would have otherwise been ignored. This feedback, in several cases, can be proved decisive in finding the missing child. Despite the efforts at country and European level to effectively address the issue of missing children, a number of key challenges remain open, including lack of location-focused distribution of alerts, insufficient capture and diffusion of information, and lack of a mechanism that uses and merges all available sources of information. The aim of this paper is to present a novel approach for handling such challenges through a data analytics platform and a mobile application available to all citizens. Using the active research fields of human mobility pattern analysis and machine learning, we show that missing children investigations, as well as search and rescue operations, can be actively supported and enhanced when multiple data sources are combined and analyzed.

No full-text available

Request Full-text Paper PDF

To read the full-text of this research,
you can request a copy directly from the authors.

... Hence, if a child goes missing, any new information on the child that becomes available, such as the place and time last seen, is introduced in the platform by the appointed case manager. The platform then enhances this collected information by applying automatic profiling and prediction methods, the preliminary findings of which can be found in a different publication (Michalitsi-Psarrou et al., 2019). Their purpose is twofold: on the one hand, to create a case profiling and to associate it with similar past cases, and on the other hand, to identify and evaluate potential Points of Interest (POIs) to search for the child. ...
Article
Full-text available
The phenomenon of missing children is complex, further complicated by the specific circumstances of missing unaccompanied migrant minors. Owing to the (often forced) migration, these children have moved through different countries with diverse legislation and work practices. The international nature of these cases leads to confusion about the responsibility of different actors. Additionally, for these cases, little data are available. This article critically assesses current work practices in the EU. It also introduces a new practical solution based on empirical data from 26 international expert interviews, proposing a new alert system for missing children cases to improve the efficiency in responding to them and the international communication between stakeholders to improve the situation of missing unaccompanied migrant minors. The solution is currently in use by three organisations and has already been used in more than 85 real-life cases. It is concluded that it holds the potential to connect actors in a new, efficient way and prevent children, and unaccompanied migrant minors particularly, from falling off the grid. It is also highlighted that the situation of unaccompanied migrant minors is highly disadvantaged, and new, homogenous legislation among the EU member states that does not discriminate against the rights of migrant minors is imperative. New research should also actively involve them to better grasp their situation before and during their disappearance.
... We focus our solution on a specific problem, the missing children issue, where a mobile application for the general public is developed to involve citizens and volunteers in missing children investigations [17]. The application broadcasts mobile alerts, sharing public information about an active case to all users that have the application installed on their mobile phones. ...
Article
Full-text available
Citizen sensing applications need to have a number of users defined that ensures their effectiveness. This is not a straightforward task because neither the relationship between the size of the userbase or its effectiveness is easily quantified, nor is it clear which threshold for the number of users would make the application ‘effective’. This paper presents an approach for estimating the number of users needed for location-based crowdsourcing applications to work successfully, depending on the use case, the circumstances, and the criteria of success. It circumvents various issues, ethical or practical, in performing real-world controlled experiments and tackles this challenge by developing an agent-based modelling and simulation framework. This framework is tested on a specific scenario, that of missing children and the search for them. The search is performed with the contribution of citizens being made aware of the disappearance through a mobile application. The result produces an easily reconfigurable testbed for the effectiveness of citizen sensing mobile applications, allowing the study of the marginal utility of new users of the application. The resulting framework aims to be the digital twin of a real urban scenario, and it has been designed to be easily adapted and support decisions on the feasibility, evaluation, and targeting of the deployment of spatial crowdsourcing applications.
... To accomplish that goal, system theories, such as Activity Theory and Collective Behaviour Theory, are analysed along with methods and scientific fields stemming from the computer science, such as Social Network Analysis and Machine Learning for modelling human behaviour, to construct reliable activity and behaviour profiles of children from both a technological and a sociological perspective. Profiling information of the missing child is then combined with open data, like geographic and transportation data, along with insights and patterns revealed from pattern matching of similar past cases, to deduce potential Points of Interest (POIs) and consequently routes and directions that the investigation should follow, in an evidence-based and scientifically-sound manner, the preliminary findings of which approach can be found in (Michalitsi-Psarrou et al. 2019). ...
Conference Paper
Full-text available
The plight of missing children is particularly strenuous and sensitive for society at local, national and European levels, cutting across class, race, and age. A quarter million cases of missing children is reported in the EU annually, which are either parental abductions, stranger abductions, runaways, missing unaccompanied migrant minors, and generally lost, injured, or otherwise missing children. The problem of missing children is a complex, multi-faceted phenomenon, comprising legal, psychological and sociological aspects, which are complicated further due to the strong emotions from the close environment of the missing child. This paper presents the challenges missing children investigation and rescue currently faces, and proposes a solution that uses ICT, advanced analytics and collective intelligence, to achieve more rapid and effective resolutions. The proposed methodology leverages the untapped potential of open, social, and linked data to augment the background information of missing children, through multi-layer-personal, psychological, social and activity-profiling and predictive analytics, respecting and protecting privacy, and personal data. Using location-based mobile notifications that spread using geo-fencing, citizens close to the place a missing child was last seen or is more probable to be found become "social sensors" for the investigation, contributing and validating potential pieces of evidence. Through the EU-funded project ChildRescue, the proposed solution is currently at the last phase of its development and aims to be adopted by different voluntary organisations, according to their needs and the readiness of their systems and processes. The project's results are now piloted in missing children cases by organisations responsible for the Amber Alert, and the 116 000 pan-European hotline, as well as unaccompanied minors' cases supported by the Hellenic Red Cross. The resulting collaboration platform and mobile applications will be publicly launched in 2020.
Article
Full-text available
Human mobility patterns reflect many aspects of life, from the global spread of infectious diseases to urban planning and daily commute patterns. In recent years, the prevalence of positioning methods and technologies, such as the global positioning system, cellular radio tower geo-positioning, and WiFi positioning systems, has driven efforts to collect human mobility data and to mine patterns of interest within these data in order to promote the development of location-based services and applications. The efforts to mine significant patterns within large-scale, high-dimensional mobility data have solicited use of advanced analysis techniques, usually based on machine learning methods, and therefore, in this paper, we survey and assess different approaches and models that analyze and learn human mobility patterns using mainly machine learning methods. We categorize these approaches and models in a taxonomy based on their positioning characteristics, the scale of analysis, the properties of the modeling approach, and the class of applications they can serve. We find that these applications can be categorized into three classes: user modeling, place modeling, and trajectory modeling, each class with its characteristics. Finally, we analyze the short-term trends and future challenges of human mobility analysis.
Article
Full-text available
The recent availability of large-scale call detail record data has substantially improved our ability of quantifying human travel patterns with broad applications in epidemiology. Notwithstanding a number of successful case studies, previous works have shown that using different mobility data sources, such as mobile phone data or census surveys, to parametrize infectious disease models can generate divergent outcomes. Thus, it remains unclear to what extent epidemic modelling results may vary when using different proxies for human movements. Here, we systematically compare 658 000 simulated outbreaks generated with a spatially structured epidemic model based on two different human mobility networks: a commuting network of France extracted from mobile phone data and another extracted from a census survey. We compare epidemic patterns originating from all the 329 possible outbreak seed locations and identify the structural network properties of the seeding nodes that best predict spatial and temporal epidemic patterns to be alike. We find that similarity of simulated epidemics is significantly correlated to connectivity, traffic and population size of the seeding nodes, suggesting that the adequacy of mobile phone data for infectious disease models becomes higher when epidemics spread between highly connected and heavily populated locations, such as large urban areas.
Article
Full-text available
Location recommendation is an important feature of social network applications and location-based services. Most existing studies focus on developing one single method or model for all users. By analyzing data from two real location-based social networks (Foursquare and Gowalla), in this paper we reveal that the decisions of users on place visits depend on multiple factors, and different users may be affected differently by these factors. We design a location recommendation framework that combines results from various recommenders that consider different factors. Our framework estimates, for each individual user, the underlying influence of each factor to her. Based on the estimation, we aggregate suggestions from different recommenders to derive personalized recommendations. Experiments on Foursquare and Gowalla show that our proposed method outperforms the state-of-the-art methods on location recommendation.
Article
Full-text available
A variety of approaches have been recently proposed to automatically infer users’ personality from their user generated content in social media. Approaches differ in terms of the machine learning algorithms and the feature sets used, type of utilized footprint, and the social media environment used to collect the data. In this paper, we perform a comparative analysis of state-of-the-art computational personality recognition methods on a varied set of social media ground truth data from Facebook, Twitter and YouTube. We answer three questions: (1) Should personality prediction be treated as a multi-label prediction task (i.e., all personality traits of a given user are predicted at once), or should each trait be identified separately? (2) Which predictive features work well across different on-line environments? and (3) What is the decay in accuracy when porting models trained in one social media environment to another?
Article
Full-text available
Natural disasters pose serious threats to large urban areas, therefore understanding and predicting human movements is critical for evaluating a population's vulnerability and resilience and developing plans for disaster evacuation, response and relief. However, only limited research has been conducted into the effect of natural disasters on human mobility. This study examines how natural disasters influence human mobility patterns in urban populations using individuals' movement data collected from Twitter. We selected fifteen destructive cases across five types of natural disaster and analyzed the human movement data before, during, and after each event, comparing the perturbed and steady state movement data. The results suggest that the power-law can describe human mobility in most cases and that human mobility patterns observed in steady states are often correlated with those in perturbed states, highlighting their inherent resilience. However, the quantitative analysis shows that this resilience has its limits and can fail in more powerful natural disasters. The findings from this study will deepen our understanding of the interaction between urban dwellers and civil infrastructure, improve our ability to predict human movement patterns during natural disasters, and facilitate contingency planning by policymakers.
Article
Full-text available
The knowledge of the transportation mode used by humans e.g. bicycle, on foot, car and train is critical for travel behaviour research, transport planning and traffic management. Nowadays, new technologies such as the Global Positioning System have replaced traditional survey methods paper diaries, telephone because they are more accurate and problems such as under reporting are avoided. However, although the movement data collected timestamped positions in digital form have generally high accuracy, they do not contain the transportation mode. We present in this article a new method for segmenting movement data into single-mode segments and for classifying them according to the transportation mode used. Our fully automatic method differs from previous attempts for five reasons: 1 it relies on fuzzy concepts found in expert systems, that is membership functions and certainty factors; 2 it uses OpenStreetMap data to help the segmentation and classification process; 3 we can distinguish between 10 transportation modes including between tram, bus and car and propose a hierarchy; 4 it handles data with signal shortages and noise, and other real-life situations; 5 in our implementation, there is a separation between the reasoning and the knowledge, so that users can easily modify the parameters used and add new transportation modes. We have implemented the method and tested it with a 17-million point data set collected in the Netherlands and elsewhere in Europe. The accuracy of the classification with the developed prototype, determined with the comparison of the classified results with the reference data derived from manual classification, is 91.6%.
Conference Paper
Full-text available
Although online recommendation systems such as recommendation of movies or music have been systematically studied in the past decade, location recommendation in Location Based Social Networks (LBSNs) is not well investigated yet. In LBSNs, users can check in and leave tips commenting on a venue. These two heterogeneous data sources both describe users' preference of venues. However, in current research work, only users' check-in behavior is considered in users' location preference model, users' tips on venues are seldom investigated yet. Moreover, while existing work mainly considers social influence in recommendation, we argue that considering venue similarity can further improve the recommendation performance. In this research, we ameliorate location recommendation by enhancing not only the user location preference model but also recommendation algorithm. First, we propose a hybrid user location preference model by combining the preference extracted from check-ins and text-based tips which are processed using sentiment analysis techniques. Second, we develop a location based social matrix factorization algorithm that takes both user social influence and venue similarity influence into account in location recommendation. Using two datasets extracted from the location based social networks Foursquare, experiment results demonstrate that the proposed hybrid preference model can better characterize user preference by maintaining the preference consistency, and the proposed algorithm outperforms the state-of-the-art methods.
Conference Paper
Full-text available
The popularity of location-based social networks provide us with a new platform to understand users' preferences based on their location histories. In this paper, we present a location-based and preference-aware recommender system that offers a particular user a set of venues (such as restaurants) within a geospatial range with the consideration of both: 1) User preferences, which are automatically learned from her location history and 2) Social opinions, which are mined from the location histories of the local experts. This recommender system can facilitate people's travel not only near their living areas but also to a city that is new to them. As a user can only visit a limited number of locations, the user-locations matrix is very sparse, leading to a big challenge to traditional collaborative filtering-based location recommender systems. The problem becomes even more challenging when people travel to a new city. To this end, we propose a novel location recommender system, which consists of two main parts: offline modeling and online recommendation. The offline modeling part models each individual's personal preferences with a weighted category hierarchy (WCH) and infers the expertise of each user in a city with respect to different category of locations according to their location histories using an iterative learning model. The online recommendation part selects candidate local experts in a geospatial range that matches the user's preferences using a preference-aware candidate selection algorithm and then infers a score of the candidate locations based on the opinions of the selected local experts. Finally, the top-k ranked locations are returned as the recommendations for the user. We evaluated our system with a large-scale real dataset collected from Foursquare. The results confirm that our method offers more effective recommendations than baselines, while having a good efficiency of providing location recommendations.
Conference Paper
Full-text available
Major depression constitutes a serious challenge in personal and public health. Tens of millions of people each year suffer from depression and only a fraction receives adequate treatment. We explore the potential to use social media to detect and diagnose major depressive disorder in individuals. We first employ crowdsourcing to compile a set of Twitter users who report being diagnosed with clinical depression, based on a standard psychometric instrument. Through their social media postings over a year preceding the onset of depression, we measure behavioral attributes relating to social engagement, emotion, language and linguistic styles, ego network, and mentions of antidepressant medications. We leverage these behavioral cues, to build a statistical classifier that provides estimates of the risk of depression, before the reported onset. We find that social media contains useful signals for characterizing the onset of depression in individuals, as measured through decrease in social activity, raised negative affect, highly clustered egonetworks, heightened relational and medicinal concerns, and greater expression of religious involvement. We believe our findings and methods may be useful in developing tools for identifying the onset of major depression, for use by healthcare agencies; or on behalf of individuals, enabling those suffering from depression to be more proactive about their mental health. Copyright © 2013, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved.
Conference Paper
Full-text available
We compare neural network techniques to rule-based systems to predict outcomes for missing persons cases, finding that neural networks successfully predict outcomes for 93% of cases, a significant improvement over accuracy achieved through the use of rule-based systems. Further, a method for non-linear dimensionality reduction is used to identify whether the data lies on a low dimensional manifold embedded in a high dimensional space. Results show an underlying dimensionality of between 5 and 8 is likely, however, the decision surface is complex and non-contiguous.
Article
Full-text available
Social mobilization, the ability to mobilize large numbers of people via social networks to achieve highly distributed tasks, has received significant attention in recent times. This growing capability, facilitated by modern communication technology, is highly relevant to endeavors which require the search for individuals that possess rare information or skills, such as finding medical doctors during disasters, or searching for missing people. An open question remains, as to whether in time-critical situations, people are able to recruit in a targeted manner, or whether they resort to so-called blind search, recruiting as many acquaintances as possible via broadcast communication. To explore this question, we examine data from our recent success in the U.S. State Department's Tag Challenge, which required locating and photographing 5 target persons in 5 different cities in the United States and Europe - in under 12 hours - based only on a single mug-shot. We find that people are able to consistently route information in a targeted fashion even under increasing time pressure. We derive an analytical model for social-media fueled global mobilization and use it to quantify the extent to which people were targeting their peers during recruitment. Our model estimates that approximately 1 in 3 messages were of targeted fashion during the most time-sensitive period of the challenge. This is a novel observation at such short temporal scales, and calls for opportunities for devising viral incentive schemes that provide distance or time-sensitive rewards to approach the target geography more rapidly. This observation of '12 hours of separation' between individuals has applications in multiple areas from emergency preparedness, to political mobilization.
Article
Full-text available
Understanding the patterns underlying human mobility is of an essential importance to applications like recommender systems. In this paper we investigate the behaviour of around 10,000 frequent users of Location Based Social Networks (LBSNs) making use of their full movement patterns. We analyse the metadata associated with the whereabouts of the users, with emphasis on the type of places and their evolution over time. We uncover patterns across different temporal scales for venue category usage. Then, focusing on individual users, we apply this knowledge in two tasks: 1) clustering users based on their behaviour and 2) predicting users' future movements. By this, we demonstrate both qualitatively and quantitatively that incorporating temporal regularities is beneficial for making better sense of user behaviour.
Article
Full-text available
The AMBER Alert system enjoys widespread public support. Yet evidence suggests that the system may be ineffective and have unintended consequences. Because AMBER Alerts are illusory means of controlling crime, they may be conceptualized as “crime control theater” (CCT) and thus are indicative of a problematic social tendency to address complex issues through simple solutions. This article utilizes principles of social cognition, attitudes, social norms, and symbolic interaction to predict that the AMBER Alert system will persevere despite its disadvantages. This analysis can help account for the popularity of other forms of CCT. It also highlights the need for future research aimed at elucidating the processes responsible for the acceptance of policies that are mere theater.
Article
Full-text available
Intense interest in disturbing child abductions by the mass media, public safety organizations, and the public has helped sustain a socially constructed mythology and sporadic “moral panic” about the presumed pervasiveness of this threat to children. The result has often been reactionary “memorial” legislation enacted in response to sensational cases. A recent example is the America's Missing Broadcast Emergency Response (AMBER) Alert system, which is designed to interrupt serious child kidnappings in progress by soliciting citizen tips to help officials quickly rescue victims. Drawing on available empirical evidence and theoretical considerations, the authors contend that AMBER Alert has not achieved and probably cannot achieve the ambitious goals that inspired its creation. In fact, AMBER Alert is arguably an example of what could be called crime control theater. It is a socially constructed “solution” to a socially constructed problem, enabling public officials to symbolically address an essentially intractable threat. Despite laudable intentions, AMBER Alert exemplifies how crime control theater can create unintended problems, such as public backlash when the theatrical policy fails and a distorted public discourse about the nature of crime. Considerations for the future of AMBER Alert in particular, and the concept of crime control theater in general, are discussed.
Article
Full-text available
The modeling of human mobility is adopting new directions due to the increasing availability of big data sources from human activity. These sources enclose digital information about daily visited locations of a large number of individuals. Examples of these data include: mobile phone calls, credit card transactions, bank notes dispersal, check-ins in internet applications, among several others. In this study, we consider the data obtained from smart subway fare card transactions to characterize and model urban mobility patterns. We present a simple mobility model for predicting peoples’ visited locations using the popularity of places in the city as an interaction parameter between different individuals. This ingredient is sufficient to reproduce several characteristics of the observed travel behavior such as: the number of trips between different locations in the city, the exploration of new places and the frequency of individual visits of a particular location. Moreover, we indicate the limitations of the proposed model and discuss open questions in the current state of the art statistical models of human mobility.
Article
Full-text available
Human movements contribute to the transmission of malaria on spatial scales that exceed the limits of mosquito dispersal. Identifying the sources and sinks of imported infections due to human travel and locating high-risk sites of parasite importation could greatly improve malaria control programs. Here, we use spatially explicit mobile phone data and malaria prevalence information from Kenya to identify the dynamics of human carriers that drive parasite importation between regions. Our analysis identifies importation routes that contribute to malaria epidemiology on regional spatial scales.
Article
Full-text available
We investigated how well adults could recognize the faces of children when they differed in appearance from photographs shown in an alert. College students in three studies saw a mock AMBER Alert while watching a television show. The children appeared either well-groomed with positive affect (as in a school photograph) or disheveled with poor affect (as abducted children might appear). Recognition accuracy and confidence were significantly lower when the faces differed in appearance from the alert displayed during the television show. Thus, AMBER Alerts may be more effective if they are accompanied by more than one type of photograph of a missing child, particularly if a photograph is shown in which the child does not appear well-groomed and happy. KeywordsMissing children–Face recognition–Eyewitness accuracy–Memory for faces–AMBER Alerts
Chapter
Full-text available
This paper presents the results of analysis to evaluate the effectiveness of data mining techniques to predict the outcome for missing persons cases. A rulebased system is used to derive augmentations to supplement police officer intuition. Results indicate that rule-based systems can effectively identify variables for prediction.
Conference Paper
Full-text available
Simulating human mobility is important in mobile networks because many mobile devices are either attached to or controlled by humans and it is very hard to deploy real mobile networks whose size is controllably scalable for performance evaluation. Lately various measurement studies of human walk traces have discovered several significant statistical patterns of human mobility. Namely these include truncated power-law distributions of flights, pause-times and inter-contact times, fractal way-points, and heterogeneously defined areas of individual mobility. Unfortunately, none of existing mobility models effectively captures all of these features. This paper presents a new mobility model called SLAW (self-similar least action walk) that can produce synthetic walk traces containing all these features. This is by far the first such model. Our performance study using using SLAW generated traces indicates that SLAW is effective in representing social contexts present among people sharing common interests or those in a single community such as university campus, companies and theme parks. The social contexts are typically common gathering places where most people visit during their daily lives such as student unions, dormitory, street malls and restaurants. SLAW expresses the mobility patterns involving these contexts by fractal way points and heavy-tail flights on top of the way points. We verify through simulation that SLAW brings out the unique performance features of various mobile network routing protocols.
Conference Paper
Full-text available
Social networks represent a sophisticated tool for accessing the preferences and properties of individuals and groups. Thus, they potentially allow up-to-date, richly annotated contextual data to be acquired as a side effect of users' everyday use of services. In this paper, we explore how such “social sensing” could be integrated into pervasive systems. We frame and survey the possible approaches to such an integration, and discuss the open issues and challenges facing researchers.
Conference Paper
Full-text available
Understanding and predicting human mobility is a crucial component of transportation planning and management. In this paper we propose a new model to predict the location of a person over time based on individual and collective behaviors. The model is based on the person's past trajectory and the geographical features of the area where the collectivity moves, both in terms of land use, points of interests and distance of trips. The effectiveness of the proposed prediction model is tested using a massive mobile phone location dataset available for the Boston metropolitan area. Experimental results show good levels of accuracy in terms of prediction error and prove the advantage of using the collective behavior in the prediction model.
Conference Paper
Full-text available
We explore the prospect of inferring the epicenter and influences of seismic activity from changes in background phone communication activities logged at cell towers. In particular, we explore the perturbations in Rwandan call data invoked by an earthquake in February 2008 centered in the Lac Kivu region of the Democratic Republic of the Congo. Beyond the initial seismic event, we investigate the challenge of assessing the distribution of the persistence of needs over geographic regions, using the persistence of call anomalies after the earthquake as a proxy for lasting influences and the potential need for assistance. We also infer uncertainties in the inferences and consider the prospect of identifying the value of surveying the areas so that surveillance resources can be best triaged.
Conference Paper
Full-text available
With the prosperity of tourism and Web 2.0 technologies, more and more people have willingness to share their travel experiences on the Web (e.g., weblogs, forums, or Web 2.0 communities). These so-called travelogues contain rich information, particularly including location-representative knowledge such as attractions (e.g., Golden Gate Bridge), styles (e.g., beach, history), and activities (e.g., diving, surfing). The location-representative information in travelogues can greatly facilitate other tourists' trip planning, if it can be correctly extracted and summarized. However, since most travelogues are unstructured and contain much noise, it is difficult for common users to utilize such knowledge effectively. In this paper, to mine location-representative knowledge from a large collection of travelogues, we propose a probabilistic topic model, named as Location-Topic model. This model has the advantages of (1) differentiability between two kinds of topics, i.e., local topics which characterize locations and global topics which represent other common themes shared by various locations, and (2) representation of locations in the local topic space to encode both location-representative knowledge and similarities between locations. Some novel applications are developed based on the proposed model, including (1) destination recommendation for on flexible queries, (2) characteristic summarization for a given destination with representative tags and snippets, and (3) identification of informative parts of a travelogue and enriching such highlights with related images. Based on a large collection of travelogues, the proposed framework is evaluated using both objective and subjective evaluation methods and shows promising results.
Conference Paper
Full-text available
Microblogging today has become a very popular communication tool among Internet users. Millions of users share opinions on different aspects of life everyday. Therefore microblogging web-sites are rich sources of data for opinion mining and sentiment analysis. Because microblogging has appeared relatively recently, there are a few research works that were devoted to this topic. In our paper, we focus on using Twitter, the most popular microblogging platform, for the task of sentiment analysis. We show how to automatically collect a corpus for sentiment analysis and opinion mining purposes. We perform linguistic analysis of the collected corpus and explain discovered phenomena. Using the corpus, we build a sentiment classifier , that is able to determine positive, negative and neutral se ntiments for a document. Experimental evaluations show that our proposed techniques are efficient and performs better than previousl y proposed methods. In our research, we worked with English, however, the proposed technique can be used with any other language.
Article
Full-text available
In Wilderness Search and Rescue (WiSAR), the incident commander (IC) creates a probability distribution map of the likely location of the missing person. This map is important because it guides the IC in allocating search resources and coordinating efforts, but it often depends almost exclusively on the missing person profile, prior experience, and subjective judgment. We propose a Bayesian model that uses publicly available terrain features data to help model lost-person behaviors. This approach enables domain experts to encode uncertainty in their prior estimations and also makes it possible to incorporate human behavior data collected in the form of posterior distributions, which are used to build a first-order Markov transition matrix for generating a temporal, posterior predictive probability distribution map. The map can work as a base to be augmented by search and rescue workers to incorporate additional information. Using a Bayesian χ 2 test for goodness-of-fit, we show that the model fits a synthetic dataset well. This model also serves as a foundation for a larger framework that allows for easy expansion to incorporate additional factors such as season and weather conditions that affect the lost-person’s behaviors.
Conference Paper
Recommender Systems (RSs) are commonly used in web applications to support users in finding items of their interest. In this paper we propose a novel RS approach that supports human decision making by leveraging data acquired in the physical world. We consider a scenario in which users' choices to visit points of interests (POIs) are tracked and used to generate recommendations for not yet visited POIs. We propose a novel approach to user behaviour modelling that is based on Inverse Reinforcement Learning (IRL). Two recommendation strategies based on the proposed behaviour model are also proposed; they generate recommendations that differ from the common approach based on user next action prediction. Our experimental analysis shows that the proposed approach outperforms state of the art models in terms of the overall utility the user gains by following the provided recommendations and the novelty of the recommended items.
Conference Paper
Geo-fencing is a location based service that allows sending of messages to users who enter/exit a specified geographical area, known as a geo-fence. Today, it has become one of the popular location based mobile marketing strategies. However, the process of designing geo-fences is presently manual, i.e. a retailer must specify the location and the radius of area around it to setup the geo-fences. Moreover, this process does not consider the user's preference towards the targeted product/service and thus, can compromise his/her experience of the app that sends these communications. We attempt to solve this problem by presenting a novel end-to-end system for automated design of affinity based smart geo-fences. Affinity towards a product/service refers to the user's interest in a product/service. Our unique formulation to estimate affinity, using historical app usage data, is sensitive to a user's location and thus, the affinity is termed as location sensitive product affinity (LSPA). The geo-fence logic tries to capture contiguous groups of locations where the affinity high. Experiments on real world e-commerce dataset reveals that geo-fences designed by our approach performs significantly better at accurately targeting the users who are interested in a product. We thus show that, using historical app usage data, geo-fences can be designed in an automated manner and can help enterprises target interested users with better accuracy as compared to the present industry practices.
Article
Point-of-Interest (POI) recommendation is a new type of recommendation task that comes along with the prevalence of location-based social networks and services in recent years. Compared with traditional recommendation tasks, POI recommendation focuses more on making personalized and context-aware recommendations to improve user experience. Traditionally, the most commonly used contextual information includes geographical and social context information. However, the increasing availability of check-in data makes it possible to design more effective location recommendation applications by modeling and integrating comprehensive types of contextual information, especially the temporal information. In this article, we propose a collaborative filtering method based on Tensor Factorization, a generalization of the Matrix Factorization approach, to model the multi-dimensional contextual information. Tensor Factorization naturally extends Matrix Factorization by increasing the dimensionality of concerns, within which the three-dimensional model is the one most popularly used. Our method exploits a high-order tensor to fuse heterogeneous contextual information about users’ check-ins instead of the traditional two-dimensional user-location matrix. The factorization of this tensor leads to a more compact model of the data that is naturally suitable for integrating contextual information to make POI recommendations. Based on the model, we further improve the recommendation accuracy by utilizing the internal relations within users and locations to regularize the latent factors. Experimental results on a large real-world dataset demonstrate the effectiveness of our approach.
Thesis
Cities today are strained by the exponential growth in population where they are homes to the majority of world's population. Understanding the complexities underlying the emerging behaviors of human travel patterns on the city level is essential toward making informed decision-making pertaining to urban transportation infrastructures This thesis includes several attempts towards modeling and understanding human mobility at the scales of individuals and the scale of aggregate population movement. The second chapter includes the development of a browser delivering visual insights of the aggregate behavior of populations in cities. The third chapter provides a computational framework for clustering regions in cities based on their attraction behavior and in doing so aids a predictive model in predicting inflows to newly developed regions. The fourth chapter investigates the patterns of individuals' movement at the city scale towards developing a predictive model for a persons' next visited location. The predictive accuracy is then increased by adding movement information of the population. The motivation behind the work of this thesis is derived from the demand of tools that provides fine-grained analysis of the complexity of human travel within cites. The approach takes advantage of the existing built infrastructures to sense the mobility of people eliminating the financial and temporal burdens of traditional methods. The outcomes of this work will assist both planners and the public in understanding the complexities of human mobility within their cities.
Conference Paper
Incorporating users' personality traits has shown to be instrumental in many personalized retrieval and recommender systems. Analysis of users' digital traces has become an important resource for inferring personality traits. To date, the analysis of users' explicit and latent characteristics is typically restricted to a single social networking site (SNS). In this work, we propose a novel method that integrates text, image, and users' meta features from two different SNSs: Twitter and Instagram. Our preliminary results indicate that the joint analysis of users' simultaneous activities in two popular SNSs seems to lead to a consistent decrease of the prediction errors for each personality trait.
Chapter
The AMBER Alert system is popular and highly regarded as a method to rapidly inform citizens to assist in the recovery of abducted children. While public safety officials and missing child advocates laud the system, the scant available empirical evidence suggests claims of its effectiveness should be sharply qualified. It is beyond dispute that some AMBER Alerts have been effective in facilitating the recovery of some abducted children. However, there is extremely little evidence that AMBER Alerts have rescued any children from life-threatening abduction scenarios. In fact, there are not only compelling reasons to doubt the system’s utility but very plausible concerns it could even backfire in specific cases. It can also potentially distort public discourse regarding threats to children. A key concern regarding the AMBER Alert system is whether it can actually hamper effective law enforcement response to specific child abductions and the larger social response to child abductions in general.
Article
Social media allow web users to create and share content pertaining to different subjects, exposing their activities, opinions, feelings and thoughts. In this context, online social media has attracted the interest of data scientists seeking to understand behaviours and trends, whilst collecting statistics for social sites. One potential application for these data is personality prediction, which aims to understand a user’s behaviour within social media. Traditional personality prediction relies on users’ profiles, their status updates, the messages they post, etc. Here, a personality prediction system for social media data is introduced that differs from most approaches in the literature, in that it works with groups of texts, instead of single texts, and does not take users’ profiles into account. Also, the proposed approach extracts meta-attributes from texts and does not work directly with the content of the messages. The set of possible personality traits is taken from the Big Five model and allows the problem to be characterised as a multi-label classification task. The problem is then transformed into a set of five binary classification problems and solved by means of a semi-supervised learning approach, due to the difficulty in annotating the massive amounts of data generated in social media. In our implementation, the proposed system was trained with three well-known machine-learning algorithms, namely a Naïve Bayes classifier, a Support Vector Machine, and a Multilayer Perceptron neural network. The system was applied to predict the personality of Tweets taken from three datasets available in the literature, and resulted in an approximately 83% accurate prediction, with some of the personality traits presenting better individual classification rates than others.
Conference Paper
In this paper, we consider the problem of developing a model of the behaviour of a Missing Person (MP) who is lost in the wilderness. Traditional models have treated the movement of an MP as a type of diffusion process, without regard for the MP's internal state or goals. However, this fails to include many important factors, including the effects of fatigue or the use of reorienting strategies, which are known to be important from empirical studies of actual lost person behaviour. To overcome these limitations, we develop a novel agent-based model of MP behaviour. This model incorporates the effects of the environment, perception and goals on the MP's movement and uses them to model the continuous switching of short and medium term goals by missing people. To validate the model, we compared the trajectories simulated by it with actual recordings of movements of participants in an unfamiliar wilderness environment. By comparing the predicted and actual trajectories, we show that the generated trajectories much more faithfully represent the actual movements of the participants than state-of-the-art diffusion models.
Article
Sentiment analysis is a growing area of research with significant applications in both industry and academia. Most of the proposed solutions are centered around supervised, machine learning approaches and review-oriented datasets. In this article, we focus on the more common informal textual communication on the Web, such as online discussions, tweets and social network comments and propose an intuitive, less domain-specific, unsupervised, lexicon-based approach that estimates the level of emotional intensity contained in text in order to make a prediction. Our approach can be applied to, and is tested in, two different but complementary contexts: subjectivity detection and polarity classification. Extensive experiments were carried on three real-world datasets, extracted from online social Web sites and annotated by human evaluators, against state-of-the-art supervised approaches. The results demonstrate that the proposed algorithm, even though unsupervised, outperforms machine learning solutions in the majority of cases, overall presenting a very robust and reliable solution for sentiment analysis of informal communication on the Web.
Article
This paper presents a new method for sentiment analysis in Facebook that, starting from messages written by users, supports: (i) to extract information about the users' sentiment polarity (positive, neutral or negative), as transmitted in the messages they write; and (ii) to model the users' usual sentiment polarity and to detect significant emotional changes. We have implemented this method in SentBuk, a Facebook application also presented in this paper. SentBuk retrieves messages written by users in Facebook and classifies them according to their polarity, showing the results to the users through an interactive interface. It also supports emotional change detection, friend's emotion finding, user classification according to their messages, and statistics, among others. The classification method implemented in SentBuk follows a hybrid approach: it combines lexical-based and machine-learning techniques. The results obtained through this approach show that it is feasible to perform sentiment analysis in Facebook with high accuracy (83.27%). In the context of e-learning, it is very useful to have information about the users' sentiments available. On one hand, this information can be used by adaptive e-learning systems to support personalized learning, by considering the user's emotional state when recommending him/her the most suitable activities to be tackled at each time. On the other hand, the students' sentiments towards a course can serve as feedback for teachers, especially in the case of online learning, where face-to-face contact is less frequent. The usefulness of this work in the context of e-learning, both for teachers and for adaptive systems, is described too.
Article
Centralized Online Social Network services (OSN) are collecting immense amounts of data, containing a wealth of information about preferences of their users. Its exploitation for the benefit of the users, even though quite promising, has not seriously been tackled, yet. For this purpose, we propose a personalized recommender for places in location-based OSNs, based on the check-ins of the entire user base. Following a brief analysis, we first propose an interpretation of the data available to OSN providers and an recommendation scheme based on regularized matrix factorization. To evaluate our approach we acquire a large sample of a real data set by crawling Gowalla, one of the most popular location-based OSNs. An exhaustive experimental evaluation then confirms the feasability of using Collaborative Filtering techniques to make personalized recommendation of potentially interesting spots.
Article
The development of a city gradually fosters different functional regions, such as educational areas and business districts. In this paper, we propose a framework (titled DRoF) that Discovers Regions of different Functions in a city using both human mobility among regions and points of interests (POIs) located in a region. Specifically, we segment a city into disjointed regions according to major roads, such as highways and urban express ways. We infer the functions of each region using a topic-based inference model, which regards a region as a document, a function as a topic, categories of POIs (e.g., restaurants and shopping malls) as metadata (like authors, affiliations, and key words), and human mobility patterns (when people reach/leave a region and where people come from and leave for) as words. As a result, a region is represented by a distribution of functions, and a function is featured by a distribution of mobility patterns. We further identify the intensity of each function in different locations. The results generated by our framework can benefit a variety of applications, including urban planning, location choosing for a business, and social recommendations. We evaluated our method using large-scale and real-world datasets, consisting of two POI datasets of Beijing (in 2010 and 2011) and two 3-month GPS trajectory datasets (representing human mobility) generated by over 12,000 taxicabs in Beijing in 2010 and 2011 respectively. The results justify the advantages of our approach over baseline methods solely using POIs or human mobility.
Article
We show that easily accessible digital records of behavior, Facebook Likes, can be used to automatically and accurately predict a range of highly sensitive personal attributes including: sexual orientation, ethnicity, religious and political views, personality traits, intelligence, happiness, use of addictive substances, parental separation, age, and gender. The analysis presented is based on a dataset of over 58,000 volunteers who provided their Facebook Likes, detailed demographic profiles, and the results of several psychometric tests. The proposed model uses dimensionality reduction for preprocessing the Likes data, which are then entered into logistic/linear regression to predict individual psychodemographic profiles from Likes. The model correctly discriminates between homosexual and heterosexual men in 88% of cases, African Americans and Caucasian Americans in 95% of cases, and between Democrat and Republican in 85% of cases. For the personality trait "Openness," prediction accuracy is close to the test-retest accuracy of a standard personality test. We give examples of associations between attributes and Likes and discuss implications for online personalization and privacy.
Article
The AMBER Alert system was designed to recover endangered missing children through the solicitation of citizen assistance via swift public announcements. Rigorous empirical support for AMBER Alert's effectiveness has been lacking, but since its inception program advocates and public safety officials have lauded the system's ability to "save lives", often basing their optimism on AMBER Alert "success" stories. However, in this paper quantitative and qualitative analyses of 333 publicized and celebrated AMBER Alert "successes" suggest AMBER Alerts rarely result in the retrieval of abducted children from clearly "life-threatening" situations, and that most of the publicized successes involved relatively benign abductors and unthreatening circumstances. The routine conflation of such apparently mundane cases with rare dramatic successes by AMBER Alert advocates suggests popular portrayals of AMBER Alert are overly sanguine. The potentially negative effects of this and policy implications are discussed.
Chapter
Technological advances in position aware devices increase the availability of tracking data of everyday objects such as animals, vehicles, people or football players. We propose a geographic data mining approach to detect generic aggregation patterns such as flocking behaviour and convergence in geospatial lifeline data. Our approach considers the object’s motion properties in an analytical space as well as spatial constraints of the object’s lifelines in geographic space. We discuss the geometric properties of the formalised patterns with respect to their efficient computation.
Conference Paper
This paper presents an analysis of continuous cellu- lar tower data representing five months of movement from 215 randomly sampled subjects in a major urban city. We demonstrate the potential of existing com- munity detection methodologies to identify salient lo- cations based on the network generated by tower tran- sitions. The tower groupings from these unsupervised clustering techniques are subsequently validated using data from Bluetooth beacons placed in the homes of the subjects. We then use these inferred locations as states within several dynamic Bayesian networks to predict each subject's subsequent movements with over 90% accuracy. We also introduce the X-Factor model, a DBN with a latent variable corresponding to abnormal behavior. We conclude with a description of extensions for this model, such as incorporating additional contex- tual and temporal variables already being logged by the phones. bluetooth beacon data placed in the homes of each subject with the tower data, we validate the output of the commu- nity structure algorithms with the community of towers co- present with the beacon exposures in each subject's home. We then describe several DBNs that use the inferred loca- tions clusters as states to parametrize and predict subsequent movements. One such DBN we use for behavioral modeling includes a latent variable, the X-Factor, corresponding to a binary switch indicative of "normal" or "abnormal" behav- ior. We conclude with ideas for extensions to these models as future work. There has recently been a significant amount of research quantifying and modeling human behavior using data from mobile phones. We will highlight a selection of the liter- ature on GSM trace analysis and subsequently discuss re- cent work on location segmentation and movement predic- tion from GPS data.
Conference Paper
The increasing availability of GPS-enabled devices is changing the way people interact with the Web, and brings us a large amount of GPS trajectories representing people's location histories. In this paper, based on multiple users' GPS trajectories, we aim to mine interesting locations and classical travel sequences in a given geospatial region. Here, interesting locations mean the culturally important places, such as Tiananmen Square in Beijing, and frequented public areas, like shopping malls and restaurants, etc. Such information can help users understand surrounding locations, and would enable travel recommendation. In this work, we first model multiple individuals' location histories with a tree-based hierarchical graph (TBHG). Second, based on the TBHG, we propose a HITS (Hypertext Induced Topic Search)-based inference model, which regards an individual's access on a location as a directed link from the user to that location. This model infers the interest of a location by taking into account the following three factors. 1) The interest of a location depends on not only the number of users visiting this location but also these users' travel experiences. 2) Users' travel experiences and location interests have a mutual reinforcement relationship. 3) The interest of a location and the travel experience of a user are relative values and are region-related. Third, we mine the classical travel sequences among locations considering the interests of these locations and users' travel experiences. We evaluated our system using a large GPS dataset collected by 107 users over a period of one year in the real world. As a result, our HITS-based inference model outperformed baseline approaches like rank-by-count and rank-by-frequency. Meanwhile, when considering the users' travel experiences and location interests, we achieved a better performance beyond baselines, such as rank- by-count and rank-by-interest, etc.
Conference Paper
With the increasing popularity of location-based services, such as tour guide and location-based social network, we now have accumulated many location data on the Web. In this paper, we show that, by using the location data based on GPS and users' comments at various locations, we can discover interesting locations and possible activities that can be performed there for recommendations. Our research is highlighted in the following location-related queries in our daily life: 1) if we want to do something such as sightseeing or food-hunting in a large city such as Beijing, where should we go? 2) If we have already visited some places such as the Bird's Nest building in Beijing's Olympic park, what else can we do there? By using our system, for the first question, we can recommend her to visit a list of interesting locations such as Tiananmen Square, Bird's Nest, etc. For the second question, if the user visits Bird's Nest, we can recommend her to not only do sightseeing but also to experience its outdoor exercise facilities or try some nice food nearby. To achieve this goal, we first model the users' location and activity histories that we take as input. We then mine knowledge, such as the location features and activity-activity correlations from the geographical databases and the Web, to gather additional inputs. Finally, we apply a collective matrix factorization method to mine interesting locations and activities, and use them to recommend to the users where they can visit if they want to perform some specific activities and what they can do if they visit some specific places. We empirically evaluated our system using a large GPS dataset collected by 162 users over a period of 2.5 years in the real-world. We extensively evaluated our system and showed that our system can outperform several state-of-the-art baselines.
Conference Paper
The unprecedented amount of data from mobile phones creates new possibilities to analyze various aspects of human behavior. Over the last few years, much effort has been devoted to studying the mobility patterns of humans. In this paper we will focus on unusually large gatherings of people, i.e. unusual social events. We introduce the methodology of detecting such social events in massive mobile phone data, based on a Bayesian location inference framework. More specifically, we also develop a framework for deciding who is attending an event. We demonstrate the method on a few examples. Finally, we discuss some possible future approaches for event detection, and some possible analyses of the detected social events.