Abstract The increasing use of data-driven decision support systems in industry and governments is accompanied by the discovery of a plethora of bias and unfairness issues in the outputs of these systems. Multiple computer science communities, and especially machine learning, have started to tackle this problem, often developing algorithmic solutions to mitigate biases to obtain fairer outputs. However, one of the core underlying causes for unfairness is bias in training data which is not fully covered by such approaches. Especially, bias in data is not yet a central topic in data engineering and management research. We survey research on bias and unfairness in several computer science domains, distinguishing between data management publications and other domains. This covers the creation of fairness metrics, fairness identification, and mitigation methods, software engineering approaches and biases in crowdsourcing activities. We identify relevant research gaps and show which data management activities could be repurposed to handle biases and which ones might reinforce such biases. In the second part, we argue for a novel data-centered approach overcoming the limitations of current algorithmic-centered methods. This approach focuses on eliciting and enforcing fairness requirements and constraints on data that systems are trained, validated, and used on. We argue for the need to extend database management systems to handle such constraints and mitigation methods. We discuss the associated future research directions regarding algorithms, formalization, modelling, users, and systems.

In online crowd mapping, crowd workers recruited through crowdsourcing marketplaces collect geographic data. Compared to traditional mapping methods, where workers physically explore the area, the benefit of using online crowd mapping is the potential to be cost-effective and time-efficient. Previous studies have focused on mapping urban objects using street-level imagery. However, they are specifically aimed at a single type of object, and only through web platforms. To the best of our knowledge, there is still a lack of understanding on how workers perform the mapping tasks through different platforms. Aiming to fill this knowledge gap, we investigate the worker performance across web, mobile, and virtual reality platforms by designing a multi-platform system for mapping urban objects using street-level imagery with novel methods for geo-location estimation. We design a preliminary study to show the feasibility of executing online mapping tasks on three platforms. The result demonstrates that the type of task and execution platform can affect the worker performance in terms of worker accuracy, execution time, user engagement, and cognitive load.

Up-to-date listings of retail stores and related building functions are challenging and costly to maintain. We introduce a novel method for automatically detecting, geo-locating, and classifying retail stores and related commercial functions, on the basis of storefronts extracted from street-level imagery. Specifically, we present a deep learning approach that takes storefronts from street-level imagery as input, and directly provides the geo-location and type of commercial function as output. Our method showed a recall of 89.05% and a precision of 88.22% on a real-world dataset of street-level images, which experimentally demonstrated that our approach achieves human-level accuracy while having a remarkable run-time efficiency compared to methods such as Faster Region-Convolutional Neural Networks (Faster R-CNN) and Single Shot Detector (SSD).

Sepideh Mesbah, Jie Yang, Robert-Jan Sips, Manuel Valle Torre, Christoph Lofi, Alessandro Bozzon, Geert-Jan Houben. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). 2019.

Knowledge about the organization of the main physical elements (e.g. streets) and objects (e.g. trees) that structure cities is important in the maintenance of city infrastructure and the planning of future urban interventions. In this paper, a novel approach to crowd-mapping urban objects is proposed. Our method capitalizes on strategies for generating crowdsourced object annotations from street-level imagery, in combination with object density and geo-location estimation techniques to enable the enumeration and geo-tagging of urban objects. To address both the coverage and precision of the mapped objects within budget constraints, we design a scheduling strategy for micro-task prioritization, aggregation, and assignment to crowd workers. We experimentally demonstrate the feasibility of our approach through a use case pertaining to the mapping of street trees in New York City and Amsterdam. We show that anonymous crowds can achieve high recall (up to 80%) and precision (up to 68%), with geo-location precision of approximately 3m. We also show that similar performance could be achieved at city scale, possibly with stringent budget constraints.

Massive Open Online Courses (MOOCs) allow learning to take place anytime and anywhere with little external monitoring by teachers. Characteristically, highly diverse groups of learners enrolled in MOOCs are required to make decisions related to their own learning activities to achieve academic success. Therefore, it is considered important to support self-regulated learning (SRL) strategies and adapt to relevant human factors (e.g., gender, cognitive abilities, prior knowledge). SRL supports have been widely investigated in traditional classroom settings, but little is known about how SRL can be supported in MOOCs. Very few experimental studies have been conducted in MOOCs at present. To fill this gap, this paper presents a systematic review of studies on approaches to support SRL in multiple types of online learning environments and how they address human factors. The 35 studies reviewed show that human factors play an important role in the efficacy of SRL supports. Future studies can use learning analytics to understand learners at a fine-grained level to provide support that best fits individual learners. The objective of the paper is twofold: (a) to inform researchers, designers and teachers about the state of the art of SRL support in online learning environments and MOOCs; (b) to provide suggestions for adaptive self-regulated learning support.

Retrieval practice has been established in the learning sciences as one of the most effective strategies to facilitate robust learning in traditional classroom contexts. The cognitive theory underpinning the "testing effect" states that actively recalling information is more effective than passively revisiting materials for storing information in long-term memory. We document the design, deployment, and evaluation of an Adaptive Retrieval Practice System (ARPS) in a MOOC. This push-based system leverages the testing effect to promote learner engagement and achievement by intelligently delivering quiz questions from prior course units to learners throughout the course. We conducted an experiment in which learners were randomized to receive ARPS in a MOOC to track their performance and behavior compared to a control group. In contrast to prior literature, we find no significant effect of retrieval practice in this MOOC environment. In the treatment condition, passing learners engaged more with ARPS but exhibited similar levels of knowledge retention as non-passing learners.

This paper applies theory and methodology from the learning design literature to large-scale learning environments through quantitative modeling of the structure and design of Massive Open Online Courses. For two institutions of higher education, we automate the task of encoding pedagogy and learning design principles for 177 courses (which accounted for for nearly 4 million enrollments). Course materials from these MOOCs are parsed and abstracted into sequences of components, such as videos and problems. Our key contributions are (i) describing the parsing and abstraction of courses for quantitative analyses, (ii) the automated categorization of similar course designs, and (iii) the identification of key structural components that show relationships between categories and learning design principles. We employ two methods to categorize similar course designs---one aimed at clustering courses using transition probabilities and another using trajectory mining. We then proceed with an exploratory analysis of relationships between our categorization and learning outcomes.

Crowdsourcing has emerged as an effective method of scaling-up tasks previously reserved for a small set of experts. Accordingly, researchers in the large-scale online learning space have begun to employ crowdworkers to conduct research about large-scale, open online learning. We here report results from a crowdsourcing study (N=135) to evaluate the extent to which crowdworkers and MOOC learners behave comparably on lecture viewing and quiz tasks---the most utilized learning activities in MOOCs. This serves to (i) validate the assumption of previous research that crowdworkers are indeed reliable proxies of online learners and (ii) address the potential of employing crowdworkers as a means of online learning environment testing. Overall, we observe mixed results---in certain contexts (quiz performance and video watching behavior) crowdworkers appear to behave comparably to MOOC learners, and in other situations (interactions with in-video quizzes), their behaviors appear to be disparate. We conclude that future research should be cautious if employing crowdworkers to carry out learning tasks, as the two populations do not behave comparably on all learning-related activities.

Massive Open Online Courses (MOOCs) aim to educate the world, especially learners from developing countries. While MOOCs are certainly available to the masses, they are not yet fully accessible. Although all course content is just clicks away, deeply engaging with a MOOC requires a substantial time commitment, which frequently becomes a barrier to success. To mitigate the time required to learn from a MOOC, we here introduce a design that enables learners to earn money by applying what they learn in the course to real-world marketplace tasks. We present a Paid Task Recommender System (Rec-$ys), which automatically recommends course-relevant tasks to learners as drawn from online freelance platforms. Rec-$ys has been deployed into a data analysis MOOC and is currently under evaluation.

Social comparison theory asserts that we establish our social and personal worth by comparing ourselves to others. In in-person learning environments, social comparison offers students critical feedback on how to behave and be successful. By contrast, online learning environments afford fewer social cues to facilitate social comparison. Can increased availability of such cues promote effective self-regulatory behavior and achievement in Massive Open Online Courses (MOOCs)? We developed a personalized feedback system that facilitates social comparison with previously successful learners based on an interactive visualization of multiple behavioral indicators. Across four randomized controlled trials in MOOCs (overall N = 33, 726), we find: (1) the availability of social comparison cues significantly increases completion rates, (2) this type of feedback benefits highly educated learners, and (3) learners' cultural context plays a significant role in their course engagement and achievement.

This brief introduction begins with an overview of the types of research that are relevant to the special issue on Big Personal Data in Interactive Intelligent Systems. The overarching question is: How can big personal data be collected, analyzed, and exploited so as to provide new or improved forms of interaction with intelligent systems, and what new issues have to be taken into account? The three articles accepted for the special issue are then characterized in terms of the concepts of this overview.

In recent years, gamification, “the use of game design elements in non-game contexts”, has drawn the attention of an increasing number of scientists. Although several studies highlighted the benefits of gamification in many applications, its potential in the \emph{enterprise} environment still needs to be fully understood.

The rising number of Massive Open Online Courses (MOOCs) enable people to advance their knowledge and competencies in a wide range of fields. Learning though is only the first step, the transfer of the taught concepts into practice is equally important and often neglected in the investigation of MOOCs. In this paper, we consider the specific case of FP101x (a functional programming MOOC on edX) and the extent to which learners alter their programming behaviour after having taken the course. We are able to link about one third of all FP101x learners to GitHub, the most popular social coding platform to date and contribute a first exploratory analysis of learner behaviour beyond the MOOC platform. A detailed longitudinal analysis of GitHub log traces reveals that (i) more than 8% of engaged learners transfer, and that (ii) most existing transfer learning findings from the classroom setting are indeed applicable in the MOOC setting as well.

Massive Open Online Courses (MOOCs) have gained considerable momentum since their inception in 2011. They are, however, plagued by two issues that threaten their future: learner engagement and learner retention. MOOCs regularly attract tens of thousands of learners, though only a very small percentage complete them successfully. In the traditional classroom setting, it has been established that personality impacts different aspects of learning. It is an open question to what extent this finding translates to MOOCs: do learners' personalities impact their learning & learning behaviour in the MOOC setting? In this paper, we explore this question and analyse the personality profiles and learning traces of hundreds of learners that have taken a EX101x Data Analysis MOOC on the edX platform. We find learners' personality traits to only weakly correlate with learning as captured through the data traces learners leave on edX.

Conducting analytics over data generated by Social Web portals such as Twitter is challenging, due to the volume, variety and velocity of the data. Commonly, adhoc pipelines are used that solve a particular use case. In this paper, we generalize across a range of typical Twitter-data use cases and determine a set of common characteristics. Based on this investigation, we present our Twitter Analytical Platform (TAP), a generic platform for conducting analytical tasks with Twitter data. The platform provides a domain-specific Twitter Analysis Language (TAL) as the interface to its functionality stack. TAL includes a set of analysis tools ranging from data collection and semantic enrichment, to machine learning. With these tools, it becomes possible to create and customize analytical workflows in TAL and build applications that make use of the analytics results. We showcase the applicability of our platform by building Twinder-a search engine for Twitter streams.

With more than 340~million messages that are posted on Twitter every day, the amount of duplicate content as well as the demand for appropriate duplicate detection mechanisms is increasing tremendously. Yet there exists little research that aims at detecting near-duplicate content on microblogging platforms. We investigate the problem of near-duplicate detection on Twitter and introduce a framework that analyzes the tweets by comparing (i) syntactical characteristics, (ii) semantic similarity, and (iii) contextual information. Our framework provides different duplicate detection strategies that, among others, make use of external Web resources which are referenced from microposts. Machine learning is exploited in order to learn patterns that help identifying duplicate content. We put our duplicate detection framework into practice by integrating it into Twinder, a search engine for Twitter streams. An in-depth analysis shows that it allows Twinder to diversify search results and improve the quality of Twitter search. We conduct extensive experiments in which we (1) evaluate the quality of different strategies for detecting duplicates, (2) analyze the impact of various features on duplicate detection, (3) investigate the quality of strategies that classify to what exact level two microposts can be considered as duplicates and (4) optimize the process of identifying duplicate content on Twitter. Our results prove that semantic features which are extracted by our framework can boost the performance of detecting duplicates.

Model-Driven Engineering (MDE) is becoming a widely accepted paradigm for the design and development of complex distributed applications. MDE advocates the use of models and model transformations as key artefacts in all phases of the software process, from system specification and analysis, to design, development and testing. Each model usually addresses one concern, independently from the rest of the issues involved in the construction of the system. Thus, the basic functionality of the system can be separated from its final implementation, and the business logic can be separated from the underlying platform technology, etc. Transformations between models enable the automated implementation of a system from the different models defined for it.

In this work we present an in-depth analysis of the user behaviors on different Social Sharing systems. We consider three popular platforms, Flickr, Delicious and StumbleUpon, and, by combining techniques from social network analysis with techniques from semantic analysis, we characterize the tagging behavior as well as the tendency to create friendship relationships of the users of these platforms. The aim of our investigation is to see if (and how) the features and goals of a given Social Sharing system reflect on the behavior of its users and, moreover, if there exists a correlation between the social and tagging behavior of the users. We report our findings in terms of the characteristics of user profiles according to three different dimensions: (i) intensity of user activities, (ii) tag-based characteristics of user profiles, and (iii) semantic characteristics of user profiles.

Estimating the geographic location of images is a task which has received increasing attention recently. Large numbers of images uploaded to platforms such as Flickr do not contain GPS-based latitude/longitude coordinates. Obtaining such geographic information is beneficial for a variety of applications including travelogues, visual place descriptions and personalized travel recommendations. While most works in this area only exploit an image's textual meta-data (tags, title, etc.) to estimate at what geographic location the image was taken, we consider an additional textual dimension: the image owner's traces on the social Web. Specifically, we hypothesize that information extracted from a person's microblog stream(s) can be utilized to improve the accuracy with which the geographic location of the images is estimated. In this paper, we investigate this hypothesis on the example of Twitter streams and find it to be confirmed. The median error distance in kilometres decreases by up to 67% in comparison to existing state-of-the-art. The best results are achieved when tweets that were posted up to two days before and after an image was taken are considered. Moreover, we also find another type of additional information useful: population density data.

In this paper, we study user modeling on Twitter and investigate the interplay between personal interests and public trends. To generate semantically meaningful user profiles, we present a framework that allows us to enrich the semantics of individual Twitter messages and features user modeling as well as trend modeling strategies. These profiles can be re-used in other applications for (trend-aware) personalization. Given a large Twitter dataset, we analyze the characteristics of user and trend profiles and evaluate the quality of the profiles in the context of a personalized news recommendation system. We show that personal interests are more important for the recommendation process than public trends and that by combining both types of profiles we can further improve recommendation quality.

With the enormous and still growing amount of data and user interaction on the Web, it becomes more and more necessary for data consumers to be able to assess the trustworthiness of data on the Web. In this paper, we present a framework for trust establishment and assessment on the Web of Data. Different from many approaches that build trust metrics within networks of people, we propose a model to represent the trust in concrete pieces of web data for a specific consumer, in which also the context is considered. Further more, we provide three strategies for trust assessment based on the principles of Linked Data, to overcome the shortcomings of the conventional web of documents: i.e. the lack of semantics and interlinking.

In this paper we present our iFanzy demonstrator, which aims at offering users television content in a personalized and context-sensitive way. With iFanzy we integrate different volatile content sources like video-on-demand, broadcast and Web information on-the-fly to disperse it on different clients on different platforms like set-top boxes and Web interfaces. Via semantic Web techniques, TV content and background data from various heterogeneous sources is integrated into a transparent RDF/OWL knowledge graph, which allows the user to navigate and browse the vast content sets nowadays available. Via illustrative examples we explain how the main integrated data set is built and how we exploit it to provide iFanzypsilas main functionality, like semantic search of the available content and execution of context sensitive recommendations.

Web-based systems can exploit Semantic Web-based approaches to link data and thus create applications that make the most out of the combination and integration of different sources and background knowledge. While a lot of attention is paid to the opportunities that this linking of data on the Web provides, the reality of implementing such solutions with currently available semantic technologies createsa serious engineering challenge. In developing such applications in a commercial setting, we have been confronted with requirements and conditions that show the limitations of current technologies for this type of Web applications. Using our experience from iFanzy, we illustrate in this paper the issues and steps in turning the concept of access to semantically integrated content into solutions that use available technology.

The World Wide Web is a rapidly growing business environmenthosting a large number of business transactions. Methods fordesigning Web Information Systems (WIS) have adopted processmodels, typically as extensions of the navigation models they arebased on. We observe that the structure of business processes inWIS goes beyond the scope of the navigation structure and deservesto be a more prominent aspect of the design, abstracted from thenavigation specification. This paper explains the design of WISdriven by the specification of business processes of WIS that isused for the automatic generation of models describing theapplication logic including the navigation structure. Thespecification of processes is explained on a conference review andsubmission system and the generation process is demonstrated onthe Hera application model.

Web application design methods traditionally aim to reduce complexity in implementing Web applications. However, these methods struggle with providing the necessary dynamics and flexibility to keep up with the increasing users' demand for personalization and feedback mechanisms. We present Hera-S, based on Sesame and the SeRQL query language that does provide the necessary flexibility. Hera-S allows designers the plain use of the Semantic Web languages RDFS and OWL for designing the domain model and the context data model, thus enabling re-use of existing data models and opening up the RDF instance data to queries and updates via the Sesame RDF-framework.

In this paper, we present a rule-based approach supporting the automatic adaptation in Web Information Systems. The approach relies on the general notions of profile and configuration. Special rules are used to specify, in a declarative way, how to build a configuration that satisfies the requirements of adaptation for a profile. The rule evaluation technique guarantees that different contexts and orthogonal requirements of adaptation, possibly not fixed in advance, can be taken into account in the adaptation process.

The evolution of the Web requires to consider an increasing number of context-dependency issues. Therefore, in our research we focus on how to extend a Web application with additional adaptation concerns without having to redesign the entire application. Based on a generic transcoding tool we illustrate here how we can add adaptation functionality to an existing Web application. Furthermore, we consider how an aspect-oriented approach can support the high-level specification of such additional concerns in the design of the Web application.

System evolution most often implies the integration of legacy components, such as databases, with newly developed ones, leading to mixed architectures that suffer from severe heterogeneity problems. For instance, incorporating a new program in a legacy database application can create an integrity mismatch, since the database model and the program data view can be quite different (e.g. standard file model versus OO model). In addition, neither the legacy DBMS (too weak to address integrity issues correctly) nor the new program (that relies on data server responsibility) correctly cope with data integrity management. The component that can reconciliate these mismatched subsystems is the R/W wrapper , which allows any client program to read, but also to update the legacy data, while controlling the integrity constraints that are ignored by the legacy DBMS.This article describes a generic, technology-independent, R/W wrapper architecture, a methodology for specifying them in a disciplined way, and a CASE tool for generating most of the corresponding code.The key concept is that of implicit construct , which is a structure or a constraint that has not been declared in the database, but which is controlled by the legacy application code. The implicit constructs are elicited through reverse engineering techniques, and then translated into validation code in the wrapper. For instance, a wrapper can be generated for a collection of COBOL files in order to allow external programs to access them through a relational, object-oriented or XML interface, while offering referential integrity control. The methodology is based on a transformational approach that provides a formal way to build the wrapper schema and to specify inter-schema mappings.

A technical infrastructure for storing, querying and managing RDFdata is a key element in the current semantic web development. Systems like Jena, Sesame or the ICS-FORTH RDF Suite are widelyused for building semantic web applications. Currently, none ofthese systems supports the integrated querying of distributed RDF repositories. We consider this a major shortcoming since the semanticweb is distributed by nature. In this paper we present an architecture for querying distributed RDF repositories by extending the existing Sesame system. We discuss the implications of our architectureand propose an index structure as well as algorithms forquery processing and optimization in such a distributed context.

No abstract available.

As Resource Description Framework (RDF) reaches maturity, there is an increasing need for tools that support it. A common and natural representation for RDF data is a directed labeled graph. Although there are tools to edit and/or browse RDF graph representations, we found their architecture rigid and not easily amenable to producing effective visual representations, especially for large RDF graphs. We discuss here how GViz, a general purpose graph visualisation tool, allows the easy construction and fine-tuning of various visual exploratory scenarios for RDF data. GViz's extended ability of customizing the visualisation's icons showed to be very useful in the context of RDF graph structures visualisation. Among the presented applications, we mention customizable selections, schema-instance comparison, instances comparison, and schemas comparison (schema evolution). GViz proved to be able not only to visualize large RDF data models, but also to be very flexible in designing scenario-specific queries to support the exploration process.

To make the WWW machine-understandable there is a strong demand both for languages describing metadata and for languages querying metadata. The Resource Description Framework (RDF), a language proposed by W3C, can be used for describing metadata about (Web) resources. The RDF schema (RDFS) extends RDF by providing means for creating application specific vocabularies (ontologies). While the above two languages are widely acknowledged as a standard means for describing Web metadata, a standardized language for querying RDF metadata is still an open issue. Research groups from both industry and academia are presently involved in proposing several RDF query languages. Due to the lack of an RDF algebra such query languages use APIs to describe their semantics and optimization issues are mostly neglected. This paper proposes RAL, an RDF algebra suitable for defining (and comparing) the semantics of different RDF query languages and (at a future stage) for performing algebraic optimizations. After a definition of the data model we present the operators with which the model can be manipulated. The operators come in three flavors: extraction operators retrieve needed resources from the input RDF model, loop operators support repetition, and construction operators build the resulting RDF model.