41 research outputs found
Towards Minimal Necessary Data: The Case for Analyzing Training Data Requirements of Recommender Algorithms
No full textContains fulltext :
178606.pdf (Publisher’s version ) (Open Access)FATREC’17: Fairness, Accountability and Transparency in Recommender Systems, 31 August 2017, Como, Ital
Creating Trust in Citizen Participation through Decentralized Autonomous Citizen Participation Organizations (DACPOs)
No full textBlockchain-based Decentralized Autonomous Organizations (DAOs) are systems for transacting and storing value by automatically executing a function without the need for trusted, centralized authorities. Participative budgeting requires voting about budget allocation by communities and is often confronted with issues in trust and transparency. Yet, DAOs are hardly used for participative budgeting. In this research, we introduce Decentralized Autonomous Citizen Participation Organizations (DACPOs). In a DACPO, data and actions are recorded and autonomously executed in a decentralized way. DACPOs can be used for enabling participative budgeting and thereby provide transparency, decrease the risks of fraud and corruption, and increase citizens' trust. The viability of DACPOs depends on a number of factors, including a minimum number of citizens who participate. In further research, factors influencing the use of DACPOs for participative budgeting can be further analyzed and tested.Green Open Access added to TU Delft Institutional Repository ‘You share, we take care!’ – Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.Information and Communication TechnologyEngineering, Systems and ServicesEconomics of Technology and Innovatio
Public Values of Trustworthy Peer-To-peer (P2P) Lending System
No full textGovernments want to improve the economy by extending the market of financial credit. Recently, Peer-To-peer (P2P) lending credit scoring systems have gained more attention for advancing society; however, the role of governments in ensuring fair access to such a system is not known. This work aims to understand better the public values for trustworthy P2P lending systems. Public values should provide the basis to which a P2P lending system should adhere. Credit scoring in P2P lending is not merely about the technology in creating a profitable system for all participants. Several public values are of relevance. Understanding credit scoring in P2P lending is crucial to ensure inclusiveness, trustworthiness, fairness, equal treatment, and accountability.Green Open Access added to TU Delft Institutional Repository ‘You share, we take care!’ – Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.Information and Communication TechnologyEngineering, Systems and Service
A Survey of State-of-the-Art Methods on Question Classification
No full textThe task of question classification (QC) is to predict the entity type of a question which is written in natural language. This is done by classifying the question to a category from a set of predefined categories. Question classification is an important component of question answering systems and it attracted a notable amount of research since the past decade. This paper gives a comprehensive overview of the state-of-the-art approaches in question classification and provides a detailed comparison of recent works on question classification and discussed about possible extensions to QC problem.Computer ScienceElectrical Engineering, Mathematics and Computer Scienc
Advanced Factorization Models for Recommender Systems
No full textRecommender Systems have become a crucial tool to serve personalized content and to promote online products and media, but also to recommend restaurants, events, news and dating profiles. The underlying algorithms have a significant impact on the quality of recommendations and have been the subject of many studies in the last two decades. In this thesis we focus on factorization models, a class of recommender system algorithms that learn user preferences based on a method called factorization. This method is a common approach in Collaborative Filtering (CF), the most successful and widely-used technique in recommender systems, where user preferences are learnt based on the preferences of similar users. We study factorization models from an algorithmic perspective to be able to extend their applications to a wider range of problems and to improve their effectiveness. The majority of the techniques that are proposed in this thesis are based on state-of-the-art factorization models known as Factorization Machines (FMs).Multimedia Computin
From requirements to a research agenda for governments governing reuse of critical raw materials in the circular economy
No full textGovernmental organisations use a diversity of policy instruments for sustainability goals. In the field of materials, they aim to advance the reuse of materials on the one hand. On the other hand, they also want to control critical raw materials (CRMs) to protect society against scarcity. Information sharing is required to monitor for both objectives. Research into information sharing for the circular economy mainly focuses on using ICT to follow entire products, such as digital product passports. However, research into information sharing for reuse flows and monitoring at the level of materials is limited so far. Therefore, in this paper, we derive the following requirements for information sharing to support the monitoring of materials and CRMs in particular: 1) businesses and government organisations should have access to the complete history of materials; 2) businesses should be able to share information on materials between different supply chains and industries; 3) information on materials should be reliable and tamper-resistant; 4) governments should be able to obtain a complete overview of the pool of CRMs in circulation and of who is responsible for them; 5) the system supporting the information sharing on materials should be highly robust and should not have a single locus of control. Based on this overview of requirements, we present a research agenda in which we identify challenges and related future research questions.Information and Communication Technolog
Challenges in the Transition towards a Quantum-safe Government
No full textThe computation power of quantum computers introduces new security threats in Public Key Infrastructure (PKI), a system used by many governments to secure their digital public services and communication. This calls for an inevitable need for governments to be quantum-safe (QS) by modifying their PKI systems to be resistant to the attacks of quantum computers. However, there is limited academic literature on a QS PKI system, and in this limited literature, the transition challenges are perceived as exclusively technological. This paper aims to create a structured overview of challenges when transitioning to a QS PKI system. We do this by reviewing literature and classifying the challenges using Technology-Organization-Environment (TOE) framework and using an expert workshop to explore the challenges in the context of the PKI system in the Dutch government. The main challenges in the technological context include no universal QS solution, legacy system, complex PKI interoperability, and vulnerable Root CA. The main challenges in the organizational context include knowledge gap, unclear governance, lack of urgency, and in-house management support. Furthermore, the main challenges in the environmental context include institutional void, stakeholder collaboration, lack of awareness, and policy guidance. The results indicate that the QS transition from the current PKI system is complex, and the challenges are socio-Technical. For policy-makers, this implies that they should start early to prepare, whereas organizations are hardly aware of the process of QS transition and the topic of quantum computing is yet to develop the urgency in organizations. Information and Communication TechnologyEngineering, Systems and Service
Let's Gamify Open Government Data Portals! the GamOGD prototype
No full textGovernment policies focused on Open Government Data (OGD) often aim to stimulate the provision of public, interoperable data towards any user, including lay citizens, through online portals. However, these OGD portals are primarily developed for expert users. This hinders the realization of transparency, empowerment, and equality of access. This system demonstration paper presents GamOGD, an OGD portal prototype tailored to lay citizens that implements fifteen gamification design propositions.Information and Communication Technolog
Influence of Auxiliary Features in Factorization-based Collaborative Filtering
No full textThe tremendous growth of the Internet brings with it a massive amount of data that users are exposed to on a daily basis. Consequently, information filtering techniques like recommender systems have become increasingly important to sift through the data and find what is relevant to a particular user. A recent approach for recommender systems, called Factorization Machines (FM), has been attracting lots of attention for its flexibility and accuracy. In this work we explore the importance of optimizing FMs, the influence of different auxiliary features on the performance of FMs and how to weight these features. The results show that the optimization of hyper-parameters, factorization dimensionality and feature weights is a very crucial part of using FMs for recommendations. Using static un-normalized feature weights is found to outperform using previously proposed normalized weights in terms of rating prediction accuracy. Several new approaches to auxiliary features are proposed. Expanding feature vectors with info based on the ratio of users that found a review of the item helpful or not is found to improve performance slightly. Additionally, constructing feature vectors using the similarity of users (based on either common movies commented on, common friends or common ratings) was also beneficial to the performance. However, the overall conclusion is that there is no clear answer to which auxiliary features are useful, as it depends heavily on the dataset and in many cases auxiliary features seem to introduce noise into the model. A noticeable trend in the results indicates that item attributes are more useful for rating predictions than user attributes, while the opposite applies for top-N ranking predictions and diversity, which benefits more from user attributes.Electrical Engineering, Mathematics and Computer ScienceMultimedia ComputingEmbedded System
Digital Government and the Circular Economy: Towards an Analytical Framework
No full textCircular economy is high on the political agenda, with governments at all levels setting ambitious goals to move away from traditional linear production models, where goods are used and disposed as waste, towards a future with less use of virgin raw materials, and where valuable materials at a product end-of-life are returned as raw materials or in an environmentally-friendly way to the biosphere. While circular economy is gaining a lot of attention on a policy level, the role that digital government can play to facilitate the circular economy transition is largely unexplored. We carry out a review of existing literature in the fields of digital government and Information Systems (IS) to identify the roles played by digital government in the circular economy. Based on an analysis of 54 empirical research articles, we identify foci and gaps in relation to the different types of roles played by government (nodality, authority, treasure, and organization), to stages of the Product Life Cycle (preuse, in-use, and post-use), and to types of digital technology focused on. Based on these findings, we present an analytical framework to guide future research on digital government in relation to the circular economy, and exemplify the use of the framework drawing on examples from circular economy initiatives in the automotive industry.Information and Communication Technolog
