One of the most important concerns in the field of adaptive information systems is to model human behaviour in order to offer personalisation and recommendation. This usually involves implicit or explicit knowledge about a user's preferences and behavioural patterns.
In this talk, I report on the lack of reliability of explicit user feedback and its interpretation in the light of system evaluation. By using probabilistic perspectives as used in metrology and physics as well as neuroscientific theories of the Bayesian brain, I will introduce novel user models with more empathy for the human nature. By means of user experiments and simulations, I will show that this information can be used to improve the standard collaborative filtering.
While semantic data models are increasingly relevant for scientific and business tasks, working with semantic data still remains complex and error-prone. This, in part, is due to the inadequate integration of related technologies in common programming languages. The research language λDL was developed to remedy this concern, by introducing static checks: It uses description logics, the underlying formalism of OWL ontologies, to provide a type system for semantic data. This thesis is based on λDL and aims to transfer the approach to the functional programming language Scala and the widely used semantic query language SPARQL.
Computational models of argumentation are logic-based formalisms for knowledge representation that allow for the explicit modelling of automatic reasoning in terms of arguments, counterarguments, and their interplay. In this talk I give an overview on the core formalism in this area, abstract argumentation frameworks, and discuss its algorithmic issues.
News streams have several challenges for the past, present, and future of events. The past hides relations among events and actors; the present reflects needs of news readers; and the future waits to be predicted. The thesis has three parts regarding these time periods: We discover news chains using zigzagged search in the past, select front-page of current news for public, and predict future public reactions to events.
User experience includes all the users' emotions, beliefs, preferences, perceptions, physical and psychological responses, behaviors and accomplishments that occur before, during and after use of a system or service. In this talk, I will give a brief introduction to user experience concepts, common methods and practices. Furthermore, I will present the case of eye-controlled applications: several gaze interaction approaches introduces novel ideas which are 'useful', but are they 'usable'? In this regard, I would discuss how the current research ignores some important aspect of user experience, limiting eye tracking as a tool for general usage. GazeTheWeb will be discussed in brief with respect to user experience.
The aim of the research project GazeMining by WeST and EYEVIDO GmbH is to capture Web sessions semantically and thus obtain a complete picture of visual content, attention and interaction. This talk will give you insight to our first ideas, how to utilize both the structural and the visual data of a Web page to achieve the described goal. We propose a layer definition from the structural data, segmentation of each user session into visual states for each layer, combination of the states across the users and eventually the extraction of components on the Web page, like carousels or menus. The talk is concluded with an open discussion to gather feedback about the presented approach and to think about further challenges and use cases.
Over the last years, vector space embeddings have evolved to be the popular approach for including semantic information in neural-network-based machine learning architectures. Word embeddings map words to a latent continuous vector space with the goal to have similar words appear close together in the vector space. Knowledge graph embeddings map semantic triples into vector spaces with the goal to predict unseen triples from this representation. However, almost all developed embedding approaches are only capable of offline training, i.e., should new training data become available or old invalid, embeddings will have to be retrained from scratch.
Analysing human activities becomes one of the important research topics in recent years due to the fast and dramatic development of security issues in public spaces. In crowded environments, it is highly important to analyse the activities that arise from people's mobilities. In other words, the activities that can be expressed by the sequential positions of people (trajectories). The reason for this is the theory that these trajectories symbolise high-level interpretation of human activities. However, several factors make studying people's activities based on their mobilities a challenging task. Specifically, the vast diversity of possible activities that people may perform yield to a very complex recognition because of the high inter-class similarity.
Misinformation generates misperceptions, which have affected policies in many domains, including economy, health, environment, and foreign policy. Co-Inform is about empowering citizens, journalists, and policymakers with co-created socio-technical solutions, to increase resilience to misinformation, and to generate more informed behaviours and policies.
Compliance knowledge bases contain declarative business logic, meant to ensure that business processes are aligned towards company goals and regulations. Maintaining the quality of respective knowledge bases is widely recognized as a challenging task. A significant problem here is a potential inconsistency of knowledge bases, as this impedes the actual use of respective artifacts. Such inconsistencies can result from the incremental, often collaborative, creation of said knowledge bases. We investigate how quantitative measures can be used to assess the severity of inconsistency for individual elements of compliance knowledge bases.