Projects

TBA

Team:

• Kwabena Odame Akomeah

Contact:

Kwabena Odame Akomeah

An Empathetic Conversational Agent for Weight Loss Treatment

The increasing rate of obesity in the German population calls for the development of new treatment options as a way to reduce costs on the public health care system and increase treatment success.

This project explores possibilities of automated empathetic conversation to support traditional obesity treatment. The constant availability of a conversational agent could solve problems related to weight loss as soon as they arise and help with impulse control. The non-judgemental nature of such a system as opposed to counsellors or peers has the potential to lower the user’s inhibitions and increase honesty in conversations about sensitive topics.

In the long term, such a conversational agent could be a valuable tool in the treatment and prevention of obesity.

Team:

• Selina Meyer, M.A.
• PD. Dr. David Elsweiler
• Prof. Dr. Bernd Ludwig

Contact:

Selina Meyer, M.A.

A Social Media Companion Safeguarding and Educating Students

This project aims to develop a Social Media User's Virtual Companion that educates and supports teenage school students facing the treats of social media such as discrimination and biases also escalating to hate speech, bullying, fake news and other toxic content that can strongly affect the real world.

The Companion will raise awareness of potential threats in social media while still providing a satisfactory experience through the use of novel gamification strategies and educative information selection algorithms. Using hand defined gamification strategies based on the concept of interactive counter-narrative together with a learnt model of diffusion of biased, hateful and general toxic content on the social media, the companion will bootstrap learning of strategies for interaction and information selection.

These strategies will be refined and personalized for each user and his social niche with the dual aims of (A) improving and creating healthy social relationships between the user, his peers and the targets of bias, as well as(B) increasing their understanding of the social effects of toxic content in social media and the user role in its propagation.

Experimentation will use data mined from real social media and re-enact them for testing in restricted and controllable conditions (eg. schools, classes).

Team:

• Prof. Dr. Udo Kruschwitz

Consortium:

University of Applied Sciences Ruhr West (Bottrop, Germany)

L'Istituto per le Tecnologie Didattiche - CNR-ITD (Palermo, Italy)

University of Essex (Colchester, UK)

Universitat Pompeu Fabra (Barcelona, Spain)

Rhein-Ruhr Institute (RIAS), (Duisburg, Germany)

University of Milano-Bicocca (Milano, Italy)

Funding:

VolkswagenStiftung

Contact:

Prof. Dr. Udo Kruschwitz

FoodChoice - Modelling & Changing Online Food Choices through Recommenders

Studying how people upload and browse online recipes has recently become an active field of research. While there is a growing body of work investigating which types of food are consumed and how this relates to real-world health related issues, such as e.g. diabetes or obesity, little research focus has yet been devoted to understanding how people make their food choices online, how they are influenced by certain contextual factors, how this behavior can be modelled or how this behavior can be changed. With respect to the last problem, recommender systems - such as those used by online stores to suggest products customers might like- are often touted as part of the solution. However, very little literature exists describing to which extent food preferences can be changed or the different effects different algorithmic approaches can have. In response we initiated a cross-border research project FoodChoice, which aims to not only to provide a better understanding regarding how certain factors, such as temporality, user geography and social relations between users influence the food choices people make online, but to moreover investigate how this behavior can be modelled and changed through novel health-aware recommender algorithms.

Team:

• PD Dr. David Elsweiler
• Dr. Christoph Trattner (University of Bergen)
• Prof. Dr. Bernd Ludwig

Corroborate: Understanding and Supporting the Information Credibility Judgments People Make Online

Making credibility judgements in information environments, such as the web is challenging because, in contrast to traditional print and broadcast media, often no quality control mechanism exists. This places increased emphasis on user information literacy skills, including their ability to evaluate information critically. These are skills, which people, regardless of education level, tend to overestimate (Gross 2012). Moreover, recent IR research has emphasized that user actions while seeking information, as well as the perception of information found is biased in countless ways. Although credibility judgements for web pages and SERP snippets have been well studied, we still know relatively little about how such evaluations are made and how they may be affected by user biases. This project aims to broaden our understanding of how people judge credibility, how successful they are, and what determines this. We further aim to design systems to support the critical evaluation of information informed by the improved better understanding the processes and biases involved.

Team:

• PD Dr. David Elsweiler
• Dr. David Losada
• Dr. Markus Kattenbeck (TU Wien)

URWalking - University of Regensburg Walking

Do you remember the last time you had to ask for the way? Have you been told to turn right after 250 meters? Probably not because people normally tend to remember landmarks to find their way.

The tangled ways to get around campus can be used to test landmark-based pedestrian navigation systems. The URWalking project appeals widely to our students.

Project head: Prof. Dr. Bernd Ludwig

Understanding food culture with digital traces

The aim of our project is to use the traces of human behavior with online recipes to explore the differences in food culture across the world. We are now focusing on the visual aspects of the images associated with recipes. Based on the Explicit Visual Features (EVF) and Deep Neural Network image embeddings (DNN), we plan to dig out how food culture distributed and the aesthetics of preferred recipe images within and across cultures. Techniques related to computer science, information science and data science would be employed in our project. We have done a couple of experiments on three datasets which sourced from three large recipe platforms from China, Germany and the United States, which shows that using visual features as mentioned above, 1) we could train classifiers to differentiate the images from these three collections; 2) it is also possible for us to predict if a recipe is appreciated or not, although the accuracy is not so satisfied. 3) visual tastes of German and US are more similar to each other than those of the Chinese.
These findings suggested that there are indeed differences in the visual aspects of online recipes. In the future work, we will cooperate with anthropologists to figure out how the differences generated and how to explain them.

Funding and Cooperation:

University of Bergen

Phobias trigger panic attacks on millions of people and can severely restrict their daily lives. Psychological treatment is usually done with exposure sessions that deal with the anxiety trigger in a controlled manner.

In the OPTAPEB project, a system was developed that enables VR-based exposure therapy with a virtual agent. The emotional reactions of the client during exposure were processed by a multimodal sensory system followed by data fusion. From this, therapeutic microinterventions jhave been derived from the virtual agent or environment. As a result, the therapeutic treatment has been meaningfully expanded and e. g. be continued and deepened in the living room.

Network coordinator: University of Regensburg

Project partners:

• VTplus GmbH, Würzburg

• Fraunhofer-Institut for integrated?circuits (IIS), Erlangen

• Ambiotex GmbH, Tübingen

• New Textile Technologies GmbH, Balingen

• audEERING GmbH, Gilching

• ZTM Bad Kissingen GmbH, Bad Kissingen

Duration: 09/2017 - 08/2020

Funding: Federal Ministry of Education and Research (BMBF)

Route Calculation with Regards to General and Individual User Preferences

As part of the URwalking project, the PhD project of Dipl.-Inf. Manuel Ullmann aimed to to provide users with alternatives to the shortest routes. Machine learning techniques are used to simulate the behavior of real users when calculating new routes. This approach enabled us to suggest routes whose natural course is easier to follow and to remember. The developed procedures also allow for the consideration of individual persons or groups of persons.

BORIS - Bar Ordering and Information Systems

As part of the project a speech and touch based dialog and recommendation system was developed. BORIS recommends and prepares cocktails based on context.

ATiZu@Web - Conception and Implementation of a Platform to Support Scientific Research as Part of the EU-Project 'Starting in Tradition'

The INTERREG-project 'starting in tradition' aimed to explore the linguistic and literary legacies of Southern Bohemia and Eastern Bavaria.

We worked alongside the universities of Passau and Budweis and supported our partners with information science know-how by developing a web application for research purposes. This application provided various ways to search for information, for example by maps. Furthermore, we developed a mobile app which enables layman to access the research findings.?

Cooperation partners: University of Passau and University of Budweis

DIVIS - Digital Indoor Localization with Inertial Sensors and Landmarks

The research project 'DIVIS' was done in cooperation with NEXOE Applications GmbH, Regensburg, to develop a positioning technology for indoor navigation systems, which help pedestrians to get safely to their destination. Not only integrated smartphone sensors were used, but also image and speech recognition.

Duration: 08/2016 - 10/2019

Funding: FuE-Program ?Information - and Communication Technology“ of the Free State of Bavaria

URWalking sub-project

Assistance of Indoor Orientation - Analyzing Landmark Based Map Interfaces on the Basis of Eye Movement of the User

This PhD project of Dr. Christina Bauer was a sub-project of URWalking. It evaluated different map representations containing reference objects with a high salient. This was done by studying the eye movement of users. A mobile eye tracker was used for this. The focus of this research was how users take in the interface and environment while navigating indoors.

Team:

• Dr. Christina Bauer
• Prof. Dr. Bernd Ludwig

App based Support of Dietary Changes

PhD scholarship holder Elinor Brondwine M.Sc. engaged in a research project about diet in the context of healthcare. The goal was to provide patients a way to follow a medically prescribed diet.

Funding: Centre of digitization.Bayern Fellowship (ZD.B Fellowship), BayWISS-Verbundkolleg Gesundheit

Refinding Tweets - Analyzing the Personal Information Management Practice Refinding in the Context of Twitter

Florian Meier M.A worked as part of his PhD project on the following questions:

• What motivates users to find tweets that they have seen before?

• Which methods are applied to this?

• How does Twitter provide support to accomplish this task?

The leading question was however how search user interfaces of social networks can be optimized in attention to the information need of refinding. ?

Dipl.-Inf. (FH) Markus Fuchs M.A focused on feedback systems in the context of teaching in higher education during his PhD project. Classgame is an online learning management system with gamification elements which was developed to help students practice programming. The system is still used? in classes at the Chair of Information Science. ?

URTalking - University of Regensburg Talking

In the seminar 'Methods of Natural Language Processing' students worked on a course guidance chatbot to help students on campus with their studies. This seminar was guided by apl. Prof. Dr. Reischer.

Project head: apl. Prof. Dr. Jürgen Reischer

NADINE - Navigation in the Context of Public Transportation

As part of the project “NADINE - Navigation in Public Transport with a Modular Service Architecture for Integration in External Applications” we worked on the implementation of a landmark based navigation.
This project was realized as part of a program called “From Door to Door – A Mobility Initiative for the Public Transportation of the Future”.

Duration: 09/2012 - 08/2015

This project was a cooperation with the HEITEC AG Erlangen.

In his PhD project Stefan Bienk worked on the question on how to predict senior citizens' increased risk of falling.

Duration: ?

Phase 1: 04/2011 - 12/2012

Phase 2: 01/2013 - 06/2014

Funding: BMBF-Spitzencluster Medical Valley.

Dr. Ludwig Hitzenberger (Chair of Information Science), Prof. Dr. Christian Wolff (Chair of Media Informatics) and the University of Erlangen worked together to create a prototype system which can change its content depending on eye movement analyses.

This project was purely pushed by students and focused on creating an archive of audio visually edited content of classes.

TransRouter - Translation Router (Telematics Applications of Common Interest - Language Engineering)

TransRouter was a system designed to help users with decision making in the context of translation projects planning.

During this project profiles to describe texts, speech data, translation tools and translators were developed as foundation of the decision process. Based on this, an algorithm was developed. A graphical and interactive user-interface supports the selection process. Three prototypes of the system were developed and evaluated through user tests.

Members of the consortium: Berlitz, Bublin;CST, Kopenhagen; University of Edinburgh; TIM/ETI; University of Genf,; Lernout and Hauspie, Munich;LRC, Dublin; University of Regensburg

Funding: Commission of the European Communities: DG XIII, Telecommunications. Information Market and Exploitation of Research, Berlitz Ireland Ltd. (Berlitz GlobalNet.).

SMMI (Phase I/II/ MOST/ III/IV) - Mixed Mode Interaction: Subproject “Speech Control Concepts for Navigation Devices and Telephones” and “Rhapsody Modelling”

The most important part was creating a generic class library to describe dialog and the integration of universal dialog functionalities.

Funding: Audi AG, Ingolstadt

MIROSLAV - Machine Translation Initiative for Russian and other Slavic Languages

Our objective was to include the East European languages to the standards of machine based language processing of the rest of Europe. This included foundational research and application of the findings.

SIMBA - Language Based Interaction with an Intelligent Front-Seat Passenger

Design, implementation and experimental study of acoustic operating instructions.

Funding: Daimler-Benz Research, Stuttgart

ACCESS - Automated Call Center Through Speech Understanding

The team built a dialog evaluation tool for call centers. The dialogs were analyzed and Wizard of OZ experiments conducted to design natural language based dialogs.

Project partners: DASA, Ulm; Daimler Benz, Researchcenter, Ulm; Interamerican, Athen; Toshiba, Regensburg; Tellit Direkt Versicherung, Bergisch-Gladbach; University of Patras; WCL, Patras.

Funding: Daimler Benz, Researchcenter, Ulm; European Union, Telematics Applications Program Nr. LE 1802-10347/0; Daimler-Benz Aerospace AG (DASA), Ulm.

WING-IIR - Material-Information-Systems with Natural Language/ Graphical User Interfaces and Intelligent Information Retrieval

This project was based around a material document database to develop an information system with a multi modular user interface and an intelligent IR component.

Application-partner (selection): motor - and turbines - Union Munich GmbH (MTU), Institute for Advanced Materials at the Joint Research Centre of the EG in Petten, Netherlands

Funding: Federal Ministry of Economic Affairs and Energy

ComfoLIR - ComfoTex & Linguistic Information Science in Regensburg

In a research project the user interface of Siemens’ text processing program ComfoTex was evaluated and an intelligent help system ComfoHelp was developed.

Funding: Siemens Nixdorf Information Systems (SNI)

DICOS - Dialogs with a Computer in a Natural Language

The project focused on human speech behavior in the context of human-computer-interaction. The differences between interpersonal communication and human-computer based interaction have been analyzed in library and train station information points.

PADOK - Patent Documentation

For the development of a German patent information system several subject cataloging methods were evaluated (e.g. via retrieval testing).

Funding: ?Federal Ministry of Economic Affairs and Energy

COBIS - Computer Based Office Information Systems

CONDOR, a natural language based information acquisition system of Siemens, was tested in office situations. The focus was to increase the efficiency in office work and using dialog based information systems to improve communication at the workplace.

Funding: Federal Ministry of Economic Affairs and Energy, Daimler-Benz AG Stuttgart-Fellbach ?

JUDO - Legal Document Analysis

The project was primarily concerned with the exemplary development of a software to process legal texts in a linguistic way.

Funding: Federal Ministry of Economic Affairs and Energy

COBAPH - COBOL-Basic Program for Philology

Focus of this project was the development of a text processing system COBAPH, which was responsible for the generation of alphabetical and frequency based word-indexes.