Project: Mobile Interaction Design for Adaptive Services

People: Dr. Wolfgang Wörndl, Florian Schulze, Béatrice Lamche, Prof. Dr. Johann Schlichter

Adaptive services such as recommender systems personalize information access to improve the user experience. Delivering accurate and timely information is particularly valuable when using mobile devices. This is due to restrictions in the user interface of mobile devices and limited attention spans of mobile users. The main question is how users interact with these mobile recommender and other adaptive services. These projects investigates this question in several sub- and Ph.D. projects. 

Related projects: Context-aware Recommender Systems in Mobile Scenarios & Mobile User Modeling

Subproject: Smart Notifications

People: Florian Schulze

  • Smart notifications for proactive recommendations
  • Sensor-based identification of opportune moments for mobile notifications
  • Adaptive and personalized notification models
  • Notification modalities subject to context and score of recommended item

Subproject: Conversational Mobile Recommender Systems

People: Béatrice Lamche


  • Limitations in the user interface
  • Limited attention span while moving
  • Importance of context (e.g. location, time)
  • Cognitive overload
Research Topics:
  • Interactive dialogues and explanations in recommender systems
  • Proactive and sensor based recommendations
  • Elicitation of user's preferences based on flexible user interfaces
  • Improvement of user experience by novel interaction patterns


Subproject: Distributed User Interfaces for Recommender Systems

People: Dr. Wolfgang Wörndl

Recommender systems recommend movies, products or other items to an active user or user group based on ratings of items or other information about users and items. For group recommender systems, an additional requirement is to facilitate the agreement process among group member to select an item. For example, users may want to go to a cinema together to watch a movie. They could rate some movies on their personal mobile devices and the system could present recommended items on a shared display such as a multi-touch tabletop.The group can then use the tabletop to refine the query and finally select a movie. This separation in the user interface is also called "distributed user interface". In this subproject, the goal is to investigate distributed user interfaces for individual and group recommender systems in more detail.

Subproject: A Gesture-based User Interface for Context-aware Recommender Systems on Tablets

People: Dr. Wolfgang Wörndl, Florian Schulze

When designing user interfaces for recommendation and search applications on mobile devices such as tablet computers, one not only has to cope with technical limitations like the reduced screen size and the lack of comfortable input methods. It is also important to consider supportive interaction patterns to allow users to easily express search preferences. We present a minimalistic interface for explorative search using touch gestures for adjusting parameters. The main idea is to use the same gestures for various filter criteria as on a map view.

Selected Publications

 Selecting Gestural User Interaction Patterns for Recommender Applications on Smartphones

 Autoren: Wolfgang Wörndl, Jan Weicker, Béatrice Lamche
 Beschreibung: In Proc. Decisions@RecSys workshop, 7th ACM Conference on Recommender Systems, Hong Kong, China Oct. 2013 (to appear)

 A Gesture-Based Interface for Map-based Exploratory Search on Tablets

 Autoren: Florian Schulze, Wolfgang Woerndl, Michael Ludwig
 Beschreibung: Mobility and Web Behavior Workshop, MobileHCI Conference, San Francisco, CA, USA, Sep. 2012

 Using Touch Gestures to Adjust Context Parameters in Mobile Recommender and Search Applications

 Autoren: Florian Schulze, Wolfgang Woerndl
 Beschreibung: Workshop on Collaboration: Human-Centered Issues & Interactivity Design (CHCI & ID 2011), Collaboration Technologies and Systems (CTS 2011), Philadelphia, PA, USA, May 2011

All publications of our chair