Automatic Usability Engineering Methods

Optimized usability engineering of interactive services by usability prediction





Motivation & Project Description

• State-of-the-art usability measurement methods still involve subjective tests with human participants, which come late in the service development cycle and at a high expense.
• The aim of this project is to provide usability estimations for multimodal interactive services on the basis of algorithmic models, including
  • Models of human behavior during the interaction
  • Models for predicting usability problems (e.g. ISO 9241)
  • Models for predicting user judgments and hedonistic quality aspects

• This way services can be developed much quicker and cheaper.

Outcome:

• Patent for SpeechEval system (user simulation and judgment prediction)
• Project funding from DFG (revised re-submission): Modellierung von Benutzerverhalten auf techniksoziologischer Basis - Eine neuartige Methodik der Usability-Evaluierung” (with Prof. Rammert)
• Application for 2nd funding phase of the aforementioned UserModel project started
• Project application DFG: COGNITIVE (prediction of user affect for sytem adaptivity and evaluation) submitted
• Project application DFG: Multimodal SpeechEval
• EU-project proposal: Extra-Ling: Development and testing of adaptive systems

• New input modalities (3D Gesture recognition and iPhone GUI) for the INSPIRE Smart-Home System
  
  • DA Florian Greb, Februar 2009
    
  • DA Tilo Westermann, Januar 2010

• Models for describing user behavior in response to the service
  • Parameters for quantifying user/system behavior in multimodal interaction (input parameters to models)
  • Models of user interaction behavior for GUIs and VUIs
  • Identification of relevant quality aspects and their interrelationship
  • Models for predicting usability aspects and user judgments on the basis of interaction parameters