Detecting Memory-Based Interaction Obstacles with a Recurrent Neural Model of User Behavior
by , ,
Abstract:
A memory-based interaction obstacle is a condition which impedes human memory during Human-Computer Interaction, for example a memory-loading secondary task. In this paper, we present an approach to detect the presence of such memory-based interaction obstacles from logged user behavior during system use. For this purpose, we use a recurrent neural network which models the resulting temporal sequences. To acquire a sufficient number of training episodes, we employ a cognitive user simulation. We evaluate the approach with data from a user test and on which we outperform a non-sequential baseline by up to 42% relative.
Reference:
Detecting Memory-Based Interaction Obstacles with a Recurrent Neural Model of User Behavior (Felix Putze, Mazen Salous, Tanja Schultz), In Proceedings of the 2018 International Conference on Intelligent User Interfaces, ACM, 2018.
Bibtex Entry:
@inproceedings{putze_salous_2018iui,
  author={Putze, Felix and Salous, Mazen and Schultz, Tanja},
  title={Detecting Memory-Based Interaction Obstacles with a Recurrent Neural Model of User Behavior},
  booktitle={Proceedings of the 2018 International Conference on Intelligent User Interfaces},
  series = {IUI '18},
  year = {2018},
  isbn = {978-1-4503-4945-1/18/03},
  location = {National Center of Sciences Building, Tokyo, Japan},
  pages = {205--209},
  numpages = {5},
  url={https://www.csl.uni-bremen.de/cms/images/documents/publications/putze_salous_2018iui.pdf},
  doi = {10.1145/3172944.3173006},
  publisher = {ACM},
  address = {Tokyo, Japan},
  keywords = {Classification of user behavior, memory, interaction obstacles, LSTMs},
  abstract={A memory-based interaction obstacle is a condition which impedes human memory during Human-Computer Interaction, for example a memory-loading secondary task. In this paper, we present an approach to detect the presence of such memory-based interaction obstacles from logged user behavior during system use. For this purpose, we use a recurrent neural network which models the resulting temporal sequences. To acquire a sufficient number of training episodes, we employ a cognitive user simulation. We evaluate the approach with data from a user test and on which we outperform a non-sequential baseline by up to 42% relative.}
}