Home // CENTRIC 2017, The Tenth International Conference on Advances in Human-oriented and Personalized Mechanisms, Technologies, and Services // View article

Dynamic Scrutable User Modeling utilizing Machine Learning

Authors:
Dima S. Mahmoud

Keywords: Personalization; User Modeling; Machine Learning; Scrutability

Abstract:
Personalization generally attempts to offer information and services that are delivered to meet user's individual preferences. It helps by providing the appropriate services in a dynamic and automatic manner. Involving the user in this process may enhance how tailored information and services are delivered. However, there is a challenge in engaging users in the user modeling process. Building user models in a manner that engages the user in a feedback cycle may improve the quality of the model and the user’s control over the personalization. Allowing such user control over machine learning-derived user models is a significant research challenge as such models are often difficult to scrutinize. This is the main challenge addressed in this early stage research. This work proposes using ontology-based domain models to provide a means for users to engage with ML-derived models. Moreover, such an approach may enable the user model scope to grow as a user’s preferences grow.

Pages: 18 to 23

Copyright: Copyright (c) IARIA, 2017

Publication date: October 8, 2017

Published in: conference

ISSN: 2308-3492

ISBN: 978-1-61208-592-0

Location: Athens, Greece

Dates: from October 8, 2017 to October 12, 2017