Research Projects

Various technologies are now available that provide context-aware support for such informal online learning. In the case of formal and structured learning, the learning material is provided by a well-trusted instructor whereas in the case of a context-aware system that assists online learning there is a lack of such a trusted entity. Additionally, there is a lack of information about how the learning material is selected by the system. Providing users with the system-generated explanation of the basis of the selection of the learning material could help increase trust. An explanation has been found to be useful in building trust towards automated and AI systems but there is no evidence of the usefulness of explanation in building trust towards context-aware online learning assistants (CALA). In this project,  we investigate explanation for building towards CALA and investigate users' perception towards explanation and trust in the context of a context-aware system meant for educational purposes. 

With advances in areas such as sensors and machine learning, wearable technologies will have increased potential to support our daily lives. Even though today’s landscape of smart wearable devices is highly varied, the real-world adoption of wearables has remained lukewarm. We propose that a key reason is that we currently only have a surface-level understanding of people’s interaction behaviors with wearable devices. A deeper understanding of user behaviors towards different wearable devices will help to inform wearable design for more seamless user experiences. We present an empirical study with 50 participants that explore people’s micro-behaviors towards five types of smart wearable devices (wristband, ring, clip, necklace, glasses) in a lab-based information-gathering context. A micro-analysis of participants’ session videos and interviews showed that people have different behaviors and attitudes in terms of affordances and functionality for different forms of wearables giving rise to a variety of design implications.

We often get questions about the processes and things that we observe in our surroundings, but there exists no practical support for exploring these questions. Exploring curiosity can lead to learning new science concepts. We propose using a post-event recall and reflection approach to support curiosity-inspired learning in everyday life. Our approach involves capturing contextual cues during the curiosity moment with wearables that can capture these contextual cues in daily life, and later using them for recall and focused reflection. Firstly, we conducted a preliminary study to explore different cues and their effectiveness in recalling these curiosity moments. Further, we conducted a virtual study to evaluate the amount of exploration through post-event recall and reflection and compared it with insitu recall and reflection. Results show a significant increase in questions and reflections made with the post-event recall and reflection approach, providing evidence for better learning outcomes from everyday curiosity.

Wearable devices are a popular class of portable ubiquitous technology, which is available in a variety of forms. The fact that smart wearable devices are attached to the body makes them particularly suitable to be integrated into people’s daily lives. We propose that wearables can be particularly useful to help people make sense of different kinds of information and situations in the course of their everyday activities, in other words, to help support learning in everyday life. While there are research on wearable use in the learning context, it is mostly limited to specific settings and usually only explores wearable use for a specific task. The smartwatch/wristband, followed by the smart glasses, was the most preferred wearable form factor to support learning. 

Various technologies are now available that provide context-aware support for such informal online learning. In the case of formal and structured learning, Additionally, there is a lack of information about how the learning material is selected by the system. Providing users with the system-generated explanation of the basis of the selection of the learning material could help increase trust. An explanation has been found to be useful in building trust towards automated and AI systems but there is no evidence of the usefulness of explanation in building trust towards context-aware online learning assistants (CALA). In this project,  we investigate three levels of user control for effective use of recommender system supporting web-search based and investigate users' perception towards explanation and trust in the context of a context-aware system meant for educational purposes.