One of the studies I did here at Human-Computer Studies on people’s interaction with adaptive and autonomous systems investigated user interaction with spam filters. While spam filters might not appear the most exciting subject, exploring users’ interaction with them actually offers quite some interesting insights for developers of adaptive and autonomous systems. Spam filters are one of the few types of systems that take semi-autonomous decisions on the user’s behalf AND are actually used in a real-life context by many, many people. They often can also be trained and sometimes operate on somewhat nontransparent criteria.
In this study, I investigated interaction with both adaptive (trainable) and non-adaptive, rule-based filters. Turns out that while many of our participants who used an adaptive filter invested a lot of effort in training, this didn’t increase their trust, nor the level of autonomy they granted their filters; investment doesn’t always translate into acceptance. Additionally, small, sub-optimal interface design features such as filters icons caused many participants to not understand interface items, induced ‘incorrect’ training behaviour and uncertainty about filter activity. It’s interesting that while research on developing adaptive and autonomous systems is on the rise, we haven’t as a community solved some of the seemingly ‘mundane’ interface design issues on less complex systems such as spam filters.
Paper will be available as: Henriette Cramer, Vanessa Evers, Maarten van Someren, Bob Wielinga, Awareness, Training and Trust in Interaction with Adaptive Spam Filters, CHI’09. Will post link to the paper as soon as it’s available.
Not only has the note been accepted, it’s also been nominated for a best note award!
This weekend I’ll give a talk on trends in mobile HCI at the Amsterdam MobileDevCamp on 29 + 30 November. It will be an intro talk trying to get coders to not only focus on novel interaction methods and all things techie, but also into considering social interaction with mobile systems and areas such as mobile persuasion.
Check out www.mobiledevcamp.nl. “A full weekend devoted to developing mobile applications for the iPhone, Android and Symbian platforms. Organised by the Bubble Foundry and hosted at Mediamatic” The sign up procedure is somewhat cumbersome (uses upcoming.org), but it’s free and there’s lots to learn. It’s good to see these type of open events are being organized. Amsterdam needs more of them.
More research-related, I’ll also be participating in the workshop on mobile user interaction at CHI next spring. Still waiting for notifications on the rest of the stuff we sent off to CHI. Already read some quite favourable reviews, so fingers crossed for the final notification [update dec 2008: accepted. I’ve got a note on interaction with adaptive spam filters and two workshop papers; one on human-robot interaction, one on mobile interaction].
Meanwhile I’m also working on our experiment on human interaction with autonomous mobile systems. The experiment context will be an environmental hazard monitoring system that uses information from both a sensor network and human users via mobile devices/phones. The overarching project aims to prevent catastrophic chemical incidents and reduce pollution through quick detection of harmful gasses and identification of pollution sources. If a potential hazard is detected or reported, the system will use human observation in and around the affected area to gather more information. Participating users will be asked by their mobile agent (e.g. application or service on phone/PDA) to self-report their observations. If necessary, the system provides location-based warnings. I’ll be carrying out a controlled experiment on effects of social behaviour of the system and its positioning as a distant entity that both caters to users but also ‘uses’ them as sensors for its own means.