Ellen Isaacs - PARC blog

The “channel blending” (vs. multitasking) phenomenon — and opportunities

24 February 2012 | Ellen Isaacs

A little while ago we did some exciting research with Sony using a novel approach to studying mobile communication. We identified small groups of friends and family who like to stay connected and video-recorded them for a half-day as they went about their activities -- we were able to capture each person's point of view as they connected, engaged, and disconnected with one another, sometimes through technology and sometimes face-to-face. (Some folks at CSCW 2012 commented that this looked like stalking!) Through this study, PARC identified a phenomenon we call "channel blending", which, in contrast to multi-tasking, is the blending together of interactions and content across multiple channels, devices, and places into a single, coherent conversation. We identified a gap in current communication technology and opportunities for addressing it.

The Web is finally starting to behave like a butler

19 January 2010 | Ellen Isaacs

When the Web was just beginning to take hold back in the mid-1990s, I remember thinking, “This is great for getting access to information, but it’s setting user interfaces back about 10 years.” It's now 15 years later, but I’m happy to say that we’ve caught up and are finally starting to surpass where we left off. The Web has moved from a face without a brain, to just a pretty face, to a helpful butler that supports users' tasks and anticipates their needs in an unobtrusive way.

Experts’ domain knowledge improves automated recommendations

9 November 2009 | Ellen Isaacs

It’s almost eerie how well the music website Pandora recommends music based on just one example of a favorite song. It does so by relying on human experts to characterize songs based on a large and musically sophisticated set of characteristics (melody, harmony, rhythm, orchestration, etc.). This approach -- of using human expertise to develop a rich set of attributes that deeply capture the essence of an item -- could be adapted to greatly improve the recommendations currently being offered in other domains, such as news, movies, hotels and so on. In our enthusiasm to develop automated recommendation systems, Pandora reminds us of the value of incorporating the intelligence of domain experts into the process.

Can a recommender choose what’s best?

7 July 2009 | Ellen Isaacs

While doing a user experience evaluation of a mobile recommendation system, I noticed how the list-based design implied that there was a single best choice, with 'goodness' decreasing in even increments. This made me wonder whether it makes sense to try to identify the one Best option when you're choosing among options that vary across many dimensions. Making choices might be easier if we assume that there is rarely one single Best.