Mobile Media Metadata (MMM)

Mobile phones with media creation capabilities are rapidly entering the marketplace in the USA and already have significant market presence in Asia and Europe. In 2003, there were more cameraphones sold worldwide than digital cameras. cameraphones will bring about a revolution in consumer imaging because they are not only networked, but programmable. Software developers can write applications for these mobile imaging devices, and software can fundamentally change the imaging experience at the point of image capture. The opportunity is to create software solutions for cameraphones that can address long standing challenges in consumer media creation, sharing, management, and reuse in a fundamentally new way. We can do this by leveraging the spatio-temporal context and social community of media capture and use (when, where, and by whom media is captured, shared, and used) to infer media content, context, and community and thereby help automate media annotation, retrieval, sharing, and reuse. As a result of this approach, we believe we will solve a fundamental problem in consumer adoption of mobile media services: the need to have content-based access to the media consumers capture on their mobile devices.

We have conducted fairly large scale deployments and user testing of our MMM prototypes with 60 users using MMM1 on the Nokia 3650 cameraphone in 2003-2004 and 60 users using MMM2 on the Nokia 7610 cameraphone in 2004-2005. Our SIMS graduate student users in IS202 Information Organization and Retrieval have also worked in project teams to develop numerous innovative mobile media application concepts based on MMM1 and MMM2.

Mobile Media Metadata 2 (MMM2)

In our MMM research, we leverage regularities in media and metadata created by communities of users that share common spatial, temporal, and social contexts to make inferences about the content, context, and community of media captured on mobile devices (especially cameraphones). MMM2 uses "context-to-community" inferencing to support the sharing of mobile media by inferring the likely recipients for media captured on cameraphones based on the user's and the community's prior sharing history and contextual metadata such as the time of capture, CellID and GPS location, and Bluetooth-sensed human co-presence. We have seen a 2189% increase in the number of photos uploaded per user per day in MMM2 (1.31) compared to MMM1 (0.06) which seems due to several factors: better image quality (VGA vs. 1 megapixel image resolution, "night mode" for low light, and digital zoom) in the Nokia 7610 vs. the Nokia 3650; familiarity of the user population with cameraphones (12 prior cameraphone users in 2004 vs. only 1 in 2003); the availability of only one, rather than two camera applications in MMM2 vs. MMM1; automatic background upload of photos to the MMM2 web photo management application; and automatic suggestion of sharing recipients on the cameraphone and in the web application. Our qualitative and quantitative studies have shown that MMM2 users are pleased with the share guesser's ability to suggest sharing recipients based on prior sharing history and contextual metadata and share on average 26% of the photos they capture and upload with MMM2.

Mobile Media Metadata 1 (MMM1)

Using this approach, MMM1 guessed the correct location of the subject of the photo (out of an average of 36.8 possible locations) 100% of the time within the first four guesses, 96% of the time within the first three guesses, 88% of the time within the first two guesses, and 69% of the time as the first guess.

This sister project lead by Prof. Nancy Van House is investigating a central problem for technology design: predicting users and uses for emerging technologies, i.e., doing user-centered design for users and uses that don't yet exist. This is especially true in the case of mobile media technology and applications, in particular cameraphones, which are undergoing rapid growth and transformation. Designers of mobile media technology and applications in industry and academia need new methods to project and design for future uses and users of mobile media. We use the term "social uses" to describe the higher level motives that guide the specific actions that users perform. For example, while we may observe that a user performs the action of emailing a photo to family members, this action (i.e., "what" the user does) is not the same as the motive informing the action (i.e., "why" the user does it), in this case to maintain the social relationship. Our social science research has uncovered several significant social uses of personal imaging technology which designers of imaging and mobile media technology need to understand and design for: constructing personal and group memory; creating and maintaining social relationships; self-expression; self-presentation, and functional uses for oneself and others.. These social uses and the associated findings from our social science research have significant implications for mobile media technology design and inform our development of design methods aimed at projecting and designing for future uses and users of mobile media technology.