Seminar Type: Invited Speakers
Title: Using Better Predictions to Help You Find Files (Talk #1)
Start Time: 06/21/2012 - 14:00
End Time: 06/21/2012 - 15:00
Location: ICT 618B
Speaker: Stephen Fitchett, University of Canterbury in New Zealand
Abstract:
AccessRank is a new algorithm that predicts revisitations and reuse in many contexts, such as file accesses, website visits, window switches, and command usage. AccessRank uses many sources of input to generate its predictions, including recency, frequency, temporal clustering, and time of day. Simulations based on log records of real user interaction across a diverse range of applications show that it more accurately predicts upcoming accesses than other algorithms. The prediction lists it generates are also shown to be more stable than other algorithms that have good predictive capability. This is important for usability when items are presented in lists, as users can rely on their spatial memory for target location. This talk will firstly introduce AccessRank, and will then present ways that it can be used in file access interfaces to help people find their files more quickly.
Biography:Stephen Fitchett is a PhD candidate from the University of Canterbury in New Zealand. Stephen's PhD thesis is on understanding and improving personal file navigation, and his previous research topics include scrolling and interfaces for language learning.
Refreshments will be served before the talk.