FolderPredictor: Reducing the cost of reaching the right folder

Helping computer users rapidly locate files in their folder hierarchies is a practical research problem involving both intelligent systems and user interface design. This article reports on FolderPredictor, a software system that can reduce the cost of locating files in hierarchical folders. FolderPredictor applies a cost-sensitive prediction algorithm to the user's previous file access information to predict the next folder that will be accessed. Experimental results show that, on average, FolderPredictor reduces the number of clicks spent on locating a file by 50%. Several variations of the cost-sensitive prediction algorithm are discussed. An experimental study shows that the best algorithm among them is a mixture of the most recently used (MRU) folder and the cost-sensitive predictions. Furthermore, FolderPredictor does not require users to adapt to a new interface, but rather meshes with the existing interface for opening files on the Windows platform.

[1]  Pattie Maes,et al.  Agents that reduce work and information overload , 1994, CACM.

[2]  George W. Furnas,et al.  Navigation in electronic worlds: a CHI 97 workshop , 1997, SGCH.

[3]  Eric Horvitz,et al.  The Lumière Project: Bayesian User Modeling for Inferring the Goals and Needs of Software Users , 1998, UAI.

[4]  Paul Dourish,et al.  Extending document management systems with user-specific active properties , 2000, TOIS.

[5]  Kristian J. Hammond,et al.  User interactions with everyday applications as context for just-in-time information access , 2000, IUI '00.

[6]  Thomas G. Dietterich,et al.  Detecting and correcting user activity switches: algorithms and interfaces , 2009, IUI.

[7]  Thomas G. Dietterich,et al.  Predicting User Tasks : I Know What You ’ re Doing ! , 2005 .

[8]  Harry Bruce,et al.  Don't take my folders away!: organizing personal information to get ghings done , 2005, CHI Extended Abstracts.

[9]  Amy J. Ko,et al.  Eliciting design requirements for maintenance-oriented IDEs: a detailed study of corrective and perfective maintenance tasks , 2005, Proceedings. 27th International Conference on Software Engineering, 2005. ICSE 2005..

[10]  Bradley J. Rhodes.  Using Physical Context for Just-in-Time Information Retrieval , 2003, IEEE Trans. Computers.

[11]  Michelle A. Vincow,et al.  Navigation in Electronic Worlds Workshop Report , 1997 .

[12]  Susanne Jul.  Navigation in Electronic Worlds Workshop Report , 1999 .

[13]  M. Angela Sasse,et al.  "Stuff goes into the computer and doesn't come out": a cross-tool study of personal information management , 2004, CHI.

[14]  Jason D. M. Rennie.  ifile: An Application of Machine Learning to E-Mail Filtering , 2000 .

[15]  Jeffrey O. Kephart,et al.  MailCat: an intelligent assistant for organizing e-mail , 1999, AGENTS '99.

[16]  Matt Pietrek.  Windows 95 System Programming Secrets , 1995 .

[17]  Thomas G. Dietterich,et al.  TaskTracer: a desktop environment to support multi-tasking knowledge workers , 2005, IUI.

[18]  George W. Furnas,et al.  Navigation in Electronic Worlds. , 1997 .

[19]  Jeffrey O. Kephart,et al.  Incremental Learning in SwiftFile , 2000, ICML.

[20]  Mark S. Ackerman,et al.  The perfect search engine is not enough: a study of orienteering behavior in directed search , 2004, CHI.

[21]  Bonnie A. Nardi,et al.  Finding and reminding: file organization from the desktop , 1995, SGCH.