Seeing is retrieving: building information context from what the user sees

As the user's document and application workspace grows more diverse, supporting personal information management becomes increasingly important. This trend toward diversity renders it difficult to implement systems which are tailored to specific applications, file types, or other information sources. We developed SeeTrieve, a personal document retrieval and classification system which abstracts applications by considering only the text they present to the user through the user interface. Associating the visible text which surrounds a document in time, SeeTrieve is able to identify important information about the task within which a document is used. This context enables novel, useful ways for users to retrieve their personal documents. When compared to content based systems, this context based retrieval achieved substantial improvements in document recall.

[1]  David Elsweiler,et al.  Towards task-based personal information management evaluations , 2007, SIGIR.

[2]  Kristian J. Hammond,et al.  Mining navigation history for recommendation , 2000, IUI '00.

[3]  Ryen W. White,et al.  A study on the effects of personalization and task information on implicit feedback performance , 2006, CIKM '06.

[4]  Nuria Oliver,et al.  SWISH: semantic analysis of window titles and switching history , 2006, IUI '06.

[5]  John F. Canny,et al.  CAAD: an automatic task support system , 2007, CHI.

[6]  Kave Eshghi,et al.  A Framework for Analyzing and Improving Content-Based Chunking Algorithms , 2005 .

[7]  Thomas G. Dietterich,et al.  A hybrid learning system for recognizing user tasks from desktop activities and email messages , 2006, IUI '06.

[8]  Diane Kelly.  Evaluating personal information management behaviors and tools , 2006, CACM.

[9]  Karl Gyllstrom,et al.  Confluence: enhancing contextual desktop search , 2007, SIGIR.

[10]  Susan T. Dumais,et al.  Personalizing Search via Automated Analysis of Interests and Activities , 2005, SIGIR.

[11]  David F. Redmiles,et al.  Extracting usability information from user interface events , 2000, CSUR.

[12]  Masatoshi Yoshikawa,et al.  Adaptive web search based on user profile constructed without any effort from users , 2004, WWW '04.

[13]  David R. Karger,et al.  Haystack: A General-Purpose Information Management Tool for End Users Based on Semistructured Data , 2005, CIDR.

[14]  Craig A. N. Soules,et al.  Connections: using context to enhance file search , 2005, SOSP '05.

[15]  Victor Kaptelinin,et al.  UMEA: translating interaction histories into project contexts , 2003, CHI '03.

[16]  Dominique L. Scapin,et al.  What do people recall about their documents?: implications for desktop search tools , 2007, IUI '07.

[17]  Deborah K. Barreau,et al.  Context as a Factor in Personal Information Management Systems , 1995, J. Am. Soc. Inf. Sci..

[18]  Susan T. Dumais,et al.  Searching to eliminate personal information management , 2006, CACM.

[19]  David B. Leake,et al.  Using Document Access Sequences to Recommend Customized Information , 2002, IEEE Intell. Syst..

[20]  Paul-Alexandru Chirita,et al.  Personalized query expansion for the web , 2007, SIGIR.

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