Abstract
Our central claim is that user interactions with productivity applications (e.g. word processors, Web browsers, etc.) provide rich contextual information that can be leveraged to support just-in-time access to task-relevant information. As evidence for our claim, we present Watson, a system which gathers contextual information in the form of the text of the document the user is manipulating, in order to proactively retrieve documents from distributed information repositories related to task at hand, as well as process explicit requests in the context of this task. We close by describing the results of several experiments with Watson, which show it consistently provides useful information to its users. The experiments also suggest that, contrary to the assumptions of many system designers, similar documents are not necessarily useful documents in the context of a particular task.
Original language | English (US) |
---|---|
Pages (from-to) | 37-53 |
Number of pages | 17 |
Journal | Knowledge-Based Systems |
Volume | 14 |
Issue number | 1-2 |
DOIs | |
State | Published - Jan 1 2001 |
Fingerprint
ASJC Scopus subject areas
- Software
- Management Information Systems
- Information Systems and Management
- Artificial Intelligence
Cite this
}
Information access in context. / Budzik, J.; Hammond, Kristian J; Birnbaum, Lawrence A.
In: Knowledge-Based Systems, Vol. 14, No. 1-2, 01.01.2001, p. 37-53.Research output: Contribution to journal › Article
TY - JOUR
T1 - Information access in context
AU - Budzik, J.
AU - Hammond, Kristian J
AU - Birnbaum, Lawrence A
PY - 2001/1/1
Y1 - 2001/1/1
N2 - Our central claim is that user interactions with productivity applications (e.g. word processors, Web browsers, etc.) provide rich contextual information that can be leveraged to support just-in-time access to task-relevant information. As evidence for our claim, we present Watson, a system which gathers contextual information in the form of the text of the document the user is manipulating, in order to proactively retrieve documents from distributed information repositories related to task at hand, as well as process explicit requests in the context of this task. We close by describing the results of several experiments with Watson, which show it consistently provides useful information to its users. The experiments also suggest that, contrary to the assumptions of many system designers, similar documents are not necessarily useful documents in the context of a particular task.
AB - Our central claim is that user interactions with productivity applications (e.g. word processors, Web browsers, etc.) provide rich contextual information that can be leveraged to support just-in-time access to task-relevant information. As evidence for our claim, we present Watson, a system which gathers contextual information in the form of the text of the document the user is manipulating, in order to proactively retrieve documents from distributed information repositories related to task at hand, as well as process explicit requests in the context of this task. We close by describing the results of several experiments with Watson, which show it consistently provides useful information to its users. The experiments also suggest that, contrary to the assumptions of many system designers, similar documents are not necessarily useful documents in the context of a particular task.
UR - http://www.scopus.com/inward/record.url?scp=0035276976&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=0035276976&partnerID=8YFLogxK
U2 - 10.1016/S0950-7051(00)00105-2
DO - 10.1016/S0950-7051(00)00105-2
M3 - Article
AN - SCOPUS:0035276976
VL - 14
SP - 37
EP - 53
JO - Knowledge-Based Systems
JF - Knowledge-Based Systems
SN - 0950-7051
IS - 1-2
ER -