Analytic Steering: Inserting Context into the Information Dialog

Conference · Sun Oct 23 04:00:00 EDT 2011

OSTI ID:1092684

Bohn, Shawn J.; Calapristi, Augustin J.; Brown, Shyretha D.; Nakamura, Grant C.

An analyst’s intrinsic domain knowledge is a primary asset in almost any analysis task. Unstructured text analysis systems that apply un-supervised content analysis approaches can be more effective if they can leverage this domain knowledge in a manner that augments the information discovery process without obfuscating new or unexpected content. Current unsupervised approaches rely upon the prowess of the analyst to submit the right queries or observe generalized document and term relationships from ranked or visual results. We propose a new approach which allows the user to control or steer the analytic view within the unsupervised space. This process is controlled through the data characterization process via user supplied context in the form of a collection of key terms. We show that steering with an appropriate choice of key terms can provide better relevance to the analytic domain and still enable the analyst to uncover un-expected relationships; this paper discusses cases where various analytic steering approaches can provide enhanced analysis results and cases where analytic steering can have a negative impact on the analysis process.

• Research Organization: Pacific Northwest National Laboratory (PNNL), Richland, WA (US)
• Sponsoring Organization: USDOE
• DOE Contract Number: AC05-76RL01830
• OSTI ID: 1092684
• Report Number(s): PNNL-SA-82732; 400470000
• Country of Publication: United States
• Language: English

Related Subjects

Steering
Text Analysis
Viewpoints
Visual Analytics