21 |
An Assessment of the Ability of the U.S. Department of Defense and the Services to Measure and Track Language and Culture Training and Capabilities Among General Purpose Forces
|
|
|
|
In: DTIC (2012)
|
|
BASE
|
|
Show details
|
|
22 |
Users' Manual and Validation of the Automated Grading System (AGS): Improving the Quality of Intelligence Summaries Using Feedback from an Unsupervised Model of Semantics
|
|
|
|
In: DTIC (2012)
|
|
BASE
|
|
Show details
|
|
23 |
Conference Report: Cultural and Linguistic Advancement for Mission Success: Enhancing Language, Regional and Cultural Capabilities Across Whole of Government for an Effective COIN Strategy
|
|
|
|
In: DTIC (2012)
|
|
BASE
|
|
Show details
|
|
24 |
Adding a Capability to Extract Sentiment from Text Using HanDles
|
|
|
|
In: DTIC (2012)
|
|
Abstract:
HanDles is a document visualization tool developed by Ohio State University for DRDC Toronto. One aspect of documents that might be of interest to analysts is the extent to which they express positive or negative opinion or sentiment toward some issue or group. In this report, we describe how HanDles was extended to include the ability to classify documents as containing predominantly positive or negative sentiment. The capability was added to the tool so that it could be used in Influence Operations contexts. As a test case, we trained HanDles to distinguish good and poor film reviews, and then tested it three times to see how well it classified documents. The first test was conducted on reviews of the Amazon Kindle. The second test was run on text segments of the original training set of movie reviews, and finally, it was tested on a set of movie reviews that it had not seen before. In general, HanDles did a poor job detecting the sentiment associated with the reviews of the Amazon Kindle. We attribute the poor performance to the fact that movie and product reviews discuss different issues, and as such, there is limited similarity in the two classes of document. Not surprisingly, HanDles did a good job classifying text segments of the original training set. Also, the finding demonstrated that, unlike many other sentiment analysis tools that only classify text at the whole-document level, HanDles can be used effectively to extract the issues being discussed within documents, and assign sentiment to those. For example, a review of a film might be classified as negative overall, but HanDles can determine that the acting was good, but the directing was poor. Finally, when we tested HanDles on a new set of movie reviews it had not seen before, it performed with 93.3% accuracy. The results of our trial suggest that there must be some similarity between the documents used during training and those used in the operational context for HanDles to work properly. ; Text in English; abstract and executive summary in English and French. Contract No. W7711-088147/001/TOR.
|
|
Keyword:
*ATTITUDES(PSYCHOLOGY); *CLASSIFICATION; *DATA MINING; *DOCUMENT VISUALIZATION; *DOCUMENTS; *EXTRACTION; *HANDLES VISUALIZATION TOOL; *INFORMATION RETRIEVAL; *OPINION MINING; *SEMANTICS; *SENTIMENT ANALYSIS; AMAZON KINDLE REVIEW CLASSIFICATION; ARTIFICIAL INTELLIGENCE; AUGMENTATION; AUTOMATION; CANADA; Cybernetics; FILM REVIEW CLASSIFICATION; FOREIGN REPORTS; INFLUENCE OPERATIONS; INFORMATION PROCESSING; Information Science; INTERNET MOVIE DATABASE; LANGUAGE PROCESSING; LEARNING MACHINES; Linguistics; MOTION PICTURES; NEGATIVE SENTIMENT; POSITIVE SENTIMENT; Psychology; SENTIMENT EXTRACTION; SUPPORT VECTOR MACHINES; TOOL AUGMENTATION; TRAINING
|
|
URL: http://oai.dtic.mil/oai/oai?&verb=getRecord&metadataPrefix=html&identifier=ADA568477 http://www.dtic.mil/docs/citations/ADA568477
|
|
BASE
|
|
Hide details
|
|
25 |
Capability Challenges in the Human Domain for Intelligence Analysis: Report on Community-Wide Discussions with Canadian Intelligence Professionals
|
|
|
|
In: DTIC (2012)
|
|
BASE
|
|
Show details
|
|
26 |
Compressed Domain Automatic Level Control Based on ITU-T G.722.2
|
|
|
|
In: DTIC (2012)
|
|
BASE
|
|
Show details
|
|
27 |
Trends in Human-Computer Interaction to Support Future Intelligence Analysis Capabilities
|
|
|
|
In: DTIC (2011)
|
|
BASE
|
|
Show details
|
|
28 |
Visual Analytics in Public Safety: Example Capabilities for Example Government Agencies
|
|
|
|
In: DTIC (2011)
|
|
BASE
|
|
Show details
|
|
29 |
An Intelligence Process Model Based on a Collaborative Approach
|
|
|
|
In: DTIC (2011)
|
|
BASE
|
|
Show details
|
|
30 |
A Concept Map Knowledge Model of Intelligence Analysis
|
|
|
|
In: DTIC (2011)
|
|
BASE
|
|
Show details
|
|
31 |
Multiple Detection Probabilistic Data Association Filter for Multistatic Target Tracking
|
|
|
|
In: DTIC (2011)
|
|
BASE
|
|
Show details
|
|
32 |
A Smarter Common Operational Picture: The Application of Abstraction Hierarchies to Naval Command and Control
|
|
|
|
In: DTIC (2011)
|
|
BASE
|
|
Show details
|
|
33 |
Cognitive Activation Theory of Stress (CATS)
|
|
|
|
In: DTIC (2011)
|
|
BASE
|
|
Show details
|
|
34 |
Towards a Semiotic Information Position Framework for Network Centric Warfare
|
|
|
|
In: DTIC (2011)
|
|
BASE
|
|
Show details
|
|
35 |
Semantic Analysis of Military Relevant Texts for Intelligence Purposes
|
|
|
|
In: DTIC (2011)
|
|
BASE
|
|
Show details
|
|
36 |
Multilingual Content Extraction Extended with Background Knowledge for Military Intelligence
|
|
|
|
In: DTIC (2011)
|
|
BASE
|
|
Show details
|
|
37 |
Related Entity Finding: University of Waterloo at TREC 2010 Entity Track
|
|
|
|
In: DTIC (2010)
|
|
BASE
|
|
Show details
|
|
38 |
Speech Understanding in Noise in the Bison Command, Control, Communications and Intelligence (C3I) Mobile Command Post (MCP)
|
|
|
|
In: DTIC (2010)
|
|
BASE
|
|
Show details
|
|
39 |
Entity Profiling for Intelligence Using the Graphical Overview of Social and Semantic Interactions of People (GOSSIP) Software Tool
|
|
|
|
In: DTIC (2010)
|
|
BASE
|
|
Show details
|
|
40 |
Issues in Intelligence Production: Summary of Interviews with Canadian Managers of Intelligence Analysts
|
|
|
|
In: DTIC (2010)
|
|
BASE
|
|
Show details
|
|
|
|