Search

Showing total 4 results
Start Over Topic data mining Topic information retrieval Region united states
4 results

1. Information Preserving Time Decompositions of Time Stamped Documents.

Author

Chundi, Parvathi and Rosenkrantz, Daniel J.

Subjects
ARCHIVES, PUBLICATIONS, ALGORITHMS, DECOMPOSITION method, INFORMATION retrieval, DATABASES, SYSTEM analysis, DATA mining
Abstract

Extraction of sequences of events from news and other documents based on the publication times of these documents has been shown to be extremely effective in tracking past events. This paper addresses the issue of constructing an optimal information preserving decomposition of the time period associated with a given document set, i.e., a decomposition with the smallest number of subintervals, subject to no loss of information. We introduce the notion of the compressed interval decomposition, where each subinterval consists of consecutive time points having identical information content. We define optimality, and show that any optimal information preserving decomposition of the time period is a refinement of the compressed interval decomposition. We define several special classes of measure functions (functions that measure the prevalence of keywords in the document set and assign them numeric values), based on their effect on the information computed as document sets are combined. We give algorithms, appropriate for different classes of measure functions, for computing an optimal information preserving decomposition of a given document set. We studied the effectiveness of these algorithms by computing several compressed interval and information preserving decompositions for a subset of the Reuters-21578 document set. The experiments support the obvious conclusion that the temporal information gleaned from a document set is strongly dependent on the measure function used and on other user-defined parameters. [ABSTRACT FROM AUTHOR]

Published
2006
Full Text
View/download PDF

2. Between Decisional Paralysis and Executive Preponderance: an Intermediate Approach to Brazilian Policymaking in the Context of Coalition Presidentialism.

Author

de Barros Correia Gomes, Fabio

Subjects
*INFORMATION storage & retrieval systems, *LEGISLATIVE bodies, *INFORMATION retrieval, *STATE governments, *DATA mining
Abstract

The article analyzes the role of the legislative power in lawmaking, considering the agenda submitted to the U.S. Congress in its two chambers and to look for other types of strategic interactions between the powers. The databases were constructed from information collected on the websites of the Chamber of Deputies, the Senate, the Presidency and the search engine Lexml.

Published
2012

3. Analysis of Log Files as a Security Aid.

Author

Pinto Leite, Jorge

Subjects
COMPUTER systems, DATA mining, OPEN source software, INFORMATION retrieval software
Abstract

Log files are the history books of a computer system. In particular, they tell a good portion of the security related events and menaces that a system has to withstand and, sometimes, fails to resist to. Therefore, log files' analysis can be valuable to system and security administrators if the difficulty of extracting the relevant information of the different kinds of data and formats can be surmounted. And if we consider a huge system in terms of users, services and accesses, the difficulty of the analysis task rises enormously. In infra-structures where there is more than one server and communication link, it is possible for the administrator and security team to configure all systems to record their logs in a central huge repository, but the search for abnormalities is quite impossible without specialized tools. As we believe that the collected information on log files can be valuable, we use information retrieval open source tools to index the log files' fields and search for patterns of suspected behavior, which may indicate a system intrusion. Our development allows queries based on variables introduced by the analyst. The preliminary results obtained when using log files from an academic institution indicates that our approach is effective and can be used as a security aid. [ABSTRACT FROM AUTHOR]

Published
2011

4. Text mining's next step.

Author

Byrne, Tony

Subjects
COMPUTER software development, DATA mining, COMPUTER software industry, INFORMATION retrieval
Abstract

This article informs that in a move that should help jump-start the emerging text mining industry, International Business Machines Corp. (IBM) has announced in August the release of an impressive set of infrastructure components known collectively as Unstructured Information Management Architecture (UIMA). Technically, UIMA consists of a software development kit, documentation and reference implementation. IBM announced that the core architecture, which is being advanced in cooperation with the U.S. Defense Advanced Research Projects Agency and other research institutions, would be submitted to open source later this year. IBM has made several of its tools UIMA-compliant, including its OmniFind search engine and other analytics packages.

Published
2005