Creation of an expert witness database through text mining

Dozier, Christopher; Jackson, Paul; Guo, Xi S.; Chaudhary, Mark; Arumainayagam, Yohendran

doi:10.1145/1047788.1047830

Cited by 9 publications

(7 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…2 Most EDM software is complex, expensive, and intended for the enterprisewide content management required for regulatory-compliance applications. Most regulations do not distinguish among specific forms of communication but rather specify the monitoring and storage of all organizational communication that may contain regulated content.…”

Section: By William L Kuechlermentioning

confidence: 99%

See 1 more Smart Citation

Business applications of unstructured text

Kuechler

2007

Commun. ACM

View full text Add to dashboard Cite

show abstract

Section: By William L Kuechlermentioning

confidence: 99%

“…An illustrative concept-based application [2] has created and maintains a database of more than 100,000 expert witnesses for a variety of court cases. Public jury verdict and settlement documents, along with professional license and other Web-available records, were mined to produce the database.…”

Section: By William L Kuechlermentioning

confidence: 99%

Business applications of unstructured text

Kuechler

2007

Commun. ACM

View full text Add to dashboard Cite

show abstract

“…Expert witnesses play an important role in the resolution of many legal conflicts, but information about who testified at what trials and in which capacities exists only in textual form. To address this problem, we created a comprehensive expert witness database of 110,000 records using text mining techniques [3].…”

Section: Peoplecite and Profilermentioning

confidence: 99%

Generating Value from Textual Discovery

Jackson

2007

Computational Science – ICCS 2007

Self Cite

View full text Add to dashboard Cite

Abstract. Much of the information associated with legal, financial, medical and educational domains is stored in electronic document repositories and retrievable only by full text search. The ability of publishers to enhance such documents through traditional editorial processes struggles to keep pace with the volume and variety of textual data currently available in proprietary collections and on the Web. Fortunately, text mining tools that support the automatic classification, summarization, and linking of documents can be developed and deployed cost effectively. The outcome is a more flexible and dynamic approach to meta-data generation that does a better job of supporting the searching and browsing behaviors of information consumers. This paper describes the application of text and data mining techniques to legal information in a manner that enables powerful report generation and document recommendation services.

show abstract

“…where (1) i FreqE is the number of occurrences of E1 in the ith Web page and min(1,2) j EE is the distance between the jth occurrence of E1, 1 j E , and E2.…”

Section: Relation Strength and Rankingmentioning

confidence: 99%

“…We argue that documents are a primary resource for discovering information about people's skills and associations. Text based approaches have already been used in some specialist domains, for example to create a database about the competencies of expert witnesses [1]. We propose to use text documents in a more general scenario and to concentrate on finding the relations between entities of several kinds rather than classifying experts against a taxonomy of skills.…”

Section: Introductionmentioning

confidence: 99%