{"id":{"repo_id":"mit","oai_identifier":"oai:dspace.mit.edu:1721.1/29415"},"canonical_url":"https://search.dev.ndltd.org/etd/mit/oai:dspace.mit.edu:1721.1/29415","repository":{"repo_id":"mit","name":"MIT","base_url":"https://dspace.mit.edu/oai/request"},"display":{"title":"Automatic classification of documents with an in-depth analysis of information extraction and automatic summarization","abstract":"Today, annual information fabrication per capita exceeds two hundred and fifty megabytes. As the amount of data increases, classification and retrieval methods become more necessary to find relevant information. This thesis describes a .Net application (named I-Document) that establishes an automatic classification scheme in a peer-to-peer environment that allows free sharing of academic, business, and personal documents. A Web service architecture for metadata extraction, Information Extraction, Information Retrieval, and text summarization is depicted. Specific details regarding the coding process, competition, business model, and technology employed in the project are also discussed.","abstract_html":"Today, annual information fabrication per capita exceeds two hundred and fifty megabytes. As the amount of data increases, classification and retrieval methods become more necessary to find relevant information. This thesis describes a .Net application (named I-Document) that establishes an automatic classification scheme in a peer-to-peer environment that allows free sharing of academic, business, and personal documents. A Web service architecture for metadata extraction, Information Extraction, Information Retrieval, and text summarization is depicted. Specific details regarding the coding process, competition, business model, and technology employed in the project are also discussed.","abstract_has_math":false,"creators":["Hohm, Joseph Brandon, 1982-"],"institution":"Massachusetts Institute of Technology","degree_name":null,"degree_level":null,"degree_discipline":null,"degree_department":"Massachusetts Institute of Technology. Dept. of Civil and Environmental Engineering.","school":null,"contributors":[],"advisors":["John R. Williams."],"committee_chairs":[],"committee_members":[],"year":2004,"date_issued":"2004","date_published":"2004","updated_at":"2026-07-22T22:21:02Z","subjects":["Civil and Environmental Engineering."],"languages":["eng"],"rights":["M.I.T. theses are protected by copyright. They may be viewed from this source for any purpose, but reproduction or distribution in any format is prohibited without written permission. See provided URL for inquiries about permission."],"rights_urls":["http://dspace.mit.edu/handle/1721.1/7582"],"identifier_entries":[]},"links":{"outbound_url":"http://hdl.handle.net/1721.1/29415","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["John R. Williams."]},{"key":"dc:contributor.department","label":"Department","values":["Massachusetts Institute of Technology. Dept. of Civil and Environmental Engineering."]},{"key":"dc:contributor.other","label":"Dc Contributor Other","values":["Massachusetts Institute of Technology. Dept. of Civil and Environmental Engineering."]},{"key":"dc:creator","label":"Author","values":["Hohm, Joseph Brandon, 1982-"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2005-10-14T20:25:25Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2005-10-14T20:25:25Z"]},{"key":"dc:date.issued","label":"Date","values":["2004"]},{"key":"dc:publisher","label":"Institution","values":["Massachusetts Institute of Technology"]},{"key":"dc:type","label":"Dc Type","values":["Thesis"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Civil and Environmental Engineering."]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language.iso","label":"Language (ISO)","values":["eng"]},{"key":"dc:rights","label":"Dc Rights","values":["M.I.T. theses are protected by copyright. They may be viewed from this source for any purpose, but reproduction or distribution in any format is prohibited without written permission. See provided URL for inquiries about permission."]},{"key":"dc:rights.uri","label":"Rights URI","values":["http://dspace.mit.edu/handle/1721.1/7582"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["http://hdl.handle.net/1721.1/29415"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Thesis (M. Eng.)--Massachusetts Institute of Technology, Dept. of Civil and Environmental Engineering, 2004.","Includes bibliographical references (leaves 78-80)."]},{"key":"dc:description.abstract","label":"Abstract","values":["Today, annual information fabrication per capita exceeds two hundred and fifty megabytes. As the amount of data increases, classification and retrieval methods become more necessary to find relevant information. This thesis describes a .Net application (named I-Document) that establishes an automatic classification scheme in a peer-to-peer environment that allows free sharing of academic, business, and personal documents. A Web service architecture for metadata extraction, Information Extraction, Information Retrieval, and text summarization is depicted. Specific details regarding the coding process, competition, business model, and technology employed in the project are also discussed."]},{"key":"dc:description.degree","label":"Dc Description Degree","values":["M.Eng."]},{"key":"dc:format.mimetype","label":"Dc Format Mimetype","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Automatic classification of documents with an in-depth analysis of information extraction and automatic summarization"]}]}],"canonical_facts":{"dc:contributor.advisor":["John R. Williams."],"dc:contributor.department":["Massachusetts Institute of Technology. Dept. of Civil and Environmental Engineering."],"dc:contributor.other":["Massachusetts Institute of Technology. Dept. of Civil and Environmental Engineering."],"dc:creator":["Hohm, Joseph Brandon, 1982-"],"dc:date.accessioned":["2005-10-14T20:25:25Z"],"dc:date.available":["2005-10-14T20:25:25Z"],"dc:date.issued":["2004"],"dc:description":["Thesis (M. Eng.)--Massachusetts Institute of Technology, Dept. of Civil and Environmental Engineering, 2004.","Includes bibliographical references (leaves 78-80)."],"dc:description.abstract":["Today, annual information fabrication per capita exceeds two hundred and fifty megabytes. As the amount of data increases, classification and retrieval methods become more necessary to find relevant information. This thesis describes a .Net application (named I-Document) that establishes an automatic classification scheme in a peer-to-peer environment that allows free sharing of academic, business, and personal documents. A Web service architecture for metadata extraction, Information Extraction, Information Retrieval, and text summarization is depicted. Specific details regarding the coding process, competition, business model, and technology employed in the project are also discussed."],"dc:description.degree":["M.Eng."],"dc:format.mimetype":["application/pdf"],"dc:identifier.uri":["http://hdl.handle.net/1721.1/29415"],"dc:language.iso":["eng"],"dc:publisher":["Massachusetts Institute of Technology"],"dc:rights":["M.I.T. theses are protected by copyright. They may be viewed from this source for any purpose, but reproduction or distribution in any format is prohibited without written permission. See provided URL for inquiries about permission."],"dc:rights.uri":["http://dspace.mit.edu/handle/1721.1/7582"],"dc:subject":["Civil and Environmental Engineering."],"dc:title":["Automatic classification of documents with an in-depth analysis of information extraction and automatic summarization"],"dc:type":["Thesis"]},"updated_at":"2026-07-22T22:21:02Z"}