{"id":{"repo_id":"vt","oai_identifier":"oai:vtechworks.lib.vt.edu:10919/30818"},"canonical_url":"https://search.dev.ndltd.org/etd/vt/oai:vtechworks.lib.vt.edu:10919/30818","repository":{"repo_id":"vt","name":"Virginia Tech","base_url":"https://vtechworks.lib.vt.edu/oai/request"},"display":{"title":"A Comparison of Statistical Filtering Methods for Automatic Term Extraction for Domain Analysis","abstract":"Fourteen word frequency metrics were tested to evaluate their effectiveness in identifying vocabulary in a domain. Fifteen domain engineering projects were examined to measure how closely the vocabularies selected by the fourteen word frequency metrics were to the vocabularies produced by domain engineers. Six filtering mechanisms were also evaluated to measure their impact on selecting proper vocabulary terms. The results of the experiment show that stemming and stop word removal do improve overlap scores and that term frequency is a valuable contributor to overlap. Variations on term frequency are not always significant improvers of overlap.","abstract_html":"Fourteen word frequency metrics were tested to evaluate their effectiveness in identifying vocabulary in a domain. Fifteen domain engineering projects were examined to measure how closely the vocabularies selected by the fourteen word frequency metrics were to the vocabularies produced by domain engineers. Six filtering mechanisms were also evaluated to measure their impact on selecting proper vocabulary terms. The results of the experiment show that stemming and stop word removal do improve overlap scores and that term frequency is a valuable contributor to overlap. Variations on term frequency are not always significant improvers of overlap.","abstract_has_math":false,"creators":["Tilley, Jason W."],"institution":"Virginia Tech","degree_name":"Master of Science","degree_level":"masters","degree_discipline":"Computer Science","degree_department":"Computer Science","school":null,"contributors":[],"advisors":[],"committee_chairs":["Frakes, William B."],"committee_members":["Kulczycki, Gregory W.","Belli, Gabriella M."],"year":2008,"date_issued":"2008-12-22","date_published":"2008-12-22","updated_at":"2026-07-22T22:19:49Z","subjects":["domain analysis","term extraction"],"languages":[],"rights":["In Copyright"],"rights_urls":["http://rightsstatements.org/vocab/InC/1.0/"],"identifier_entries":[{"key":"dc:identifier.other","label":"Dc Identifier Other","values":["etd-01052009-103100"],"render_values":[{"text":"etd-01052009-103100","href":null,"code":true}]}]},"links":{"outbound_url":"http://hdl.handle.net/10919/30818","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.committeechair","label":"Committee Chair","values":["Frakes, William B."]},{"key":"dc:contributor.committeemember","label":"Committee Member","values":["Kulczycki, Gregory W.","Belli, Gabriella M."]},{"key":"dc:contributor.department","label":"Department","values":["Computer Science"]},{"key":"dc:creator","label":"Author","values":["Tilley, Jason W."]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2014-03-14T20:30:11Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2014-03-14T20:30:11Z","2009-05-13"]},{"key":"dc:date.issued","label":"Date","values":["2008-12-22"]},{"key":"dc:publisher","label":"Institution","values":["Virginia Tech"]},{"key":"dc:type","label":"Dc Type","values":["Thesis"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Computer Science"]},{"key":"thesis:degree_level","label":"Degree Level","values":["masters"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Master of Science"]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["Virginia Polytechnic Institute and State University"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["domain analysis","term extraction"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:rights","label":"Dc Rights","values":["In Copyright"]},{"key":"dc:rights.uri","label":"Rights URI","values":["http://rightsstatements.org/vocab/InC/1.0/"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.other","label":"Dc Identifier Other","values":["etd-01052009-103100"]},{"key":"dc:identifier.uri","label":"Identifier URI","values":["http://hdl.handle.net/10919/30818"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Fourteen word frequency metrics were tested to evaluate their effectiveness in identifying vocabulary in a domain. Fifteen domain engineering projects were examined to measure how closely the vocabularies selected by the fourteen word frequency metrics were to the vocabularies produced by domain engineers. Six filtering mechanisms were also evaluated to measure their impact on selecting proper vocabulary terms. The results of the experiment show that stemming and stop word removal do improve overlap scores and that term frequency is a valuable contributor to overlap. Variations on term frequency are not always significant improvers of overlap."]},{"key":"dc:description.degree","label":"Dc Description Degree","values":["Master of Science"]},{"key":"dc:title","label":"Title","values":["A Comparison of Statistical Filtering Methods for Automatic Term Extraction for Domain Analysis"]}]}],"canonical_facts":{"dc:contributor.committeechair":["Frakes, William B."],"dc:contributor.committeemember":["Kulczycki, Gregory W.","Belli, Gabriella M."],"dc:contributor.department":["Computer Science"],"dc:creator":["Tilley, Jason W."],"dc:date.accessioned":["2014-03-14T20:30:11Z"],"dc:date.available":["2014-03-14T20:30:11Z","2009-05-13"],"dc:date.issued":["2008-12-22"],"dc:description.abstract":["Fourteen word frequency metrics were tested to evaluate their effectiveness in identifying vocabulary in a domain. Fifteen domain engineering projects were examined to measure how closely the vocabularies selected by the fourteen word frequency metrics were to the vocabularies produced by domain engineers. Six filtering mechanisms were also evaluated to measure their impact on selecting proper vocabulary terms. The results of the experiment show that stemming and stop word removal do improve overlap scores and that term frequency is a valuable contributor to overlap. Variations on term frequency are not always significant improvers of overlap."],"dc:description.degree":["Master of Science"],"dc:identifier.other":["etd-01052009-103100"],"dc:identifier.uri":["http://hdl.handle.net/10919/30818"],"dc:publisher":["Virginia Tech"],"dc:rights":["In Copyright"],"dc:rights.uri":["http://rightsstatements.org/vocab/InC/1.0/"],"dc:subject":["domain analysis","term extraction"],"dc:title":["A Comparison of Statistical Filtering Methods for Automatic Term Extraction for Domain Analysis"],"dc:type":["Thesis"],"thesis:degree_discipline":["Computer Science"],"thesis:degree_level":["masters"],"thesis:degree_name":["Master of Science"],"thesis:institution_name":["Virginia Polytechnic Institute and State University"]},"updated_at":"2026-07-22T22:19:49Z"}