{"id":{"repo_id":"duquesne","oai_identifier":"oai:dsc.duq.edu:etd-1447"},"canonical_url":"https://search.dev.ndltd.org/etd/duquesne/oai:dsc.duq.edu:etd-1447","repository":{"repo_id":"duquesne","name":"Duquesne","base_url":"https://dsc.duq.edu/do/oai/"},"display":{"title":"Improving Search Results with Automated Summarization and Sentence Clustering","abstract":"Have you ever searched for something on the web and been overloaded with irrelevant results? Many search engines tend to cast a very wide net and rely on ranking to show you the relevant results first. But, this doesn't always work. Perhaps the occurrence of irrelevant results could be reduced if we could eliminate the unimportant content from each webpage while indexing. Instead of casting a wide net, maybe we can make the net smarter. Here, I investigate the feasibility of using automated document summarization and clustering to do just that. The results indicate that such methods can make search engines more precise, more efficient, and faster, but not without costs.","abstract_html":"Have you ever searched for something on the web and been overloaded with irrelevant results? Many search engines tend to cast a very wide net and rely on ranking to show you the relevant results first. But, this doesn't always work. Perhaps the occurrence of irrelevant results could be reduced if we could eliminate the unimportant content from each webpage while indexing. Instead of casting a wide net, maybe we can make the net smarter. Here, I investigate the feasibility of using automated document summarization and clustering to do just that. The results indicate that such methods can make search engines more precise, more efficient, and faster, but not without costs.","abstract_has_math":false,"creators":["Cotter, Steven"],"institution":null,"degree_name":"MS","degree_level":"Immediate Access","degree_discipline":"Computational Mathematics","degree_department":null,"school":null,"contributors":["Patrick Juola","John Kern","Donald Simon"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2012,"date_issued":"2012-01-01T08:00:00Z","date_published":"2012-01-01T08:00:00Z","updated_at":"2026-07-24T02:09:27Z","subjects":["Automatic summarization","Extractive summarization","Search engine precision","Sentence clustering","Spectral clustering","TextRank"],"languages":["English"],"rights":[],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://dsc.duq.edu/etd/434","outbound_label":"Repository record","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Patrick Juola","John Kern","Donald Simon"]},{"key":"dc:creator","label":"Author","values":["Cotter, Steven"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.available","label":"Dc Date Available","values":["2018-08-03T07:00:00Z"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Computational Mathematics"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Immediate Access"]},{"key":"thesis:degree_name","label":"Degree Name","values":["MS"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Automatic summarization","Extractive summarization","Search engine precision","Sentence clustering","Spectral clustering","TextRank"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["English"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://dsc.duq.edu/etd/434"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Have you ever searched for something on the web and been overloaded with irrelevant results? Many search engines tend to cast a very wide net and rely on ranking to show you the relevant results first. But, this doesn't always work. Perhaps the occurrence of irrelevant results could be reduced if we could eliminate the unimportant content from each webpage while indexing. Instead of casting a wide net, maybe we can make the net smarter. Here, I investigate the feasibility of using automated document summarization and clustering to do just that. The results indicate that such methods can make search engines more precise, more efficient, and faster, but not without costs."]},{"key":"dc:title","label":"Title","values":["Improving Search Results with Automated Summarization and Sentence Clustering"]}]}],"canonical_facts":{"dc:contributor":["Patrick Juola","John Kern","Donald Simon"],"dc:creator":["Cotter, Steven"],"dc:date.available":["2018-08-03T07:00:00Z"],"dc:description.abstract":["Have you ever searched for something on the web and been overloaded with irrelevant results? Many search engines tend to cast a very wide net and rely on ranking to show you the relevant results first. But, this doesn't always work. Perhaps the occurrence of irrelevant results could be reduced if we could eliminate the unimportant content from each webpage while indexing. Instead of casting a wide net, maybe we can make the net smarter. Here, I investigate the feasibility of using automated document summarization and clustering to do just that. The results indicate that such methods can make search engines more precise, more efficient, and faster, but not without costs."],"dc:identifier":["https://dsc.duq.edu/etd/434"],"dc:language":["English"],"dc:subject":["Automatic summarization","Extractive summarization","Search engine precision","Sentence clustering","Spectral clustering","TextRank"],"dc:title":["Improving Search Results with Automated Summarization and Sentence Clustering"],"thesis:degree_discipline":["Computational Mathematics"],"thesis:degree_level":["Immediate Access"],"thesis:degree_name":["MS"]},"updated_at":"2026-07-24T02:09:27Z"}