{"id":{"repo_id":"uiuc","oai_identifier":"oai:www.ideals.illinois.edu:2142/14680"},"canonical_url":"https://search.dev.ndltd.org/etd/uiuc/oai:www.ideals.illinois.edu:2142/14680","repository":{"repo_id":"uiuc","name":"University of Illinois - Urbana-Champaign","base_url":"https://www.ideals.illinois.edu/oai-pmh"},"display":{"title":"Generating comparative summaries of contradictory opinions in text","abstract":"This thesis presents a study of a novel summarization problem called contrastive opinion summarization (COS). Given two sets of positively and negatively opinionated sentences which are often the output of an existing opinion summarizer, COS aims to extract comparable sentences from each set of opinions and generate a comparative summary containing a set of contrastive sentence pairs. We formally formulate the problem as an optimization problem and propose two general methods for generating a comparative summary using the framework, both of which rely on measuring the content similarity and contrastive similarity of two sentences. We study several strategies to compute these two similarities. We also create a test data set for evaluating such a novel summarization problem. Experiment results on this test set show that the proposed methods are effective for generating comparative summaries of contradictory opinions. In addition, we implemented two demo systems which show the usefulness of the algorithm intuitively.","abstract_html":"This thesis presents a study of a novel summarization problem called contrastive opinion summarization (COS). Given two sets of positively and negatively opinionated sentences which are often the output of an existing opinion summarizer, COS aims to extract comparable sentences from each set of opinions and generate a comparative summary containing a set of contrastive sentence pairs. We formally formulate the problem as an optimization problem and propose two general methods for generating a comparative summary using the framework, both of which rely on measuring the content similarity and contrastive similarity of two sentences. We study several strategies to compute these two similarities. We also create a test data set for evaluating such a novel summarization problem. Experiment results on this test set show that the proposed methods are effective for generating comparative summaries of contradictory opinions. In addition, we implemented two demo systems which show the usefulness of the algorithm intuitively.","abstract_has_math":false,"creators":["Kim, Hyun Duk"],"institution":"University of Illinois at Urbana-Champaign","degree_name":"M.S.","degree_level":"Thesis","degree_discipline":"Computer Science","degree_department":null,"school":null,"contributors":["Zhai, ChengXiang"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2010,"date_issued":"2010-01-06T16:21:09Z","date_published":"2010-01-06T16:21:09Z","updated_at":"2026-07-22T22:25:08Z","subjects":["Opinion Summarization","Contrastive Opinion Summary","Text mining"],"languages":["en"],"rights":["Copyright 2009 by Hyun Duk Kim. All rights reserved."],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"http://hdl.handle.net/2142/14680","outbound_label":"Handle","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Zhai, ChengXiang"]},{"key":"dc:creator","label":"Author","values":["Kim, Hyun Duk"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2010-01-06T16:21:09Z","2009-12"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Computer Science"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Thesis"]},{"key":"thesis:degree_name","label":"Degree Name","values":["M.S."]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["University of Illinois at Urbana-Champaign"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Opinion Summarization","Contrastive Opinion Summary","Text mining"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["en"]},{"key":"dc:rights","label":"Dc Rights","values":["Copyright 2009 by Hyun Duk Kim. All rights reserved."]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["http://hdl.handle.net/2142/14680"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["This thesis presents a study of a novel summarization problem called contrastive opinion summarization (COS). Given two sets of positively and negatively opinionated sentences which are often the output of an existing opinion summarizer, COS aims to extract comparable sentences from each set of opinions and generate a comparative summary containing a set of contrastive sentence pairs. We formally formulate the problem as an optimization problem and propose two general methods for generating a comparative summary using the framework, both of which rely on measuring the content similarity and contrastive similarity of two sentences. We study several strategies to compute these two similarities. We also create a test data set for evaluating such a novel summarization problem. Experiment results on this test set show that the proposed methods are effective for generating comparative summaries of contradictory opinions. In addition, we implemented two demo systems which show the usefulness of the algorithm intuitively.","Item withdrawn by Mark Zulauf (zulauf@illinois.edu) on 2009-12-10T21:33:00Z Item was in collections: University of Illinois Theses & Dissertations (ID: 1) No. of bitstreams: 1 Kim_Hyun Duk.pdf: 4857592 bytes, checksum: fa404624087e7ec7eac2fdd988d4ab95 (MD5)","Made available in DSpace on 2010-01-06T16:21:09Z (GMT). No. of bitstreams: 5 license.txt: 4057 bytes, checksum: 4edd3f26960cfcee5c25a9cabce8737f (MD5) Kim_Hyun Duk.pdf: 4857591 bytes, checksum: e3809471e8732be2f5a19a7e0095bdb9 (MD5) 1_Kim_Hyun Duk.pdf: 4857601 bytes, checksum: 82fbcb4e951b9ff7d41229c52c91ee2f (MD5) 2_Kim_Hyun Duk.pdf: 4857596 bytes, checksum: d420e7cb1c51c49e49934e16853537c4 (MD5) 3_Kim_Hyun Duk.pdf: 4857592 bytes, checksum: fa404624087e7ec7eac2fdd988d4ab95 (MD5)"]},{"key":"dc:title","label":"Title","values":["Generating comparative summaries of contradictory opinions in text"]}]}],"canonical_facts":{"dc:contributor":["Zhai, ChengXiang"],"dc:creator":["Kim, Hyun Duk"],"dc:date":["2010-01-06T16:21:09Z","2009-12"],"dc:description":["This thesis presents a study of a novel summarization problem called contrastive opinion summarization (COS). Given two sets of positively and negatively opinionated sentences which are often the output of an existing opinion summarizer, COS aims to extract comparable sentences from each set of opinions and generate a comparative summary containing a set of contrastive sentence pairs. We formally formulate the problem as an optimization problem and propose two general methods for generating a comparative summary using the framework, both of which rely on measuring the content similarity and contrastive similarity of two sentences. We study several strategies to compute these two similarities. We also create a test data set for evaluating such a novel summarization problem. Experiment results on this test set show that the proposed methods are effective for generating comparative summaries of contradictory opinions. In addition, we implemented two demo systems which show the usefulness of the algorithm intuitively.","Item withdrawn by Mark Zulauf (zulauf@illinois.edu) on 2009-12-10T21:33:00Z Item was in collections: University of Illinois Theses & Dissertations (ID: 1) No. of bitstreams: 1 Kim_Hyun Duk.pdf: 4857592 bytes, checksum: fa404624087e7ec7eac2fdd988d4ab95 (MD5)","Made available in DSpace on 2010-01-06T16:21:09Z (GMT). No. of bitstreams: 5 license.txt: 4057 bytes, checksum: 4edd3f26960cfcee5c25a9cabce8737f (MD5) Kim_Hyun Duk.pdf: 4857591 bytes, checksum: e3809471e8732be2f5a19a7e0095bdb9 (MD5) 1_Kim_Hyun Duk.pdf: 4857601 bytes, checksum: 82fbcb4e951b9ff7d41229c52c91ee2f (MD5) 2_Kim_Hyun Duk.pdf: 4857596 bytes, checksum: d420e7cb1c51c49e49934e16853537c4 (MD5) 3_Kim_Hyun Duk.pdf: 4857592 bytes, checksum: fa404624087e7ec7eac2fdd988d4ab95 (MD5)"],"dc:identifier":["http://hdl.handle.net/2142/14680"],"dc:language":["en"],"dc:rights":["Copyright 2009 by Hyun Duk Kim. All rights reserved."],"dc:subject":["Opinion Summarization","Contrastive Opinion Summary","Text mining"],"dc:title":["Generating comparative summaries of contradictory opinions in text"],"thesis:degree_discipline":["Computer Science"],"thesis:degree_level":["Thesis"],"thesis:degree_name":["M.S."],"thesis:institution_name":["University of Illinois at Urbana-Champaign"]},"updated_at":"2026-07-22T22:25:08Z"}