{"id":{"repo_id":"birmingham","oai_identifier":"oai:etheses.bham.ac.uk:15892"},"canonical_url":"https://search.ndltd.org/etd/birmingham/oai:etheses.bham.ac.uk:15892","repository":{"repo_id":"birmingham","name":"University of Birmingham","base_url":"https://etheses.bham.ac.uk/cgi/oai2"},"display":{"title":"Essays on the use of machine learning in economics: The case of Brexit","abstract":"This thesis comprises three papers on Brexit, focusing on uncertainty and non-verbal media bias, utilizing cutting-edge machine learning techniques. The first paper constructs a set of indices to measure Brexit-related uncertainty by analyzing newspaper coverage from 2013 to 2022. Employing machine learning techniques, these indices provide a real-time view of uncertainty trends, including topic-specific indices for key areas such as trade, immigration, and employment. The paper also distinguishes between Brexit-related uncertainty and the impact of the COVID-19 pandemic. The second paper examines visual media bias during the 2016 Brexit referendum by analyzing how UK newspapers depicted politicians in images. Using machine learning and computer vision tools, the analysis uncovers clear partisan bias, particularly in tabloid newspapers, which tended to portray politicians aligned with their stance more positively and placed them in more favorable contexts. This bias was especially pronounced in front-page images and among a few key politicians but diminished after the referendum. The third paper explores the economic consequences of Brexit uncertainty using a proxy structural vector autoregressive (proxy-SVAR) model. To identify Brexit uncertainty shocks, we construct an external instrument based on a high-frequency Brexit uncertainty index developed in the first paper. Our results indicate a short-term boost in economic activity following the uncertainty shocks, driven by a temporary stimulus to the tradable sector. Collectively, these papers enhance our understanding of Brexit-related uncertainty, its economic consequences, and visual media slant during the referendum, providing valuable insights for policymaking efforts and media analysis.","abstract_html":"This thesis comprises three papers on Brexit, focusing on uncertainty and non-verbal media bias, utilizing cutting-edge machine learning techniques. The first paper constructs a set of indices to measure Brexit-related uncertainty by analyzing newspaper coverage from 2013 to 2022. Employing machine learning techniques, these indices provide a real-time view of uncertainty trends, including topic-specific indices for key areas such as trade, immigration, and employment. The paper also distinguishes between Brexit-related uncertainty and the impact of the COVID-19 pandemic. The second paper examines visual media bias during the 2016 Brexit referendum by analyzing how UK newspapers depicted politicians in images. Using machine learning and computer vision tools, the analysis uncovers clear partisan bias, particularly in tabloid newspapers, which tended to portray politicians aligned with their stance more positively and placed them in more favorable contexts. This bias was especially pronounced in front-page images and among a few key politicians but diminished after the referendum. The third paper explores the economic consequences of Brexit uncertainty using a proxy structural vector autoregressive (proxy-SVAR) model. To identify Brexit uncertainty shocks, we construct an external instrument based on a high-frequency Brexit uncertainty index developed in the first paper. Our results indicate a short-term boost in economic activity following the uncertainty shocks, driven by a temporary stimulus to the tradable sector. Collectively, these papers enhance our understanding of Brexit-related uncertainty, its economic consequences, and visual media slant during the referendum, providing valuable insights for policymaking efforts and media analysis.","abstract_has_math":false,"creators":["Dai, Duiyi"],"institution":"University of Birmingham","degree_name":"d_ph","degree_level":"d_ph","degree_discipline":null,"degree_department":null,"school":null,"contributors":[],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2025,"date_issued":"2025-07","date_published":"2025-07","updated_at":"2026-11-19T09:33:03Z","subjects":["H Social Sciences (General)"],"languages":["eng"],"rights":[],"rights_urls":[],"identifier_entries":[],"person_identifier_entries":[]},"links":{"outbound_url":null,"outbound_label":null,"outbound_source":null,"record_url":null,"record_label":null,"record_kind":null,"record_source":null,"download_url":"http://etheses.bham.ac.uk//id/eprint/15892/7/Dai2025PhD.pdf","download_label":"Download PDF","download_source":"dc:identifier.uri","access_status":null,"embargo_until":null,"access_note":null},"source_record":{"url":"https://etheses.bham.ac.uk/cgi/oai2?verb=GetRecord&metadataPrefix=uketd_dc&identifier=oai%3Aetheses.bham.ac.uk%3A15892","prefix":"uketd_dc"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.sponsor","label":"Sponsor","values":["na"]},{"key":"dc:creator","label":"Author","values":["Dai, Duiyi"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2025-07-16"]},{"key":"dc:date.issued","label":"Date","values":["2025-07"]},{"key":"dc:publisher.department","label":"Dc Publisher Department","values":["College of Social Sciences","Birmingham Business School, Department of Economics"]},{"key":"dc:publisher.institution","label":"Dc Publisher Institution","values":["University of Birmingham"]},{"key":"dc:relation.isreferencedby","label":"Dc Relation Isreferencedby","values":["http://etheses.bham.ac.uk//id/eprint/15892/"]},{"key":"dc:type","label":"Dc Type","values":["Thesis"]},{"key":"dc:type.qualificationlevel","label":"Dc Type Qualificationlevel","values":["d_ph"]},{"key":"dc:type.qualificationname","label":"Dc Type Qualificationname","values":["d_ph"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["H Social Sciences (General)"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language.dcterms_iso639_2","label":"Language (ISO 639-2)","values":["eng"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["http://etheses.bham.ac.uk//id/eprint/15892/7/Dai2025PhD.pdf"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["This thesis comprises three papers on Brexit, focusing on uncertainty and non-verbal media bias, utilizing cutting-edge machine learning techniques. The first paper constructs a set of indices to measure Brexit-related uncertainty by analyzing newspaper coverage from 2013 to 2022. Employing machine learning techniques, these indices provide a real-time view of uncertainty trends, including topic-specific indices for key areas such as trade, immigration, and employment. The paper also distinguishes between Brexit-related uncertainty and the impact of the COVID-19 pandemic. The second paper examines visual media bias during the 2016 Brexit referendum by analyzing how UK newspapers depicted politicians in images. Using machine learning and computer vision tools, the analysis uncovers clear partisan bias, particularly in tabloid newspapers, which tended to portray politicians aligned with their stance more positively and placed them in more favorable contexts. This bias was especially pronounced in front-page images and among a few key politicians but diminished after the referendum. The third paper explores the economic consequences of Brexit uncertainty using a proxy structural vector autoregressive (proxy-SVAR) model. To identify Brexit uncertainty shocks, we construct an external instrument based on a high-frequency Brexit uncertainty index developed in the first paper. Our results indicate a short-term boost in economic activity following the uncertainty shocks, driven by a temporary stimulus to the tradable sector. Collectively, these papers enhance our understanding of Brexit-related uncertainty, its economic consequences, and visual media slant during the referendum, providing valuable insights for policymaking efforts and media analysis."]},{"key":"dc:format","label":"Dc Format","values":["text"]},{"key":"dcterms:accessrights","label":"Dcterms Accessrights","values":["public"]},{"key":"dc:title","label":"Title","values":["Essays on the use of machine learning in economics: The case of Brexit"]}]}],"canonical_facts":{"dc:contributor.sponsor":["na"],"dc:creator":["Dai, Duiyi"],"dc:date":["2025-07-16"],"dc:date.issued":["2025-07"],"dc:description.abstract":["This thesis comprises three papers on Brexit, focusing on uncertainty and non-verbal media bias, utilizing cutting-edge machine learning techniques. The first paper constructs a set of indices to measure Brexit-related uncertainty by analyzing newspaper coverage from 2013 to 2022. Employing machine learning techniques, these indices provide a real-time view of uncertainty trends, including topic-specific indices for key areas such as trade, immigration, and employment. The paper also distinguishes between Brexit-related uncertainty and the impact of the COVID-19 pandemic. The second paper examines visual media bias during the 2016 Brexit referendum by analyzing how UK newspapers depicted politicians in images. Using machine learning and computer vision tools, the analysis uncovers clear partisan bias, particularly in tabloid newspapers, which tended to portray politicians aligned with their stance more positively and placed them in more favorable contexts. This bias was especially pronounced in front-page images and among a few key politicians but diminished after the referendum. The third paper explores the economic consequences of Brexit uncertainty using a proxy structural vector autoregressive (proxy-SVAR) model. To identify Brexit uncertainty shocks, we construct an external instrument based on a high-frequency Brexit uncertainty index developed in the first paper. Our results indicate a short-term boost in economic activity following the uncertainty shocks, driven by a temporary stimulus to the tradable sector. Collectively, these papers enhance our understanding of Brexit-related uncertainty, its economic consequences, and visual media slant during the referendum, providing valuable insights for policymaking efforts and media analysis."],"dc:format":["text"],"dc:identifier.uri":["http://etheses.bham.ac.uk//id/eprint/15892/7/Dai2025PhD.pdf"],"dc:language.dcterms_iso639_2":["eng"],"dc:publisher.department":["College of Social Sciences","Birmingham Business School, Department of Economics"],"dc:publisher.institution":["University of Birmingham"],"dc:relation.isreferencedby":["http://etheses.bham.ac.uk//id/eprint/15892/"],"dc:subject":["H Social Sciences (General)"],"dcterms:accessrights":["public"],"dc:title":["Essays on the use of machine learning in economics: The case of Brexit"],"dc:type":["Thesis"],"dc:type.qualificationlevel":["d_ph"],"dc:type.qualificationname":["d_ph"]},"updated_at":"2026-11-19T09:33:03Z"}