{"id":{"repo_id":"msu","oai_identifier":"oai:d.lib.msu.edu:etd_52773"},"canonical_url":"https://search.ndltd.org/etd/msu/oai:d.lib.msu.edu:etd_52773","repository":{"repo_id":"msu","name":"Michigan State University","base_url":"https://d.lib.msu.edu/oai"},"display":{"title":"UNDERSTANDING SOCIAL NETWORKS ON SOCIAL MEDIA : MACHINE LEARNING, SOCIAL INFLUENCE, AND SENSITIVITY ANALYSIS IN TWITTER DISCOURSES ON CRITICAL RACE THEORY","abstract":"Thesis (Ph.D.)--Michigan State University. Measurement and Quantitative Methods - Doctor of Philosophy, 2025","abstract_html":"Thesis (Ph.D.)--Michigan State University. Measurement and Quantitative Methods - Doctor of Philosophy, 2025","abstract_has_math":false,"creators":["Dai, Shimeng"],"institution":null,"degree_name":null,"degree_level":null,"degree_discipline":null,"degree_department":null,"school":null,"contributors":["Frank, Kenneth","Gorney, Kylie","Xu, Ran","Murillo, Michael"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2025,"date_issued":"2025","date_published":"2025","updated_at":"2026-11-18T18:59:28Z","subjects":["Educational tests & measurements","Artificial intelligence","Education policy","Education and state","Educational tests and measurements"],"languages":["eng"],"rights":["In Copyright"],"rights_urls":[],"identifier_entries":[{"key":"dc:identifier","label":"Identifier","values":["etd:52773","local:Dai_grad.msu_0128D_21767"],"render_values":[{"text":"etd:52773","href":null,"code":true},{"text":"local:Dai_grad.msu_0128D_21767","href":null,"code":true}]}],"person_identifier_entries":[]},"links":{"outbound_url":"https://doi.org/doi:10.25335/tkf2-0883","outbound_label":"DOI","outbound_source":"dc:identifier","record_url":"https://doi.org/doi:10.25335/tkf2-0883","record_label":"Repository record","record_kind":"doi","record_source":"dc:identifier","download_url":null,"download_label":null,"download_source":null,"access_status":null,"embargo_until":null,"access_note":null},"source_record":{"url":"https://d.lib.msu.edu/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai%3Ad.lib.msu.edu%3Aetd_52773","prefix":"oai_dc"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Frank, Kenneth","Gorney, Kylie","Xu, Ran","Murillo, Michael"]},{"key":"dc:creator","label":"Author","values":["Dai, Shimeng"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2025"]},{"key":"dc:relation","label":"Dc Relation","values":["Electronic Theses & Dissertations"]},{"key":"dc:type","label":"Dc Type","values":["text","Electronic dissertations"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Educational tests & measurements","Artificial intelligence","Education policy","Education and state","Educational tests and measurements"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["eng"]},{"key":"dc:rights","label":"Dc Rights","values":["In Copyright"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["etd:52773","local:Dai_grad.msu_0128D_21767","https://doi.org/doi:10.25335/tkf2-0883"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Thesis (Ph.D.)--Michigan State University. Measurement and Quantitative Methods - Doctor of Philosophy, 2025","This dissertation brings together three interconnected studies that collectively examine online discourse surrounding Critical Race Theory (CRT) while advancing methodological innovations in evaluating machine learning (ML) model performance through sensitivity analysis. Study 1 employs a combination of natural language processing (NLP) and ML techniques to categorize CRT-related tweets, assessing both topical relevance and sentiment. It comparatively assesses various feature extraction methods and classification models for detecting tweets relating to CRT, school board recalls, and transgender student rights (TSR), as well as discerning right-leaning sentiments. Study 2 builds on the optimal models established in Study 1, using the influence model to investigate the influence process and the patterns of user engagement with these topics and sentiments. Focused on the Loudoun County school board recall, this study explores how exposure within Twitter networks influences subsequent tweeting behaviors, highlighting the amplification roles of both bot-like and human users in promoting right-leaning sentiments. Study 3 introduces a methodological innovation through the MCRINI sensitivity framework. Derived from the mathematical equivalence between the area under the ROC curve (AUC) and the Mann-Whitney-Wilcoxon rank-sum test, this framework conceptualizes ML model performance as robustness to rank shifts. It quantifies sensitivity in terms of the number of cases that need to be re-ranked in order to nullify the inference, which improves both interpretability and stakeholder engagement in social science applications of ML.","Description based on online resource. Title from PDF t.p. (Michigan State University Fedora Repository, viewed ).","Includes bibliographical references."]},{"key":"dc:format","label":"Dc Format","values":["application/pdf","1 online resource (165 p.) : ill."]},{"key":"dc:title","label":"Title","values":["UNDERSTANDING SOCIAL NETWORKS ON SOCIAL MEDIA : MACHINE LEARNING, SOCIAL INFLUENCE, AND SENSITIVITY ANALYSIS IN TWITTER DISCOURSES ON CRITICAL RACE THEORY"]}]}],"canonical_facts":{"dc:contributor":["Frank, Kenneth","Gorney, Kylie","Xu, Ran","Murillo, Michael"],"dc:creator":["Dai, Shimeng"],"dc:date":["2025"],"dc:description":["Thesis (Ph.D.)--Michigan State University. Measurement and Quantitative Methods - Doctor of Philosophy, 2025","This dissertation brings together three interconnected studies that collectively examine online discourse surrounding Critical Race Theory (CRT) while advancing methodological innovations in evaluating machine learning (ML) model performance through sensitivity analysis. Study 1 employs a combination of natural language processing (NLP) and ML techniques to categorize CRT-related tweets, assessing both topical relevance and sentiment. It comparatively assesses various feature extraction methods and classification models for detecting tweets relating to CRT, school board recalls, and transgender student rights (TSR), as well as discerning right-leaning sentiments. Study 2 builds on the optimal models established in Study 1, using the influence model to investigate the influence process and the patterns of user engagement with these topics and sentiments. Focused on the Loudoun County school board recall, this study explores how exposure within Twitter networks influences subsequent tweeting behaviors, highlighting the amplification roles of both bot-like and human users in promoting right-leaning sentiments. Study 3 introduces a methodological innovation through the MCRINI sensitivity framework. Derived from the mathematical equivalence between the area under the ROC curve (AUC) and the Mann-Whitney-Wilcoxon rank-sum test, this framework conceptualizes ML model performance as robustness to rank shifts. It quantifies sensitivity in terms of the number of cases that need to be re-ranked in order to nullify the inference, which improves both interpretability and stakeholder engagement in social science applications of ML.","Description based on online resource. Title from PDF t.p. (Michigan State University Fedora Repository, viewed ).","Includes bibliographical references."],"dc:format":["application/pdf","1 online resource (165 p.) : ill."],"dc:identifier":["etd:52773","local:Dai_grad.msu_0128D_21767","https://doi.org/doi:10.25335/tkf2-0883"],"dc:language":["eng"],"dc:relation":["Electronic Theses & Dissertations"],"dc:rights":["In Copyright"],"dc:subject":["Educational tests & measurements","Artificial intelligence","Education policy","Education and state","Educational tests and measurements"],"dc:title":["UNDERSTANDING SOCIAL NETWORKS ON SOCIAL MEDIA : MACHINE LEARNING, SOCIAL INFLUENCE, AND SENSITIVITY ANALYSIS IN TWITTER DISCOURSES ON CRITICAL RACE THEORY"],"dc:type":["text","Electronic dissertations"]},"updated_at":"2026-11-18T18:59:28Z"}