{"id":{"repo_id":"calpoly","oai_identifier":"oai:digitalcommons.calpoly.edu:theses-5096"},"canonical_url":"https://search.ndltd.org/etd/calpoly/oai:digitalcommons.calpoly.edu:theses-5096","repository":{"repo_id":"calpoly","name":"Cal Poly","base_url":"https://digitalcommons.calpoly.edu/do/oai/"},"display":{"title":"Predicting Student Belonging in Computing Education: A Multimodal Machine Learning Approach Using EEG and Survey Data","abstract":"Measuring students’ sense of belonging, characterized by feelings of acceptance, inclusion, and encouragement from teachers, remains a significant challenge in computing education. Prior research has associated this multidimensional construct with positive academic outcomes and has identified instructors’ growth- and fixed-mindset messaging as a potential influence. However, belonging is a complex and deeply personal experience that is difficult to capture through direct observation alone. Current measurement methods rely on self-report surveys, which may not capture every aspect of an experience that can also involve emotional and cognitive responses. This thesis investigates whether combining EEG data recorded during a belonging questionnaire with survey responses can improve the classification of students’ sense of belonging in computing education. Supervised multimodal machine learning models were constructed using several label-construction approaches derived from student survey responses. Multiple EEG representations were explored, including raw signals and two-dimensional scalograms. Because EEG-based machine learning is challenged by noisy recordings and limited training data, data augmentation was applied to the scalogram representations to improve model generalization. CNN-LSTM, CNN-GRU, and ChronoNet architectures were evaluated on these inputs, with the multimodal 2D CNN-GRU model achieving the strongest performance at an accuracy of 87.5% compared with its corresponding survey-only baseline of 80.0%. These findings offer preliminary evidence that EEG may provide complementary information and support more comprehensive approaches to understanding belonging in computing education.","abstract_html":"Measuring students’ sense of belonging, characterized by feelings of acceptance, inclusion, and encouragement from teachers, remains a significant challenge in computing education. Prior research has associated this multidimensional construct with positive academic outcomes and has identified instructors’ growth- and fixed-mindset messaging as a potential influence. However, belonging is a complex and deeply personal experience that is difficult to capture through direct observation alone. Current measurement methods rely on self-report surveys, which may not capture every aspect of an experience that can also involve emotional and cognitive responses. This thesis investigates whether combining EEG data recorded during a belonging questionnaire with survey responses can improve the classification of students’ sense of belonging in computing education. Supervised multimodal machine learning models were constructed using several label-construction approaches derived from student survey responses. Multiple EEG representations were explored, including raw signals and two-dimensional scalograms. Because EEG-based machine learning is challenged by noisy recordings and limited training data, data augmentation was applied to the scalogram representations to improve model generalization. CNN-LSTM, CNN-GRU, and ChronoNet architectures were evaluated on these inputs, with the multimodal 2D CNN-GRU model achieving the strongest performance at an accuracy of 87.5% compared with its corresponding survey-only baseline of 80.0%. These findings offer preliminary evidence that EEG may provide complementary information and support more comprehensive approaches to understanding belonging in computing education.","abstract_has_math":false,"creators":["Moshtaghi, Hannah"],"institution":null,"degree_name":"MS in Computer Science","degree_level":null,"degree_discipline":"Computer Science","degree_department":null,"school":null,"contributors":["Sumona Mukhopadhyay","Computer Science","College of Engineering"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":null,"date_issued":"","date_published":null,"updated_at":"2026-11-19T07:13:00Z","subjects":["Student belonging","computing education","EEG","multimodal learning","scalograms","Artificial Intelligence and Robotics","Data Science","Education","Engineering Education","School Psychology"],"languages":[],"rights":[],"rights_urls":[],"identifier_entries":[],"person_identifier_entries":[]},"links":{"outbound_url":"https://digitalcommons.calpoly.edu/theses/3418","outbound_label":"Repository record","outbound_source":"dc:identifier","record_url":"https://digitalcommons.calpoly.edu/theses/3418","record_label":"Repository record","record_kind":"record","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://digitalcommons.calpoly.edu/do/oai/?verb=GetRecord&metadataPrefix=oai_etdms&identifier=oai%3Adigitalcommons.calpoly.edu%3Atheses-5096","prefix":"oai_etdms"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Sumona Mukhopadhyay","Computer Science","College of Engineering"]},{"key":"dc:creator","label":"Author","values":["Moshtaghi, Hannah"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.available","label":"Dc Date Available","values":["2026-08-12T07:00:00Z"]},{"key":"dc:date.created","label":"Dc Date Created","values":["2026-08-01T07:00:00Z"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Computer Science"]},{"key":"thesis:degree_name","label":"Degree Name","values":["MS in Computer Science"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Student belonging","computing education","EEG","multimodal learning","scalograms","Artificial Intelligence and Robotics","Data Science","Education","Engineering Education","School Psychology"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://digitalcommons.calpoly.edu/theses/3418"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Measuring students’ sense of belonging, characterized by feelings of acceptance, inclusion, and encouragement from teachers, remains a significant challenge in computing education. Prior research has associated this multidimensional construct with positive academic outcomes and has identified instructors’ growth- and fixed-mindset messaging as a potential influence. However, belonging is a complex and deeply personal experience that is difficult to capture through direct observation alone. Current measurement methods rely on self-report surveys, which may not capture every aspect of an experience that can also involve emotional and cognitive responses. This thesis investigates whether combining EEG data recorded during a belonging questionnaire with survey responses can improve the classification of students’ sense of belonging in computing education. Supervised multimodal machine learning models were constructed using several label-construction approaches derived from student survey responses. Multiple EEG representations were explored, including raw signals and two-dimensional scalograms. Because EEG-based machine learning is challenged by noisy recordings and limited training data, data augmentation was applied to the scalogram representations to improve model generalization. CNN-LSTM, CNN-GRU, and ChronoNet architectures were evaluated on these inputs, with the multimodal 2D CNN-GRU model achieving the strongest performance at an accuracy of 87.5% compared with its corresponding survey-only baseline of 80.0%. These findings offer preliminary evidence that EEG may provide complementary information and support more comprehensive approaches to understanding belonging in computing education."]},{"key":"dc:title","label":"Title","values":["Predicting Student Belonging in Computing Education: A Multimodal Machine Learning Approach Using EEG and Survey Data"]}]}],"canonical_facts":{"dc:contributor":["Sumona Mukhopadhyay","Computer Science","College of Engineering"],"dc:creator":["Moshtaghi, Hannah"],"dc:date.available":["2026-08-12T07:00:00Z"],"dc:date.created":["2026-08-01T07:00:00Z"],"dc:description.abstract":["Measuring students’ sense of belonging, characterized by feelings of acceptance, inclusion, and encouragement from teachers, remains a significant challenge in computing education. Prior research has associated this multidimensional construct with positive academic outcomes and has identified instructors’ growth- and fixed-mindset messaging as a potential influence. However, belonging is a complex and deeply personal experience that is difficult to capture through direct observation alone. Current measurement methods rely on self-report surveys, which may not capture every aspect of an experience that can also involve emotional and cognitive responses. This thesis investigates whether combining EEG data recorded during a belonging questionnaire with survey responses can improve the classification of students’ sense of belonging in computing education. Supervised multimodal machine learning models were constructed using several label-construction approaches derived from student survey responses. Multiple EEG representations were explored, including raw signals and two-dimensional scalograms. Because EEG-based machine learning is challenged by noisy recordings and limited training data, data augmentation was applied to the scalogram representations to improve model generalization. CNN-LSTM, CNN-GRU, and ChronoNet architectures were evaluated on these inputs, with the multimodal 2D CNN-GRU model achieving the strongest performance at an accuracy of 87.5% compared with its corresponding survey-only baseline of 80.0%. These findings offer preliminary evidence that EEG may provide complementary information and support more comprehensive approaches to understanding belonging in computing education."],"dc:identifier":["https://digitalcommons.calpoly.edu/theses/3418"],"dc:subject":["Student belonging","computing education","EEG","multimodal learning","scalograms","Artificial Intelligence and Robotics","Data Science","Education","Engineering Education","School Psychology"],"dc:title":["Predicting Student Belonging in Computing Education: A Multimodal Machine Learning Approach Using EEG and Survey Data"],"thesis:degree_discipline":["Computer Science"],"thesis:degree_name":["MS in Computer Science"]},"updated_at":"2026-11-19T07:13:00Z"}