{"id":{"repo_id":"vt","oai_identifier":"oai:vtechworks.lib.vt.edu:10919/137518"},"canonical_url":"https://search.dev.ndltd.org/etd/vt/oai:vtechworks.lib.vt.edu:10919/137518","repository":{"repo_id":"vt","name":"Virginia Tech","base_url":"https://vtechworks.lib.vt.edu/oai/request"},"display":{"title":"Enhancing Learning Algorithms in Computer Science on YouTube: A Personalized Educational System, EduTube AI","abstract":"In the context of self-directed computer science education, our studies show that learners often struggle to find high quality algorithm content that matches their current level and supports a coherent progression. Despite the popularity of platforms like YouTube, many users report challenges such as overwhelming search results, inconsistent instructional quality, and a lack of personalized learning paths. To explore these issues, we conducted a series of learner focused studies examining how individuals search for and engage with algorithm-related content online, and what barriers they encounter along the way. Drawing on these insights, we developed EduTube AI, a tool that integrates the YouTube API with GPT-4 to provide personalized video recommendations for algorithm learning. The system uses the learner's knowledge level, suggests relevant videos, and offers brief follow up quiz to reinforce the material. A follow-up study was conducted to gather user feedback on the tool's perceived relevance, structure, and support for learning progression. While the results are exploratory, they suggest directions for how AI-based systems might be used to support more adaptive and learner-centered experiences in open educational environments.","abstract_html":"In the context of self-directed computer science education, our studies show that learners often struggle to find high quality algorithm content that matches their current level and supports a coherent progression. Despite the popularity of platforms like YouTube, many users report challenges such as overwhelming search results, inconsistent instructional quality, and a lack of personalized learning paths. To explore these issues, we conducted a series of learner focused studies examining how individuals search for and engage with algorithm-related content online, and what barriers they encounter along the way. Drawing on these insights, we developed EduTube AI, a tool that integrates the YouTube API with GPT-4 to provide personalized video recommendations for algorithm learning. The system uses the learner's knowledge level, suggests relevant videos, and offers brief follow up quiz to reinforce the material. A follow-up study was conducted to gather user feedback on the tool's perceived relevance, structure, and support for learning progression. While the results are exploratory, they suggest directions for how AI-based systems might be used to support more adaptive and learner-centered experiences in open educational environments.","abstract_has_math":false,"creators":["Farzanehpour, Sahar"],"institution":"Virginia Tech","degree_name":"Master of Science","degree_level":"masters","degree_discipline":"Computer Science & Applications","degree_department":"Computer Science and Applications","school":null,"contributors":[],"advisors":[],"committee_chairs":["Brown, Dwayne Christian"],"committee_members":["Seyam, Mohammed","Gulzar, Muhammad Ali"],"year":2025,"date_issued":"2025-08-15","date_published":"2025-08-15","updated_at":"2026-07-22T22:19:47Z","subjects":["Software Engineering","AI","Education"],"languages":["en"],"rights":["In Copyright"],"rights_urls":["http://rightsstatements.org/vocab/InC/1.0/"],"identifier_entries":[{"key":"dc:identifier.other","label":"Dc Identifier Other","values":["vt_gsexam:44445"],"render_values":[{"text":"vt_gsexam:44445","href":null,"code":true}]}]},"links":{"outbound_url":"https://hdl.handle.net/10919/137518","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.committeechair","label":"Committee Chair","values":["Brown, Dwayne Christian"]},{"key":"dc:contributor.committeemember","label":"Committee Member","values":["Seyam, Mohammed","Gulzar, Muhammad Ali"]},{"key":"dc:contributor.department","label":"Department","values":["Computer Science and Applications"]},{"key":"dc:creator","label":"Author","values":["Farzanehpour, Sahar"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2025-08-16T08:00:17Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2025-08-16T08:00:17Z"]},{"key":"dc:date.issued","label":"Date","values":["2025-08-15"]},{"key":"dc:publisher","label":"Institution","values":["Virginia Tech"]},{"key":"dc:type","label":"Dc Type","values":["Thesis"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Computer Science & Applications"]},{"key":"thesis:degree_level","label":"Degree Level","values":["masters"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Master of Science"]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["Virginia Polytechnic Institute and State University"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Software Engineering","AI","Education"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language.iso","label":"Language (ISO)","values":["en"]},{"key":"dc:rights","label":"Dc Rights","values":["In Copyright"]},{"key":"dc:rights.uri","label":"Rights URI","values":["http://rightsstatements.org/vocab/InC/1.0/"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.other","label":"Dc Identifier Other","values":["vt_gsexam:44445"]},{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://hdl.handle.net/10919/137518"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["In the context of self-directed computer science education, our studies show that learners often struggle to find high quality algorithm content that matches their current level and supports a coherent progression. Despite the popularity of platforms like YouTube, many users report challenges such as overwhelming search results, inconsistent instructional quality, and a lack of personalized learning paths. To explore these issues, we conducted a series of learner focused studies examining how individuals search for and engage with algorithm-related content online, and what barriers they encounter along the way. Drawing on these insights, we developed EduTube AI, a tool that integrates the YouTube API with GPT-4 to provide personalized video recommendations for algorithm learning. The system uses the learner's knowledge level, suggests relevant videos, and offers brief follow up quiz to reinforce the material. A follow-up study was conducted to gather user feedback on the tool's perceived relevance, structure, and support for learning progression. While the results are exploratory, they suggest directions for how AI-based systems might be used to support more adaptive and learner-centered experiences in open educational environments."]},{"key":"dc:description.abstractgeneral","label":"General Abstract","values":["Learning algorithms can be one of the hardest parts of studying computer science, and finding helpful videos online doesn't always make it easier. Many people turn to YouTube for explanations, but it's not always clear which videos are right for them, or where to start if they feel lost. To understand this better, we asked learners about the challenges they face when studying algorithms and using platforms like YouTube. Their answers helped shape a new tool we created, called EduTube AI. EduTube AI is designed to help people find videos that better match what they already know. It asks a few questions first to get a sense of the user's goals and level of knowledge, then recommends a video that fits, along with a short practice activity. We also asked users to try the tool and share their thoughts. While it's still early, the feedback offers some ideas for how smart tools like this could help make learning online a little more organized and easier to follow."]},{"key":"dc:description.degree","label":"Dc Description Degree","values":["Master of Science"]},{"key":"dc:format.medium","label":"Dc Format Medium","values":["ETD"]},{"key":"dc:title","label":"Title","values":["Enhancing Learning Algorithms in Computer Science on YouTube: A Personalized Educational System, EduTube AI"]}]}],"canonical_facts":{"dc:contributor.committeechair":["Brown, Dwayne Christian"],"dc:contributor.committeemember":["Seyam, Mohammed","Gulzar, Muhammad Ali"],"dc:contributor.department":["Computer Science and Applications"],"dc:creator":["Farzanehpour, Sahar"],"dc:date.accessioned":["2025-08-16T08:00:17Z"],"dc:date.available":["2025-08-16T08:00:17Z"],"dc:date.issued":["2025-08-15"],"dc:description.abstract":["In the context of self-directed computer science education, our studies show that learners often struggle to find high quality algorithm content that matches their current level and supports a coherent progression. Despite the popularity of platforms like YouTube, many users report challenges such as overwhelming search results, inconsistent instructional quality, and a lack of personalized learning paths. To explore these issues, we conducted a series of learner focused studies examining how individuals search for and engage with algorithm-related content online, and what barriers they encounter along the way. Drawing on these insights, we developed EduTube AI, a tool that integrates the YouTube API with GPT-4 to provide personalized video recommendations for algorithm learning. The system uses the learner's knowledge level, suggests relevant videos, and offers brief follow up quiz to reinforce the material. A follow-up study was conducted to gather user feedback on the tool's perceived relevance, structure, and support for learning progression. While the results are exploratory, they suggest directions for how AI-based systems might be used to support more adaptive and learner-centered experiences in open educational environments."],"dc:description.abstractgeneral":["Learning algorithms can be one of the hardest parts of studying computer science, and finding helpful videos online doesn't always make it easier. Many people turn to YouTube for explanations, but it's not always clear which videos are right for them, or where to start if they feel lost. To understand this better, we asked learners about the challenges they face when studying algorithms and using platforms like YouTube. Their answers helped shape a new tool we created, called EduTube AI. EduTube AI is designed to help people find videos that better match what they already know. It asks a few questions first to get a sense of the user's goals and level of knowledge, then recommends a video that fits, along with a short practice activity. We also asked users to try the tool and share their thoughts. While it's still early, the feedback offers some ideas for how smart tools like this could help make learning online a little more organized and easier to follow."],"dc:description.degree":["Master of Science"],"dc:format.medium":["ETD"],"dc:identifier.other":["vt_gsexam:44445"],"dc:identifier.uri":["https://hdl.handle.net/10919/137518"],"dc:language.iso":["en"],"dc:publisher":["Virginia Tech"],"dc:rights":["In Copyright"],"dc:rights.uri":["http://rightsstatements.org/vocab/InC/1.0/"],"dc:subject":["Software Engineering","AI","Education"],"dc:title":["Enhancing Learning Algorithms in Computer Science on YouTube: A Personalized Educational System, EduTube AI"],"dc:type":["Thesis"],"thesis:degree_discipline":["Computer Science & Applications"],"thesis:degree_level":["masters"],"thesis:degree_name":["Master of Science"],"thesis:institution_name":["Virginia Polytechnic Institute and State University"]},"updated_at":"2026-07-22T22:19:47Z"}