{"id":{"repo_id":"usf","oai_identifier":"oai:digitalcommons.usf.edu:etd-12018"},"canonical_url":"https://search.ndltd.org/etd/usf/oai:digitalcommons.usf.edu:etd-12018","repository":{"repo_id":"usf","name":"University of South Florida","base_url":"https://digitalcommons.usf.edu/do/oai/"},"display":{"title":"Big Data Analytics for Healthcare Social Media: New Algorithms and Insights","abstract":"Over the last two decades, there has been a rapid evolution in information and communication technology, including the emergence of social media. Social media has a significant impact on various fields such as politics, business, culture, education, careers, innovation, and especially healthcare. This influence is not a new phenomenon since a survey from ten years ago showed that up to 78\\% of American adults used the internet to look for health-related information for themselves or someone else. With the shift towards on-demand services in society, healthcare is also affected by this trend. Instead of waiting for weeks or months to see a physician, people prefer to search for information on the Internet. However, the vast amount of information available online makes it challenging to verify the accuracy of the information in real time, leading to the easy spread of misinformation and disinformation. Given the challenges related to social media and health content quality, this dissertation presents new approaches to analyze healthcare social media data. Specifically, (i) using topic modeling and sentiment analysis it sheds light on a possible solution to improve health content quality (Chapter 2), (ii) for improved querying and prediction ability it represents social media in the form of a temporal heterogeneous graph and demonstrates how meta-paths based on the proposed representation can be combined with label propagation algorithm for prediction tasks (Chapter 3), and (iii) demonstrates how new heuristic algorithms can be developed to use the YouTube recommender system to discover temporal viewing habits of pregnant women (Chapter 4).","abstract_html":"Over the last two decades, there has been a rapid evolution in information and communication technology, including the emergence of social media. Social media has a significant impact on various fields such as politics, business, culture, education, careers, innovation, and especially healthcare. This influence is not a new phenomenon since a survey from ten years ago showed that up to 78\\% of American adults used the internet to look for health-related information for themselves or someone else. With the shift towards on-demand services in society, healthcare is also affected by this trend. Instead of waiting for weeks or months to see a physician, people prefer to search for information on the Internet. However, the vast amount of information available online makes it challenging to verify the accuracy of the information in real time, leading to the easy spread of misinformation and disinformation. Given the challenges related to social media and health content quality, this dissertation presents new approaches to analyze healthcare social media data. Specifically, (i) using topic modeling and sentiment analysis it sheds light on a possible solution to improve health content quality (Chapter 2), (ii) for improved querying and prediction ability it represents social media in the form of a temporal heterogeneous graph and demonstrates how meta-paths based on the proposed representation can be combined with label propagation algorithm for prediction tasks (Chapter 3), and (iii) demonstrates how new heuristic algorithms can be developed to use the YouTube recommender system to discover temporal viewing habits of pregnant women (Chapter 4).","abstract_has_math":false,"creators":["Maleki, Negar"],"institution":"University of South Florida","degree_name":"Doctor of Philosophy (Ph.D.)","degree_level":"Dissertation","degree_discipline":"Information Systems and Decision Sciences","degree_department":null,"school":null,"contributors":["Balaji Padmanabhan, Ph.D.","Kaushik Dutta, Ph.D.","Paul C. Kuo, MD, MS, MBA","Tapas K. Das, Ph.D."],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2023,"date_issued":"2023-11-08T08:00:00Z","date_published":"2023-11-08T08:00:00Z","updated_at":"2026-11-19T08:50:14Z","subjects":["Heterogeneous Graph Representation","Incentive-based Platform","Label Propagation","Large Language Models","Prompt Engineering","YouTube Recommender System","Artificial Intelligence and Robotics","Business Administration, Management, and Operations"],"languages":[],"rights":[],"rights_urls":[],"identifier_entries":[],"person_identifier_entries":[]},"links":{"outbound_url":"https://digitalcommons.usf.edu/etd/10731","outbound_label":"Repository record","outbound_source":"dc:identifier","record_url":"https://digitalcommons.usf.edu/etd/10731","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.usf.edu/do/oai/?verb=GetRecord&metadataPrefix=oai_etdms&identifier=oai%3Adigitalcommons.usf.edu%3Aetd-12018","prefix":"oai_etdms"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Balaji Padmanabhan, Ph.D.","Kaushik Dutta, Ph.D.","Paul C. Kuo, MD, MS, MBA","Tapas K. Das, Ph.D."]},{"key":"dc:creator","label":"Author","values":["Maleki, Negar"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2023-11-08T08:00:00Z"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Information Systems and Decision Sciences"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Dissertation","Ph.D."]},{"key":"thesis:degree_name","label":"Degree Name","values":["Doctor of Philosophy (Ph.D.)"]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["University of South Florida"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Heterogeneous Graph Representation","Incentive-based Platform","Label Propagation","Large Language Models","Prompt Engineering","YouTube Recommender System","Artificial Intelligence and Robotics","Business Administration, Management, and Operations"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://digitalcommons.usf.edu/etd/10731"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Over the last two decades, there has been a rapid evolution in information and communication technology, including the emergence of social media. Social media has a significant impact on various fields such as politics, business, culture, education, careers, innovation, and especially healthcare. This influence is not a new phenomenon since a survey from ten years ago showed that up to 78\\% of American adults used the internet to look for health-related information for themselves or someone else. With the shift towards on-demand services in society, healthcare is also affected by this trend. Instead of waiting for weeks or months to see a physician, people prefer to search for information on the Internet. However, the vast amount of information available online makes it challenging to verify the accuracy of the information in real time, leading to the easy spread of misinformation and disinformation. Given the challenges related to social media and health content quality, this dissertation presents new approaches to analyze healthcare social media data. Specifically, (i) using topic modeling and sentiment analysis it sheds light on a possible solution to improve health content quality (Chapter 2), (ii) for improved querying and prediction ability it represents social media in the form of a temporal heterogeneous graph and demonstrates how meta-paths based on the proposed representation can be combined with label propagation algorithm for prediction tasks (Chapter 3), and (iii) demonstrates how new heuristic algorithms can be developed to use the YouTube recommender system to discover temporal viewing habits of pregnant women (Chapter 4)."]},{"key":"dc:title","label":"Title","values":["Big Data Analytics for Healthcare Social Media: New Algorithms and Insights"]}]}],"canonical_facts":{"dc:contributor":["Balaji Padmanabhan, Ph.D.","Kaushik Dutta, Ph.D.","Paul C. Kuo, MD, MS, MBA","Tapas K. Das, Ph.D."],"dc:creator":["Maleki, Negar"],"dc:date":["2023-11-08T08:00:00Z"],"dc:description":["Over the last two decades, there has been a rapid evolution in information and communication technology, including the emergence of social media. Social media has a significant impact on various fields such as politics, business, culture, education, careers, innovation, and especially healthcare. This influence is not a new phenomenon since a survey from ten years ago showed that up to 78\\% of American adults used the internet to look for health-related information for themselves or someone else. With the shift towards on-demand services in society, healthcare is also affected by this trend. Instead of waiting for weeks or months to see a physician, people prefer to search for information on the Internet. However, the vast amount of information available online makes it challenging to verify the accuracy of the information in real time, leading to the easy spread of misinformation and disinformation. Given the challenges related to social media and health content quality, this dissertation presents new approaches to analyze healthcare social media data. Specifically, (i) using topic modeling and sentiment analysis it sheds light on a possible solution to improve health content quality (Chapter 2), (ii) for improved querying and prediction ability it represents social media in the form of a temporal heterogeneous graph and demonstrates how meta-paths based on the proposed representation can be combined with label propagation algorithm for prediction tasks (Chapter 3), and (iii) demonstrates how new heuristic algorithms can be developed to use the YouTube recommender system to discover temporal viewing habits of pregnant women (Chapter 4)."],"dc:identifier":["https://digitalcommons.usf.edu/etd/10731"],"dc:subject":["Heterogeneous Graph Representation","Incentive-based Platform","Label Propagation","Large Language Models","Prompt Engineering","YouTube Recommender System","Artificial Intelligence and Robotics","Business Administration, Management, and Operations"],"dc:title":["Big Data Analytics for Healthcare Social Media: New Algorithms and Insights"],"thesis:degree_discipline":["Information Systems and Decision Sciences"],"thesis:degree_level":["Dissertation","Ph.D."],"thesis:degree_name":["Doctor of Philosophy (Ph.D.)"],"thesis:institution_name":["University of South Florida"]},"updated_at":"2026-11-19T08:50:14Z"}