{"id":{"repo_id":"mit","oai_identifier":"oai:dspace.mit.edu:1721.1/152774"},"canonical_url":"https://search.dev.ndltd.org/etd/mit/oai:dspace.mit.edu:1721.1/152774","repository":{"repo_id":"mit","name":"MIT","base_url":"https://dspace.mit.edu/oai/request"},"display":{"title":"Dynamic Matching of Users and Creators on Social Media Platforms","abstract":"Social media platforms are two-sided markets bridging content creators and users. Existing literature on content recommendation algorithms used by platforms often focuses on user preferences and decisions, and does not jointly address creator incentives. We propose a model of content recommendation that explicitly focuses on dynamic user-content matching, with the novel contribution that both users and creators may leave the platform if they feel dissatisfied. In our model, each player decides to stay or leave at each time step based on utilities derived from the current match: users based on their similarities with the recommended content, and creators based on their audience size. We show that a user-centric greedy algorithm that only maximizes immediate engagement can result in poor total engagement in the long run, even if users and creators are randomly generated from prior distributions, but explicitly maximizing long-term engagement is NP-hard. Finally, we present new practical algorithms with provable guarantees and good empirical performance.","abstract_html":"Social media platforms are two-sided markets bridging content creators and users. Existing literature on content recommendation algorithms used by platforms often focuses on user preferences and decisions, and does not jointly address creator incentives. We propose a model of content recommendation that explicitly focuses on dynamic user-content matching, with the novel contribution that both users and creators may leave the platform if they feel dissatisfied. In our model, each player decides to stay or leave at each time step based on utilities derived from the current match: users based on their similarities with the recommended content, and creators based on their audience size. We show that a user-centric greedy algorithm that only maximizes immediate engagement can result in poor total engagement in the long run, even if users and creators are randomly generated from prior distributions, but explicitly maximizing long-term engagement is NP-hard. Finally, we present new practical algorithms with provable guarantees and good empirical performance.","abstract_has_math":false,"creators":["Lyu, Liang"],"institution":"Massachusetts Institute of Technology","degree_name":"Master","degree_level":null,"degree_discipline":null,"degree_department":"Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science","school":null,"contributors":[],"advisors":["Ozdaglar, Asuman","Huttenlocher, Daniel"],"committee_chairs":[],"committee_members":[],"year":2023,"date_issued":"2023-09","date_published":"2023-09","updated_at":"2026-07-22T22:21:26Z","subjects":[],"languages":[],"rights":["In Copyright - Educational Use Permitted","Copyright retained by author(s)"],"rights_urls":["https://rightsstatements.org/page/InC-EDU/1.0/"],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/1721.1/152774","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Ozdaglar, Asuman","Huttenlocher, Daniel"]},{"key":"dc:contributor.department","label":"Department","values":["Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science"]},{"key":"dc:creator","label":"Author","values":["Lyu, Liang"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2023-11-02T20:15:17Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2023-11-02T20:15:17Z"]},{"key":"dc:date.issued","label":"Date","values":["2023-09"]},{"key":"dc:publisher","label":"Institution","values":["Massachusetts Institute of Technology"]},{"key":"dc:type","label":"Dc Type","values":["Thesis"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Master","Master of Science in Electrical Engineering and Computer Science"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:rights","label":"Dc Rights","values":["In Copyright - Educational Use Permitted","Copyright retained by author(s)"]},{"key":"dc:rights.uri","label":"Rights URI","values":["https://rightsstatements.org/page/InC-EDU/1.0/"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://hdl.handle.net/1721.1/152774"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Social media platforms are two-sided markets bridging content creators and users. Existing literature on content recommendation algorithms used by platforms often focuses on user preferences and decisions, and does not jointly address creator incentives. We propose a model of content recommendation that explicitly focuses on dynamic user-content matching, with the novel contribution that both users and creators may leave the platform if they feel dissatisfied. In our model, each player decides to stay or leave at each time step based on utilities derived from the current match: users based on their similarities with the recommended content, and creators based on their audience size. We show that a user-centric greedy algorithm that only maximizes immediate engagement can result in poor total engagement in the long run, even if users and creators are randomly generated from prior distributions, but explicitly maximizing long-term engagement is NP-hard. Finally, we present new practical algorithms with provable guarantees and good empirical performance."]},{"key":"dc:description.degree","label":"Dc Description Degree","values":["S.M."]},{"key":"dc:title","label":"Title","values":["Dynamic Matching of Users and Creators on Social Media Platforms"]}]}],"canonical_facts":{"dc:contributor.advisor":["Ozdaglar, Asuman","Huttenlocher, Daniel"],"dc:contributor.department":["Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science"],"dc:creator":["Lyu, Liang"],"dc:date.accessioned":["2023-11-02T20:15:17Z"],"dc:date.available":["2023-11-02T20:15:17Z"],"dc:date.issued":["2023-09"],"dc:description.abstract":["Social media platforms are two-sided markets bridging content creators and users. Existing literature on content recommendation algorithms used by platforms often focuses on user preferences and decisions, and does not jointly address creator incentives. We propose a model of content recommendation that explicitly focuses on dynamic user-content matching, with the novel contribution that both users and creators may leave the platform if they feel dissatisfied. In our model, each player decides to stay or leave at each time step based on utilities derived from the current match: users based on their similarities with the recommended content, and creators based on their audience size. We show that a user-centric greedy algorithm that only maximizes immediate engagement can result in poor total engagement in the long run, even if users and creators are randomly generated from prior distributions, but explicitly maximizing long-term engagement is NP-hard. Finally, we present new practical algorithms with provable guarantees and good empirical performance."],"dc:description.degree":["S.M."],"dc:identifier.uri":["https://hdl.handle.net/1721.1/152774"],"dc:publisher":["Massachusetts Institute of Technology"],"dc:rights":["In Copyright - Educational Use Permitted","Copyright retained by author(s)"],"dc:rights.uri":["https://rightsstatements.org/page/InC-EDU/1.0/"],"dc:title":["Dynamic Matching of Users and Creators on Social Media Platforms"],"dc:type":["Thesis"],"thesis:degree_name":["Master","Master of Science in Electrical Engineering and Computer Science"]},"updated_at":"2026-07-22T22:21:26Z"}