{"id":{"repo_id":"uoit","oai_identifier":"oai:ontariotechu.scholaris.ca:10155/1923"},"canonical_url":"https://search.dev.ndltd.org/etd/uoit/oai:ontariotechu.scholaris.ca:10155/1923","repository":{"repo_id":"uoit","name":"Ontario Institute of Technology","base_url":"https://ontariotechu.scholaris.ca/server/oai/request"},"display":{"title":"Topic modeling in game reviews","abstract":"Game reviews heavily influence public perception. User feedback is crucial for developers, offering valuable insights to enhance game quality. In this thesis, Metacritic game reviews for Elden Ring were analyzed for topic modelling using Latent Dirichlet Allocation (LDA), Bidirectional Encoder Representations from Transformers (BERT), and a hybrid model combining both to identify effective methods for extracting underlying themes in player feedback. We analyzed and interpreted these models’ outputs to learn the game reviews. We aimed to identify the differences, similarities, and variations between the three to determine which provided more valuable and instructive information. Our findings indicate that each method successfully identified keywords with some similarities in identified words. The LDA model had the highest silhouette score, indicating the most distinct clustering. The LDA-BERT model had a 1% higher coherence score than LDA, indicating more meaningful or relevant topics.","abstract_html":"Game reviews heavily influence public perception. User feedback is crucial for developers, offering valuable insights to enhance game quality. In this thesis, Metacritic game reviews for Elden Ring were analyzed for topic modelling using Latent Dirichlet Allocation (LDA), Bidirectional Encoder Representations from Transformers (BERT), and a hybrid model combining both to identify effective methods for extracting underlying themes in player feedback. We analyzed and interpreted these models’ outputs to learn the game reviews. We aimed to identify the differences, similarities, and variations between the three to determine which provided more valuable and instructive information. Our findings indicate that each method successfully identified keywords with some similarities in identified words. The LDA model had the highest silhouette score, indicating the most distinct clustering. The LDA-BERT model had a 1% higher coherence score than LDA, indicating more meaningful or relevant topics.","abstract_has_math":false,"creators":["Dehghani, Fatemeh"],"institution":"University of Ontario Institute of Technology","degree_name":"Master of Science (MSc)","degree_level":null,"degree_discipline":"Computer Science","degree_department":null,"school":null,"contributors":[],"advisors":["Zaman, Loutfouz"],"committee_chairs":[],"committee_members":[],"year":2024,"date_issued":"2024-04-01","date_published":"2024-04-01","updated_at":"2026-07-24T05:35:43Z","subjects":[],"languages":["en"],"rights":[],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/10155/1923","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Zaman, Loutfouz"]},{"key":"dc:creator","label":"Author","values":["Dehghani, Fatemeh"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2025-04-29T13:56:44Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2025-04-29T13:56:44Z"]},{"key":"dc:date.issued","label":"Date","values":["2024-04-01"]},{"key":"dc:type","label":"Dc Type","values":["Thesis"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Computer Science"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Master of Science (MSc)"]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["University of Ontario Institute of Technology"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language.iso","label":"Language (ISO)","values":["en"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://hdl.handle.net/10155/1923"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Game reviews heavily influence public perception. User feedback is crucial for developers, offering valuable insights to enhance game quality. In this thesis, Metacritic game reviews for Elden Ring were analyzed for topic modelling using Latent Dirichlet Allocation (LDA), Bidirectional Encoder Representations from Transformers (BERT), and a hybrid model combining both to identify effective methods for extracting underlying themes in player feedback. We analyzed and interpreted these models’ outputs to learn the game reviews. We aimed to identify the differences, similarities, and variations between the three to determine which provided more valuable and instructive information. Our findings indicate that each method successfully identified keywords with some similarities in identified words. The LDA model had the highest silhouette score, indicating the most distinct clustering. The LDA-BERT model had a 1% higher coherence score than LDA, indicating more meaningful or relevant topics."]},{"key":"dc:title","label":"Title","values":["Topic modeling in game reviews"]}]}],"canonical_facts":{"dc:contributor.advisor":["Zaman, Loutfouz"],"dc:creator":["Dehghani, Fatemeh"],"dc:date.accessioned":["2025-04-29T13:56:44Z"],"dc:date.available":["2025-04-29T13:56:44Z"],"dc:date.issued":["2024-04-01"],"dc:description.abstract":["Game reviews heavily influence public perception. User feedback is crucial for developers, offering valuable insights to enhance game quality. In this thesis, Metacritic game reviews for Elden Ring were analyzed for topic modelling using Latent Dirichlet Allocation (LDA), Bidirectional Encoder Representations from Transformers (BERT), and a hybrid model combining both to identify effective methods for extracting underlying themes in player feedback. We analyzed and interpreted these models’ outputs to learn the game reviews. We aimed to identify the differences, similarities, and variations between the three to determine which provided more valuable and instructive information. Our findings indicate that each method successfully identified keywords with some similarities in identified words. The LDA model had the highest silhouette score, indicating the most distinct clustering. The LDA-BERT model had a 1% higher coherence score than LDA, indicating more meaningful or relevant topics."],"dc:identifier.uri":["https://hdl.handle.net/10155/1923"],"dc:language.iso":["en"],"dc:title":["Topic modeling in game reviews"],"dc:type":["Thesis"],"thesis:degree_discipline":["Computer Science"],"thesis:degree_name":["Master of Science (MSc)"],"thesis:institution_name":["University of Ontario Institute of Technology"]},"updated_at":"2026-07-24T05:35:43Z"}