{"id":{"repo_id":"carleton","oai_identifier":"oai:carleton.scholaris.ca:20.500.14718/42701"},"canonical_url":"https://search.dev.ndltd.org/etd/carleton/oai:carleton.scholaris.ca:20.500.14718/42701","repository":{"repo_id":"carleton","name":"Carleton University","base_url":"https://carleton.scholaris.ca/server/oai/request"},"display":{"title":"Empirical Study on Improving Hate Speech Detection: Novel BERT based One-Versus-All Classification Approach (BOVAC) with a Novel Performance Metric: Global Performance (GP)","abstract":"Text classification is an application of natural language processing (NLP) which involves the automated processing of text data for the purpose of extracting features, classifying opinions or performing sentiment analysis. Attempting to improve the task of automated detection of hate speech and the understanding of the framework upon which it operates, I present my thesis in which: I explore an approach I call BERT-based one-versus-all text classification (BOVAC) for improving the task of hate speech detection. The performance of the proposed approach is assessed based on an empirical study on a dataset which was previously constructed, cleaned and manually labeled by Davidson and colleagues (Davidson et al., 2017). In addition to presenting an approach to improve hate speech detection, I propose the use of a new performance metric I call global performance (GP) to improve the process of assessing the performance of hate speech detection and text classification models.","abstract_html":"Text classification is an application of natural language processing (NLP) which involves the automated processing of text data for the purpose of extracting features, classifying opinions or performing sentiment analysis. Attempting to improve the task of automated detection of hate speech and the understanding of the framework upon which it operates, I present my thesis in which: I explore an approach I call BERT-based one-versus-all text classification (BOVAC) for improving the task of hate speech detection. The performance of the proposed approach is assessed based on an empirical study on a dataset which was previously constructed, cleaned and manually labeled by Davidson and colleagues (Davidson et al., 2017). In addition to presenting an approach to improve hate speech detection, I propose the use of a new performance metric I call global performance (GP) to improve the process of assessing the performance of hate speech detection and text classification models.","abstract_has_math":false,"creators":["Al Assafin, Samer"],"institution":"Carleton University","degree_name":"Master of Cognitive Science (M.Cog.Sc.)","degree_level":"Master's","degree_discipline":"Cognitive Science","degree_department":null,"school":null,"contributors":[],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2023,"date_issued":"2023","date_published":"2023","updated_at":"2026-07-24T01:34:41Z","subjects":[],"languages":["en"],"rights":["Copyright © 2023 the author(s). Theses may be used for non-commercial research, educational, or related academic purposes only. Such uses include personal study, research, scholarship, and teaching. Theses may only be shared by linking to Carleton University Institutional Repository and no part may be used without proper attribution to the author. No part may be used for commercial purposes directly or indirectly via a for-profit platform; no adaptation or derivative works are permitted without consent from the copyright owner."],"rights_urls":[],"identifier_entries":[{"key":"dc:identifier.doi","label":"DOI","values":["10.22215/etd/2023-15400"],"render_values":[{"text":"10.22215/etd/2023-15400","href":"https://doi.org/10.22215/etd/2023-15400","code":true}]}]},"links":{"outbound_url":"https://hdl.handle.net/20.500.14718/42701","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:creator","label":"Author","values":["Al Assafin, Samer"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2025-04-08T20:42:26Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2025-04-08T20:42:26Z"]},{"key":"dc:date.issued","label":"Date","values":["2023"]},{"key":"dc:publisher","label":"Institution","values":["Carleton University"]},{"key":"dc:type","label":"Dc Type","values":["thesis"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Cognitive Science"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Master's"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Master of Cognitive Science (M.Cog.Sc.)"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language.iso","label":"Language (ISO)","values":["en"]},{"key":"dc:rights","label":"Dc Rights","values":["Copyright © 2023 the author(s). Theses may be used for non-commercial research, educational, or related academic purposes only. Such uses include personal study, research, scholarship, and teaching. Theses may only be shared by linking to Carleton University Institutional Repository and no part may be used without proper attribution to the author. No part may be used for commercial purposes directly or indirectly via a for-profit platform; no adaptation or derivative works are permitted without consent from the copyright owner."]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.doi","label":"DOI","values":["10.22215/etd/2023-15400"]},{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://hdl.handle.net/20.500.14718/42701"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Text classification is an application of natural language processing (NLP) which involves the automated processing of text data for the purpose of extracting features, classifying opinions or performing sentiment analysis. Attempting to improve the task of automated detection of hate speech and the understanding of the framework upon which it operates, I present my thesis in which: I explore an approach I call BERT-based one-versus-all text classification (BOVAC) for improving the task of hate speech detection. The performance of the proposed approach is assessed based on an empirical study on a dataset which was previously constructed, cleaned and manually labeled by Davidson and colleagues (Davidson et al., 2017). In addition to presenting an approach to improve hate speech detection, I propose the use of a new performance metric I call global performance (GP) to improve the process of assessing the performance of hate speech detection and text classification models."]},{"key":"dc:title","label":"Title","values":["Empirical Study on Improving Hate Speech Detection: Novel BERT based One-Versus-All Classification Approach (BOVAC) with a Novel Performance Metric: Global Performance (GP)"]}]}],"canonical_facts":{"dc:creator":["Al Assafin, Samer"],"dc:date.accessioned":["2025-04-08T20:42:26Z"],"dc:date.available":["2025-04-08T20:42:26Z"],"dc:date.issued":["2023"],"dc:description.abstract":["Text classification is an application of natural language processing (NLP) which involves the automated processing of text data for the purpose of extracting features, classifying opinions or performing sentiment analysis. Attempting to improve the task of automated detection of hate speech and the understanding of the framework upon which it operates, I present my thesis in which: I explore an approach I call BERT-based one-versus-all text classification (BOVAC) for improving the task of hate speech detection. The performance of the proposed approach is assessed based on an empirical study on a dataset which was previously constructed, cleaned and manually labeled by Davidson and colleagues (Davidson et al., 2017). In addition to presenting an approach to improve hate speech detection, I propose the use of a new performance metric I call global performance (GP) to improve the process of assessing the performance of hate speech detection and text classification models."],"dc:identifier.doi":["10.22215/etd/2023-15400"],"dc:identifier.uri":["https://hdl.handle.net/20.500.14718/42701"],"dc:language.iso":["en"],"dc:publisher":["Carleton University"],"dc:rights":["Copyright © 2023 the author(s). Theses may be used for non-commercial research, educational, or related academic purposes only. Such uses include personal study, research, scholarship, and teaching. Theses may only be shared by linking to Carleton University Institutional Repository and no part may be used without proper attribution to the author. No part may be used for commercial purposes directly or indirectly via a for-profit platform; no adaptation or derivative works are permitted without consent from the copyright owner."],"dc:title":["Empirical Study on Improving Hate Speech Detection: Novel BERT based One-Versus-All Classification Approach (BOVAC) with a Novel Performance Metric: Global Performance (GP)"],"dc:type":["thesis"],"thesis:degree_discipline":["Cognitive Science"],"thesis:degree_level":["Master's"],"thesis:degree_name":["Master of Cognitive Science (M.Cog.Sc.)"]},"updated_at":"2026-07-24T01:34:41Z"}