{"id":{"repo_id":"bu","oai_identifier":"oai:open.bu.edu:2144/49336"},"canonical_url":"https://search.ndltd.org/etd/bu/oai:open.bu.edu:2144/49336","repository":{"repo_id":"bu","name":"Boston University","base_url":"https://open.bu.edu/oai/request"},"display":{"title":"Leveraging keyword identification for abusive language detection in social online domains","abstract":"Abusive Language Detection is an important NLP task that can lead to improved content moderation and is particularly crucial for a safer online experience for all. Most online spaces, such as social media or video games, employ some form of content moderation and allow users to report instances of abusive language but fall short when it comes to real-time detection and intervention. Our work focuses on abusive language detection in social online domains. We begin by exploring the use of pre-trained transformer models for this task and provide a set of baseline results. We introduce an offline filtering step that identifies and removes non-keywords using pointwise mutual information to address linguistic challenges such as domain-specific language and misspelled words. This process emphasizes the remaining words and builds a stronger association between word-category pairs. We also explore an online filtering framework that aims to replicate and remove the offline filtering step by utilizing transformer-produced context-aware embeddings to score words. Identifying and removing non-keywords can significantly improve performance for this task but relies on knowledge of word-category co-occurrences.","abstract_html":"Abusive Language Detection is an important NLP task that can lead to improved content moderation and is particularly crucial for a safer online experience for all. Most online spaces, such as social media or video games, employ some form of content moderation and allow users to report instances of abusive language but fall short when it comes to real-time detection and intervention. Our work focuses on abusive language detection in social online domains. We begin by exploring the use of pre-trained transformer models for this task and provide a set of baseline results. We introduce an offline filtering step that identifies and removes non-keywords using pointwise mutual information to address linguistic challenges such as domain-specific language and misspelled words. This process emphasizes the remaining words and builds a stronger association between word-category pairs. We also explore an online filtering framework that aims to replicate and remove the offline filtering step by utilizing transformer-produced context-aware embeddings to score words. Identifying and removing non-keywords can significantly improve performance for this task but relies on knowledge of word-category co-occurrences.","abstract_has_math":false,"creators":["Saravanan, Duruvan"],"institution":"Boston University","degree_name":"Master of Science","degree_level":"masters","degree_discipline":"Computer Science","degree_department":null,"school":null,"contributors":[],"advisors":["Plummer, Bryan"],"committee_chairs":[],"committee_members":[],"year":2023,"date_issued":"2023","date_published":"2023","updated_at":"2026-11-18T19:47:49Z","subjects":["Computer science","Abusive language detection","Machine learning","Natural language processing","Social media"],"languages":["en_US"],"rights":["Attribution 4.0 International"],"rights_urls":["http://creativecommons.org/licenses/by/4.0/"],"identifier_entries":[],"person_identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/2144/49336","outbound_label":"Handle","outbound_source":"dc:identifier.uri","record_url":"https://hdl.handle.net/2144/49336","record_label":"Repository record","record_kind":"handle","record_source":"dc:identifier.uri","download_url":null,"download_label":null,"download_source":null,"access_status":null,"embargo_until":null,"access_note":null},"source_record":{"url":"https://open.bu.edu/oai/request?verb=GetRecord&metadataPrefix=dim&identifier=oai%3Aopen.bu.edu%3A2144%2F49336","prefix":"dim"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Plummer, Bryan"]},{"key":"dc:creator","label":"Author","values":["Saravanan, Duruvan"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2024-09-26T14:34:41Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2024-09-26T14:34:41Z"]},{"key":"dc:date.issued","label":"Date","values":["2023"]},{"key":"dc:date.updated","label":"Dc Date Updated","values":["2024-09-25T16:23:28Z"]},{"key":"dc:type","label":"Dc Type","values":["Thesis/Dissertation"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Computer Science"]},{"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":["Boston University"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Computer science","Abusive language detection","Machine learning","Natural language processing","Social media"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language.iso","label":"Language (ISO)","values":["en_US"]},{"key":"dc:rights","label":"Dc Rights","values":["Attribution 4.0 International"]},{"key":"dc:rights.uri","label":"Rights URI","values":["http://creativecommons.org/licenses/by/4.0/"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://hdl.handle.net/2144/49336"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Abusive Language Detection is an important NLP task that can lead to improved content moderation and is particularly crucial for a safer online experience for all. Most online spaces, such as social media or video games, employ some form of content moderation and allow users to report instances of abusive language but fall short when it comes to real-time detection and intervention. Our work focuses on abusive language detection in social online domains. We begin by exploring the use of pre-trained transformer models for this task and provide a set of baseline results. We introduce an offline filtering step that identifies and removes non-keywords using pointwise mutual information to address linguistic challenges such as domain-specific language and misspelled words. This process emphasizes the remaining words and builds a stronger association between word-category pairs. We also explore an online filtering framework that aims to replicate and remove the offline filtering step by utilizing transformer-produced context-aware embeddings to score words. Identifying and removing non-keywords can significantly improve performance for this task but relies on knowledge of word-category co-occurrences."]},{"key":"dc:title","label":"Title","values":["Leveraging keyword identification for abusive language detection in social online domains"]}]}],"canonical_facts":{"dc:contributor.advisor":["Plummer, Bryan"],"dc:creator":["Saravanan, Duruvan"],"dc:date.accessioned":["2024-09-26T14:34:41Z"],"dc:date.available":["2024-09-26T14:34:41Z"],"dc:date.issued":["2023"],"dc:date.updated":["2024-09-25T16:23:28Z"],"dc:description.abstract":["Abusive Language Detection is an important NLP task that can lead to improved content moderation and is particularly crucial for a safer online experience for all. Most online spaces, such as social media or video games, employ some form of content moderation and allow users to report instances of abusive language but fall short when it comes to real-time detection and intervention. Our work focuses on abusive language detection in social online domains. We begin by exploring the use of pre-trained transformer models for this task and provide a set of baseline results. We introduce an offline filtering step that identifies and removes non-keywords using pointwise mutual information to address linguistic challenges such as domain-specific language and misspelled words. This process emphasizes the remaining words and builds a stronger association between word-category pairs. We also explore an online filtering framework that aims to replicate and remove the offline filtering step by utilizing transformer-produced context-aware embeddings to score words. Identifying and removing non-keywords can significantly improve performance for this task but relies on knowledge of word-category co-occurrences."],"dc:identifier.uri":["https://hdl.handle.net/2144/49336"],"dc:language.iso":["en_US"],"dc:rights":["Attribution 4.0 International"],"dc:rights.uri":["http://creativecommons.org/licenses/by/4.0/"],"dc:subject":["Computer science","Abusive language detection","Machine learning","Natural language processing","Social media"],"dc:title":["Leveraging keyword identification for abusive language detection in social online domains"],"dc:type":["Thesis/Dissertation"],"thesis:degree_discipline":["Computer Science"],"thesis:degree_level":["masters"],"thesis:degree_name":["Master of Science"],"thesis:institution_name":["Boston University"]},"updated_at":"2026-11-18T19:47:49Z"}