{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/bidirectional-recurrent-models-for-offensive","title":"Bidirectional Recurrent Models for Offensive Tweet Classification","arxiv_id":"1903.08808","date":"2019-03-19","proceeding":null,"authors":["Aleix Cambray","Norbert Podsadowski"],"abstract":"In this paper we propose four deep recurrent architectures to tackle the task\nof offensive tweet detection as well as further classification into targeting\nand subject of said targeting. Our architectures are based on LSTMs and GRUs,\nwe present a simple bidirectional LSTM as a baseline system and then further\nincrease the complexity of the models by adding convolutional layers and\nimplementing a split-process-merge architecture with LSTM and GRU as\nprocessors. Multiple pre-processing techniques were also investigated. The\nvalidation F1-score results from each model are presented for the three\nsubtasks as well as the final F1-score performance on the private competition\ntest set. It was found that model complexity did not necessarily yield better\nresults. Our best-performing model was also the simplest, a bidirectional LSTM;\nclosely followed by a two-branch bidirectional LSTM and GRU architecture.","url_abs":"http://arxiv.org/abs/1903.08808v1","url_pdf":"http://arxiv.org/pdf/1903.08808v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"bidirectional-recurrent-models-for-offensive","repo_url":"https://github.com/Nadhila/Explainble-AI","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"bidirectional-recurrent-models-for-offensive","repo_url":"https://github.com/acambray/SemEval2019-OffensiveTweetClassification","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"classification","task_name":"General Classification"}],"methods":[{"method_slug":"gru","method_name":"GRU"},{"method_slug":"lstm","method_name":"LSTM"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"},{"method_slug":"tanh-activation","method_name":"Tanh Activation"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}