SubmissionNumber#=%=#20 FinalPaperTitle#=%=#BDA at SemEval-2024 Task 4: Detection of Persuasion in Memes Across Languages with Ensemble Learning and External Knowledge ShortPaperTitle#=%=# NumberOfPages#=%=#10 CopyrightSigned#=%=#Victoria Sherratt JobTitle#==# Organization#==#University of Hull Cottingham Road, Hull, HU6 7RX Abstract#==#This paper outlines our multimodal ensemble learning system for identifying persuasion techniques in memes. We contribute an approach which utilises the novel inclusion of consistent named visual entities extracted using Google Vision's API as an external knowledge source, joined to our multimodal ensemble via late fusion. As well as detailing our experiments in ensemble combinations, fusion methods and data augmentation, we explore the impact of including external data and summarise post-evaluation improvements to our architecture based on analysis of the task results. Author{1}{Firstname}#=%=#Victoria Author{1}{Lastname}#=%=#Sherratt Author{1}{Username}#=%=#vemchance Author{1}{Email}#=%=#v.sherratt-2020@hull.ac.uk Author{1}{Affiliation}#=%=#University of Hull Author{2}{Firstname}#=%=#Sedat Author{2}{Lastname}#=%=#Dogan Author{2}{Username}#=%=#sdogan13 Author{2}{Email}#=%=#s.dogan-2021@hull.ac.uk Author{2}{Affiliation}#=%=#University of Hull Author{3}{Firstname}#=%=#Ifeoluwa Author{3}{Lastname}#=%=#Wuraola Author{3}{Username}#=%=#ifeooluwa Author{3}{Email}#=%=#wuraolaifeoluwa@gmail.com Author{3}{Affiliation}#=%=#University of Hull, England Author{4}{Firstname}#=%=#Lydia Author{4}{Lastname}#=%=#Bryan-Smith Author{4}{Username}#=%=#bryan-smithl Author{4}{Email}#=%=#l.bryan-smith@hull.ac.uk Author{4}{Affiliation}#=%=#University of Hull Author{5}{Firstname}#=%=#Oyinkansola C. Author{5}{Lastname}#=%=#Onwuchekwa Author{5}{Username}#=%=#oyinkanchekwas Author{5}{Email}#=%=#keenahkaychekwas@gmail.com Author{5}{Affiliation}#=%=#University of Hull Author{6}{Firstname}#=%=#Nina Author{6}{Lastname}#=%=#Dethlefs Author{6}{Username}#=%=#nide Author{6}{Email}#=%=#n.s.dethlefs@gmail.com Author{6}{Affiliation}#=%=#University of Hull ========== èéáğö