SubmissionNumber#=%=#128
FinalPaperTitle#=%=#Snarci at SemEval-2024 Task 4: Themis Model for Binary Classification of Memes
ShortPaperTitle#=%=#
NumberOfPages#=%=#6
CopyrightSigned#=%=#Luca Zedda
JobTitle#==#
Organization#==#Department of Mathematics and Computer Science, University of Cagliari, Via Ospedale 72, Cagliari (Italy)
Abstract#==#This paper introduces an approach developed for multimodal meme analysis, specifically targeting the identification of persuasion techniques embedded within memes. Our methodology integrates Large Language Models (LLMs) and contrastive learning image encoders to discern the presence of persuasive elements in memes across diverse platforms. By capitalizing on the contextual understanding facilitated by LLMs and the discriminative power of contrastive learning for image encoding, our framework provides a robust solution for detecting and classifying memes with persuasion techniques. The system was used in Task 4 of Semeval 2024, precisely for Substask 2b (binary classification of presence of persuasion techniques). It showed promising results overall, achieving a Macro-F1=0.7986 on the English test data (i.e., the language the system was trained on) and Macro-F1=0.66777/0.47917/0.5554, respectively, on the other three "surprise'' languages proposed by the task organizers, i.e., Bulgarian, North Macedonian and Arabic. The paper provides an overview of the system, along with a discussion of the results obtained and its main limitations.
Author{1}{Firstname}#=%=#Luca
Author{1}{Lastname}#=%=#Zedda
Author{1}{Username}#=%=#lucazedda
Author{1}{Email}#=%=#luca.zedda@unica.it
Author{1}{Affiliation}#=%=#University of Cagliari
Author{2}{Firstname}#=%=#Alessandra
Author{2}{Lastname}#=%=#Perniciano
Author{2}{Username}#=%=#alessandraperniciano
Author{2}{Email}#=%=#a.pernician@unica.it
Author{2}{Affiliation}#=%=#University of Cagliari
Author{3}{Firstname}#=%=#Andrea
Author{3}{Lastname}#=%=#Loddo
Author{3}{Username}#=%=#andrealoddo
Author{3}{Email}#=%=#andrea.loddo@unica.it
Author{3}{Affiliation}#=%=#University of Cagliari
Author{4}{Firstname}#=%=#Cecilia
Author{4}{Lastname}#=%=#Di Ruberto
Author{4}{Username}#=%=#ceciliadir
Author{4}{Email}#=%=#dirubert@unica.it
Author{4}{Affiliation}#=%=#University of Cagliari
Author{5}{Firstname}#=%=#Manuela
Author{5}{Lastname}#=%=#Sanguinetti
Author{5}{Username}#=%=#manu_start
Author{5}{Email}#=%=#manu.sanguin@gmail.com
Author{5}{Affiliation}#=%=#University of Cagliari, Department of Mathematics and Computer Science
Author{6}{Firstname}#=%=#Maurizio
Author{6}{Lastname}#=%=#Atzori
Author{6}{Username}#=%=#atzori
Author{6}{Email}#=%=#atzori@unica.it
Author{6}{Affiliation}#=%=#University of Cagliari

==========
èéáğö