DANKMEMES @ EVALITA 2020: The Memeing of Life: Memes, Multimodality and Politics

DANKMEMES is a shared task proposed for the 2020 EVALITA campaign, focusing on the automatic classification of Internet memes. Providing a corpus of 2.361 memes on the 2019 Italian Government Crisis, DANKMEMES features three tasks: A) Meme Detection, B) Hate Speech Identification, and C) Event Clustering. Overall, 5 groups took part in the first task, 2 in the second and 1 in the third. The best system was proposed by the UniTor group and achieved a F1 score of 0.8501 for task A, 0.8235 for task B and 0.2657 for task C. In this report, we describe how the task was set up, we report the system results and we discuss them.

[1]  Léon Bottou,et al.  Learning Image Embeddings using Convolutional Neural Networks for Improved Multi-Modal Semantics , 2014, EMNLP.

[2]  V AbelL.Peirson,et al.  Dank Learning: Generating Memes Using Deep Neural Networks , 2018, ArXiv.

[3]  R. Lewontin.  ‘The Selfish Gene’ , 1977, Nature.

[4]  Stefano Fiorucci.  SNK @ DANKMEMES: Leveraging Pretrained Embeddings for Multimodal Meme Detection (short paper) , 2020, EVALITA.

[5]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[6]  Colin Lankshear,et al.  Online memes, affinities, and cultural production , 2007 .

[7]  E. S. Smitha,et al.  Meme Classification Using Textual and Visual Features , 2018 .

[8]  De la Rosa-Carrillo,et al.  On the Language of Internet Memes , 2015 .

[9]  Dumitru-Clementin Cercel,et al.  UPB @ DANKMEMES: Italian Memes Analysis - Employing Visual Models and Graph Convolutional Networks for Meme Identification and Hate Speech Detection (short paper) , 2020, EVALITA.

[10]  Mehmet Fatih Çömlekçi.  Custodians of the Internet: Platforms, Content Moderation, and the Hidden Decisions that Shape Social Media , 2019 .

[11]  Emi Tanaka,et al.  Improving MEME via a two-tiered significance analysis , 2014, Bioinform..

[12]  Klaus Krippendorff,et al.  Content Analysis: An Introduction to Its Methodology , 1980 .

[13]  Jean H. French.  Image-based memes as sentiment predictors , 2017, 2017 International Conference on Information Society (i-Society).

[14]  Thomas M. Ballard.  The world made meme: Public conversations and participatory media , 2018, New Media Soc..

[15]  Preslav Nakov,et al.  Predicting the Type and Target of Offensive Posts in Social Media , 2019, NAACL.

[16]  Felice Dell'Orletta,et al.  Overview of the EVALITA 2018 Hate Speech Detection Task , 2018, EVALITA@CLiC-it.

[17]  O. Bennett,et al.  Satirical User-Generated Memes as an Effective Source of Political Criticism, Extending Debate and Enhancing Civic Engagement , 2014 .

[18]  Danilo Croce,et al.  EVALITA 2020: Overview of the 7th Evaluation Campaign of Natural Language Processing and Speech Tools for Italian , 2020, EVALITA.

[19]  Preslav Nakov,et al.  SemEval-2019 Task 6: Identifying and Categorizing Offensive Language in Social Media (OffensEval) , 2019, *SEMEVAL.

[20]  Roberto Basili,et al.  UNITOR @ DANKMEME: Combining Convolutional Models and Transformer-based architectures for accurate MEME management , 2020, EVALITA.

[21]  Hugo Gonçalo Oliveira,et al.  One does not simply produce funny memes! - Explorations on the Automatic Generation of Internet humor , 2016, ICCC.

[22]  Limor Shifman,et al.  “It Gets Better”: Internet memes and the construction of collective identity , 2016, New Media Soc..

[23]  Xavier Giró-i-Nieto,et al.  Hate Speech in Pixels: Detection of Offensive Memes towards Automatic Moderation , 2019, ArXiv.

[24]  Limor Shifman,et al.  Memes in a Digital World: Reconciling with a Conceptual Troublemaker , 2013, J. Comput. Mediat. Commun..