Abstract
Misogyny is a form of hate against women and has been spreading exponentially through the Web, especially in social media platforms. Hateful contents may be expressed through popular communication tools, like memes. A meme is an image characterised by a pictorial content with an overlaying text introduced a posteriori, and its main aim is originally to be funny and/or ironic. However, the use of memes to convey misogynous messages has increased and thus an automatic detection of these contents seems to be necessary to counteract this phenomenon. This task is particularly challenging, having that (1) different memes can present the same image, but different texts and vice versa, (2) two memes with the same image but different texts can convey a misogynous and not misogynous message, respectively, (3) misogyny can be expressed by image alone, text alone or their combination. In this paper both unimodal and multimodal approaches are investigated whose classifiers are trained and tested on a dataset of in the wild memes, which present both experts and perceived labels. The proposed multimodal approach provides better results compared to the unimodal ones and the VisualBERT state-of-the-art benchmark.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
References
Afridi, T.H., Alam, A., Khan, M.N., Khan, J., Lee, Y.K.: A multimodal memes classification: A survey and open research issues. In: The Proceedings of the Third International Conference on Smart City Applications, pp. 1451–1466. Springer (2020). https://doi.org/10.1007/978-3-030-66840-2_109
Anzovino, M., Fersini, E., Rosso, P.: Automatic identification and classification of misogynistic language on twitter. In: Silberztein, M., Atigui, F., Kornyshova, E., Métais, E., Meziane, F. (eds.) NLDB 2018. LNCS, vol. 10859, pp. 57–64. Springer, Cham (2018). https://doi.org/10.1007/978-3-319-91947-8_6
Bianco, S., Gasparini, F., Schettini, R.: Adaptive skin classification using face and body detection. IEEE Trans. Image Process. 24(12), 4756–4765 (2015)
Cer, D., et al.: Universal sentence encoder for english. In: Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, pp. 169–174 (2018)
Corchs, S., Fersini, E., Gasparini, F.: Ensemble learning on visual and textual data for social image emotion classification. Int. J. Mach. Learn. Cybern. 10(8), 2057–2070 (2017). https://doi.org/10.1007/s13042-017-0734-0
Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)
Fersini, E., Gasparini, F., Corchs, S.: Detecting sexist meme on the web: a study on textual and visual cues. In: 2019 8th International Conference on Affective Computing and Intelligent Interaction Workshops and Demos (ACIIW), pp. 226–231. IEEE (2019)
Fersini, E., Nozza, D., Rosso, P.: Overview of the evalita 2018 task on automatic misogyny identification (ami). EVALITA Eval. NLP Speech Tools Italian 12, 59 (2018)
Fersini, E., Nozza, D., Rosso, P.: Ami@ evalita2020: automatic misogyny identification. In: EVALITA (2020)
Fersini, E., Rosso, P., Anzovino, M.: Overview of the task on automatic misogyny identification at ibereval 2018. IberEval@ SEPLN, vol. 2150, pp. 214–228 (2018)
Ford, T.E., Boxer, C.F., Armstrong, J., Edel, J.R.: More than “just a joke’’: the prejudice-releasing function of sexist humor. Pers. Soc. Psychol. Bull. 34(2), 159–170 (2008)
Franks, M.A.: Unwilling avatars: idealism and discrimination in cyberspace. Colum. J. Gender L. 20, 224 (2011)
Gasparini, F., Erba, I., Fersini, E., Corchs, S.: Multimodal classification of sexist advertisements. In: ICETE (1), pp. 565–572 (2018)
Gasparini, F., Rizzi, G., Saibene, A., Fersini, E.: Benchmark dataset of memes with text transcriptions for automatic detection of multi-modal misogynistic content. arXiv preprint arXiv:2106.08409 (2021)
Khatua, A., Cambria, E., Ghosh, K., Chaki, N., Khatua, A.: Tweeting in support of lgbt? a deep learning approach. In: Proceedings of the ACM India Joint International Conference on Data Science and Management of Data, pp. 342–345 (2019)
Khatua, A., Cambria, E., Khatua, A.: Sounds of silence breakers: exploring sexual violence on twitter. In: 2018 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM), pp. 397–400. IEEE (2018)
Kiela, D., et al.: The hateful memes challenge: detecting hate speech in multimodal memes (2021)
Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)
Lee, J.S., Kuo, Y.M., Chung, P.C., Chen, E.L.: Naked image detection based on adaptive and extensible skin color model. Pattern Recogn. 40(8), 2261–2270 (2007)
Li, L.H., Yatskar, M., Yin, D., Hsieh, C.J., Chang, K.W.: Visualbert: a simple and performant baseline for vision and language. arXiv preprint arXiv:1908.03557 (2019)
Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740–755. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-10602-1_48
Lu, J., Batra, D., Parikh, D., Lee, S.: Vilbert: pretraining task-agnostic visiolinguistic representations for vision-and-language tasks. arXiv preprint arXiv:1908.02265 (2019)
Paciello, M., D’Errico, F., Saleri, G., Lamponi, E.: Online sexist meme and its effects on moral and emotional processes in social media. Comput. Hum. Behav. 116, 106655 (2021)
Parikh, P., Abburi, H., Chhaya, N., Gupta, M., Varma, V.: Categorizing sexism and misogyny through neural approaches. ACM Trans. Web (TWEB) 15(4), 1–31 (2021)
Poria, S., Cambria, E., Bajpai, R., Hussain, A.: A review of affective computing: from unimodal analysis to multimodal fusion. Inf. Fusion 37, 98–125 (2017)
Romero-Sánchez, M., Durán, M., Carretero-Dios, H., Megías, J.L., Moya, M.: Exposure to sexist humor and rape proclivity: the moderator effect of aversiveness ratings. J. Interpersonal Violence 25(12), 2339–2350 (2010)
Ryan, K.M., Kanjorski, J.: The enjoyment of sexist humor, rape attitudes, and relationship aggression in college students. Sex Roles 38(9), 743–756 (1998). https://doi.org/10.1023/A:1018868913615
Safi Samghabadi, N., Patwa, P., PYKL, S., Mukherjee, P., Das, A., Solorio, T.: Aggression and misogyny detection using BERT: a multi-task approach. In: Proceedings of the Second Workshop on Trolling, Aggression and Cyberbullying, pp. 126–131. European Language Resources Association (ELRA), Marseille, France (2020)
Schmidhuber, J., Hochreiter, S., et al.: Long short-term memory. Neural Comput. 9(8), 1735–1780 (1997)
Sharma, P., Ding, N., Goodman, S., Soricut, R.: Conceptual captions: a cleaned, hypernymed, image alt-text dataset for automatic image captioning. In: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 2556–2565 (2018)
Shifman, L.: Memes in a digital world: reconciling with a conceptual troublemaker. J. Comput.-Mediated Commun. 18(3), 362–377 (2013). https://doi.org/10.1111/jcc4.12013
Siddiqi, N., Bains, A., Mushtaq, A., Aleem, S.: Analysing threads of sexism in new age humour: a content analysis of internet memes. Indian J. Soci. Res. 59(3), 355–367 (2018)
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)
Tabone, A., Camilleri, K., Bonnici, A., Cristina, S., Farrugia, R., Borg, M.: Pornographic content classification using deep-learning. In: Proceedings of the 21st ACM Symposium on Document Engineering, pp. 1–10 (2021)
Thomae, M., Viki, G.T.: Why did the woman cross the road? the effect of sexist humor on men’s rape proclivity. J. Soci. Evol. Cult. Psychol. 7(3), 250 (2013)
Zeinert, P., Inie, N., Derczynski, L.: Annotating online misogyny. In: Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pp. 3181–3197. Association for Computational Linguistics (2021). https://doi.org/10.18653/v1/2021.acl-long.247, https://aclanthology.org/2021.acl-long.247
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Fersini, E., Rizzi, G., Saibene, A., Gasparini, F. (2022). Misogynous MEME Recognition: A Preliminary Study. In: Bandini, S., Gasparini, F., Mascardi, V., Palmonari, M., Vizzari, G. (eds) AIxIA 2021 – Advances in Artificial Intelligence. AIxIA 2021. Lecture Notes in Computer Science(), vol 13196. Springer, Cham. https://doi.org/10.1007/978-3-031-08421-8_19
Download citation
DOI: https://doi.org/10.1007/978-3-031-08421-8_19
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-08420-1
Online ISBN: 978-3-031-08421-8
eBook Packages: Computer ScienceComputer Science (R0)