IIT DHANBAD CODECHAMPS at SemEval-2022 Task 5: MAMI - Multimedia Automatic Misogyny Identification

Proceedings of the 16th International Workshop on Semantic Evaluation (SemEval-2022), pages 733 - 735 July 14-15, 2022 ©2022 Association for Computational Linguistics IIT DHANBAD CODECHAMPS at SemEval-2022 Task 5: MAMI - Multimedia Automatic Misogyny Identification Shubham Kumar Barnwal Department of Computer Science and Engineering , Indian Institute of Technology (Indian School of Mines), Dhanbad, India shubham.developer02@gmail.com Ritesh Kumar Department of Computer Science and Engineering, National Institute of Technology Jamshedpur, India ritesh.cse@nitjsr.ac.in Rajendra Pamula Department of Computer Science and Engineering , Indian Institute of Technology (Indian School of Mines), Dhanbad, India rajendrapamula@gmail.com Abstract With the growth of the internet, the use of so- cial media based on images has drastically in- creased like Twitter, Instagram, etc. In these social media, women have a very high contri- bution as of 75% women use social media mul- tiple times compared to men which is only 65% of men uses social media multiple times a day. However, with this much contribution, it also increases systematic inequality and discrimi- nation offline is replicated in online spaces in the form of MEMEs. A meme is essentially an image characterized by pictorial content with an overlaying text a posteriori introduced by humans, with the main goal of being funny and/or ironic. Although most of them are cre- ated with the intent of making funny jokes, in a short time people started to use them as a form of hate and prejudice against women, landing to sexist and aggressive messages in online environments that subsequently amplify the sexual stereotyping and gender inequality of the offline world. This leads to the need for automatic detection of Misogyny MEMEs. Specifically, I described the model submitted for the shared task on Multimedia Automatic Misogyny Identification (MAMI (Fersini et al., 2022)) and my team name is IIT DHANBAD CODECHAMPS. 1 Introduction With the growth of the internet, social media be- comes a crucial part of everyone’s life. As every coin has two side positive and negative, social me- dia also comes with a number of problems. The challenge of identifying misogyny (Srivastava et al., 2017) in different social media specially in forms of meme which contains both image and text is very complicated. Misogyny meme highly affected the life of women’s as its spread hate and preju- dice behaviour against women’s. Social media like twitter, Instagram, etc have handled by their own ways. However, detecting such memes is highly challenging. Due to this challenge, it attracts the researcher’s attention. According to one social me- dia Instagram, more than 1 million users shared memes daily. So, with this huge amount of data in social medias and internet it is impossible to detect every misogyny meme by man power. So, we need machine learning, deep learning and artifi- cial intelligence techniques to detect automatically misogyny memes in social media. In this paper, we have explored various Machine Learning (ML) and Deep Learning (DL) algorithms for misogyny iden- tification in shared task MAMI (Fersini et al., 2022) challenge and my team’s name is IIT DHANBAD …

Content truncated to 500 words