DIMEMEX-2024

Social networks are increasingly playing crucial roles in people’s lives, transforming the dynamics of communication and information sharing. Analyzing the content originated on these platforms has become a hot research topic for the computational linguistics community. However, despite the notable advances made in recent years, there are still open challenges that merit additional research for better treatment or deeper understanding. One such challenge is the detection of abusive content, which includes aspects like hate speech, aggression, offensive language, and other related phenomena.

Given the multimodal nature of social media platforms, we aim to promote the research and development of multimodal computational models for the detection of abusive content in Mexican Spanish, particularly hate, offensive, and vulgar memes. Memes are defined as the conjunction of a text and an image which often, provide a joint meaning. This meaning is predominantly humorous or ironic, and the absence of either text or image may alter its interpretation. Accordingly, combining information from both modalities to identify a meme as abusive represents an exciting and challenging problem.

DIMEMEX comprises two subtasks:

a) A three-way classification: hate speech, inappropriate content, and neither. 

b) A finer-grained classification distinguishing instances containing hate speech  into different categories such as classism, sexism, racism, and others.