HASOC-meme (2025)

This is the seventh edition of the HASOC shared task. HASOC 2025 will offer memes for abuse, sentiment, sarcasm, vulgarity detection.

Track Description: This task involves analyzing multimodal data (image and text) to detect abuse, identify targeted communities, assess vulgarity and sarcasm, and assign sentiment labels. So, the task will be in five parts.

Sentiment detection:

• Positive - The meme conveys a supportive, humorous, or appreciative tone.

• Neutral - The meme is neither overtly positive nor negative in tone.

• Negative - The meme expresses hostility, mockery, or criticism.

Sarcasm Detection:

• Sarcastic - The meme presents statements or visuals that imply the opposite of their literal meaning, often to mock or ridicule.

• Non-Sarcastic: The meme directly conveys its message without sarcasm or irony.

Vulgarity Detection:

• Vulgar - The meme contains explicit or offensive words, gestures, or depictions.

• Not Vulgar - The meme does not include any such content.

Abuse Detection:

• Abusive - The meme includes offensive, harmful, or derogatory language, imagery, or implications targeting an individual or a group.

• Non-abusive - The meme does not contain any offensive, harmful, or derogatory content.

Target Community Identification:

• Gender - Any reference to male, female, non-binary, or transgender identities.

• Religion - Mentions or imagery related to any religious belief, deity, or practice.

• Individual - Specifically mentions or portrays a particular person.

• Political - Targets political ideologies, parties, politicians, or policies.

• National Origin - Targets people based on their country or ethnicity.

• Social Sub-groups - Groups based on socio-economic status, occupation, cultural identity, or other affiliations.

• Others - Any target that does not fall into the above categories.

• None - If the meme does not target any specific community, no target label is assigned.