Food Hazard Detection

# Food Hazard Detection
# Based on Randl et al., SemEval-2025 Task 9: The Food Hazard Detection Challenge
# Paper: https://aclanthology.org/2025.semeval-1.325/
# Dataset: https://food-hazard-detection-semeval-2025.github.io/
#
# This task asks annotators to classify short food-incident report texts.
# Following the two SemEval subtasks, annotators assign the coarse hazard-category
# (1 of 10) and product-category (1 of 22), and highlight the specific hazard and
# product mentions that ground the fine-grained (ST2) labels.

annotation_task_name: "Food Hazard Detection"
task_dir: "."

data_files:
  - sample-data.json

item_properties:
  id_key: "id"
  text_key: "text"

output_annotation_dir: "annotation_output/"
output_annotation_format: "json"

port: 8000
server_name: localhost

annotation_schemes:
  # Subtask 1 (coarse): single hazard-category label (1 of 10)
  - annotation_type: radio
    name: hazard_category
    description: "Which hazard-category does this text imply? (choose one)"
    labels:
      - "allergens"
      - "biological"
      - "chemical"
      - "foreign bodies"
      - "fraud"
      - "organoleptic aspects"
      - "packaging defect"
      - "food additives and flavourings"
      - "migration"
      - "other hazard"
    tooltips:
      "allergens": "Undeclared or mislabelled allergens (e.g., milk, nuts, gluten)"
      "biological": "Microbiological contamination (e.g., Listeria, Salmonella, E. coli)"
      "chemical": "Chemical contamination (e.g., pesticides, heavy metals, toxins, aflatoxins)"
      "foreign bodies": "Physical contaminants such as glass, metal, or plastic fragments"
      "fraud": "Adulteration, mislabelling, or fraudulent substitution"
      "organoleptic aspects": "Abnormal smell, taste, colour, or texture"
      "packaging defect": "Faulty or damaged packaging affecting safety"
      "food additives and flavourings": "Unauthorised or excessive additives/flavourings"
      "migration": "Migration of substances from packaging or contact materials"
      "other hazard": "Any hazard not covered by the categories above"

  # Subtask 1 (coarse): single product-category label (1 of 22)
  - annotation_type: radio
    name: product_category
    description: "Which product-category is affected? (choose one)"
    labels:
      - "meat, egg and dairy products"
      - "cereals and bakery products"
      - "fruits and vegetables"
      - "soups, broths, sauces and condiments"
      - "prepared dishes and snacks"
      - "seafood and fish products"
      - "nuts, nut products and seeds"
      - "confectionery"
      - "fats and oils"
      - "cocoa and cocoa preparations, coffee and tea"
      - "alcoholic beverages"
      - "non-alcoholic beverages"
      - "herbs and spices"
      - "food additives and flavourings"
      - "food contact materials"
      - "dietetic foods, food supplements, fortified foods"
      - "honey and royal jelly"
      - "ices and desserts"
      - "sugars and syrups"
      - "feed materials"
      - "pet feed"
      - "other food product / mixed"

  # Subtask 2 (fine-grained): highlight the specific hazard and product mentions
  - annotation_type: span
    name: hazard_product_spans
    description: "Highlight the specific hazard and product mentioned in the text."
    labels:
      - "Hazard"
      - "Product"

annotation_instructions: |
  You will be shown the title or text of a food-incident report. Your task is to:
  1. Read the report carefully.
  2. Assign the single best hazard-category (Subtask 1).
  3. Assign the single best product-category (Subtask 1).
  4. Highlight the specific hazard and product mentions in the text (Subtask 2).

html_layout: |
  <div style="padding: 15px; max-width: 800px; margin: auto;">
    <div style="background: #fef2f2; border: 1px solid #fecaca; border-radius: 8px; padding: 16px; margin-bottom: 16px;">
      <strong style="color: #991b1b;">Food Safety Incident Report:</strong>
      <p style="font-size: 16px; line-height: 1.7; margin: 8px 0 0 0;">{{text}}</p>
    </div>
  </div>

allow_all_users: true
instances_per_annotator: 50
annotation_per_instance: 2
allow_skip: true
skip_reason_required: false