Skip to content
Showcase/Text-Based Emotion Detection
intermediatetext

Text-Based Emotion Detection

Text-based emotion detection task requiring annotators to classify the primary emotion in text and identify expression characteristics such as explicitness, sarcasm, and mixed emotions. Based on SemEval-2025 Task 11.

Select all that apply:

ملف الإعدادconfig.yaml

# Text-Based Emotion Detection
# Based on SemEval 2025 Task 11 Organizers, SemEval 2025
# Paper: https://aclanthology.org/volumes/2025.semeval-1/
# Dataset: https://github.com/SemEval/semeval-2025-task11
#
# This task asks annotators to identify the primary emotion expressed
# in a text and to characterize how the emotion is conveyed (explicitly,
# implicitly, sarcastically, or as a mixture of emotions).

annotation_task_name: "Text-Based Emotion 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:
  - annotation_type: radio
    name: primary_emotion
    description: "What is the primary emotion expressed in this text?"
    labels:
      - "Joy"
      - "Sadness"
      - "Anger"
      - "Fear"
      - "Surprise"
      - "Disgust"
      - "Neutral"
    keyboard_shortcuts:
      "Joy": "1"
      "Sadness": "2"
      "Anger": "3"
      "Fear": "4"
      "Surprise": "5"
      "Disgust": "6"
      "Neutral": "7"
    tooltips:
      "Joy": "Happiness, delight, excitement, or positive emotion"
      "Sadness": "Grief, sorrow, melancholy, or loss"
      "Anger": "Irritation, frustration, rage, or hostility"
      "Fear": "Anxiety, worry, dread, or apprehension"
      "Surprise": "Astonishment, shock, or unexpectedness"
      "Disgust": "Revulsion, contempt, or strong disapproval"
      "Neutral": "No clear emotion or purely informational"

  - annotation_type: multiselect
    name: expression_type
    description: "How is the emotion expressed? Select all that apply."
    labels:
      - "Explicit"
      - "Implicit"
      - "Sarcastic"
      - "Mixed Emotion"
    tooltips:
      "Explicit": "The emotion is directly stated using emotion words"
      "Implicit": "The emotion is conveyed indirectly through context or description"
      "Sarcastic": "The text uses sarcasm or irony to convey emotion"
      "Mixed Emotion": "Multiple emotions are present simultaneously"

annotation_instructions: |
  You will be shown a text passage. Your task is to:
  1. Read the text carefully.
  2. Identify the primary emotion expressed in the text.
  3. Select how the emotion is expressed (explicit, implicit, sarcastic, or mixed).

html_layout: |
  <div style="padding: 15px; max-width: 800px; margin: auto;">
    <div style="background: #f0f9ff; border: 1px solid #bae6fd; border-radius: 8px; padding: 16px; margin-bottom: 16px;">
      <strong style="color: #0369a1;">Text:</strong>
      <p style="font-size: 16px; line-height: 1.7; margin: 8px 0 0 0;">{{text}}</p>
    </div>
    <div style="background: #f0fdf4; border: 1px solid #bbf7d0; border-radius: 8px; padding: 12px;">
      <strong style="color: #166534;">Language:</strong> <span>{{language}}</span>
    </div>
  </div>

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

بيانات نموذجيةsample-data.json

[
  {
    "id": "emo_001",
    "text": "I just got accepted into my dream university! I can't believe it, I've been working towards this for years and it finally happened!",
    "language": "English"
  },
  {
    "id": "emo_002",
    "text": "My grandmother passed away last night. She was the kindest person I ever knew and the house feels so empty without her.",
    "language": "English"
  }
]

// ... and 8 more items

احصل على هذا التصميم

View on GitHub

Clone or download from the repository

بدء سريع:

git clone https://github.com/davidjurgens/potato-showcase.git
cd potato-showcase/semeval/2025/task11-emotion-detection
potato start config.yaml

التفاصيل

أنواع التوسيم

radiomultiselect

المجال

SemEvalNLPEmotion DetectionMultilingual

حالات الاستخدام

Emotion ClassificationSentiment AnalysisAffective Computing

الوسوم

semevalsemeval-2025shared-taskemotiondetectionmultilingual

وجدت مشكلة أو تريد تحسين هذا التصميم؟

افتح مشكلة