Showcase/Sarcasm Detection
intermediatetext

Sarcasm Detection

Identify sarcastic statements and label their type and target in social media and conversational text.

📝

text annotation

Configuration Fileconfig.yaml

# Sarcasm Detection Configuration
# Identify and categorize sarcastic statements

annotation_task_name: "Sarcasm Detection"

data_files:
  - "data/tweets.json"

item_properties:
  id_key: "id"
  text_display_key: "text"

user_config:
  allow_all_users: true

annotation_schemes:
  - annotation_type: "radio"
    name: "is_sarcastic"
    description: "Is this text sarcastic?"
    labels:
      - name: "Sarcastic"
        tooltip: "The text means the opposite of what it literally says"
        key_value: "s"
      - name: "Not Sarcastic"
        tooltip: "The text is meant literally"
        key_value: "n"
      - name: "Unclear"
        tooltip: "Cannot determine without more context"
        key_value: "u"

  - annotation_type: "radio"
    name: "sarcasm_type"
    description: "What type of sarcasm?"
    labels:
      - name: "Verbal Irony"
        tooltip: "Saying the opposite of what is meant"
      - name: "Self-deprecating"
        tooltip: "Mocking oneself"
      - name: "Situational"
        tooltip: "Pointing out ironic situations"
      - name: "Exaggeration"
        tooltip: "Over-the-top statements"
      - name: "Understatement"
        tooltip: "Downplaying something significant"
    show_if:
      field: "is_sarcastic"
      value: "Sarcastic"

  - annotation_type: "radio"
    name: "sarcasm_target"
    description: "What is the target of the sarcasm?"
    labels:
      - name: "Self"
      - name: "Other person"
      - name: "Organization/Company"
      - name: "Situation/Event"
      - name: "General/Unclear"
    show_if:
      field: "is_sarcastic"
      value: "Sarcastic"

  - annotation_type: "likert"
    name: "confidence"
    description: "How confident are you?"
    size: 5
    min_label: "Not confident"
    max_label: "Very confident"

  - annotation_type: "text"
    name: "literal_interpretation"
    description: "What would this mean if taken literally?"
    required: false

output: "annotation_output/"

Sample Datasample-data.json

[
  {
    "id": "sarc_001",
    "text": "Oh great, another Monday. Just what I needed.",
    "source": "twitter"
  },
  {
    "id": "sarc_002",
    "text": "I love waking up to construction noise at 6am. Really helps me start the day right.",
    "source": "twitter"
  }
]

// ... and 3 more items

Get This Design

View on GitHub

Clone or download from the repository

Quick start:

git clone https://github.com/davidjurgens/potato-showcase.git
cd potato-showcase/sarcasm-detection
potato start config.yaml

Details

Annotation Types

radiotext

Domain

nlpsocial-media

Use Cases

sentiment-analysisirony-detection

Tags

sarcasmironysentimentsocial-medianlp

Found an issue or want to improve this design?

Open an Issue

Related Designs

Fact Verification

Verify claims as supported, refuted, or not enough information based on provided evidence.

radiotext

Reading Comprehension QA

Evaluate question-answer pairs for reading comprehension by verifying answers and rating quality.

radiospan

Commonsense Inference (ATOMIC 2020)

Annotate commonsense inferences about events, mental states, and social interactions. Based on ATOMIC 2020 (Hwang et al., AAAI 2021). Generate if-then knowledge about causes, effects, intents, and reactions.

radiotext