Skip to content
intermediatetext

Sarcasm Detection

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

Try it live — no install

Boot the real Potato server in your browser (WebAssembly) and annotate with this exact config. Nothing leaves your machine.

Run live in your browser

Get This Design

View on GitHub(opens in a new tab)

Clone or download from the repository

Quick start:

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

Configuration File

yaml
# Sarcasm Detection Configuration
# Identify and categorize sarcastic statements

task_dir: "."
annotation_task_name: "Sarcasm Detection"

data_files:
  - "data/tweets.json"

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

output_annotation_dir: "annotation_output/"
output_annotation_format: "json"

Sample 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

Details

Annotation Types

likertradiotext

Domain

nlpsocial-media

Use Cases

sentiment-analysisirony-detection

Tags

sarcasmironysentimentsocial-medianlp

Found an issue or want to improve this design?

Open an Issue(opens in a new tab)

Related Designs

Fact Verification

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

likertmultiselect

Intent Classification

Classify user utterances into intents for chatbot and virtual assistant training.

likertmultiselect

Reading Comprehension QA

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

likertradio