RuSentiment - Social Media Sentiment

# RuSentiment - Social Media Sentiment Classification
# Based on Rogers et al., COLING 2018
# Paper: https://aclanthology.org/C18-1064/
# Dataset: https://github.com/text-machine-lab/rusentiment
#
# 5-class sentiment scheme designed for social media:
# - Positive: explicit or implicit positive sentiment
# - Negative: explicit or implicit negative sentiment
# - Neutral: no sentiment expressed
# - Speech Act: formulaic posts (greetings, thanks, congratulations)
# - Skip: unclear, noisy, or user-generated content like poems
#
# Guidelines:
# - Mixed sentiment: annotate based on dominant sentiment
# - Hashtags and emojis are NOT automatic sentiment labels
# - Speech Acts may not reflect sender's actual sentiment
# - Annotation speed target: 250-350 posts per hour

annotation_task_name: "RuSentiment: Social Media Sentiment Classification"
task_dir: "."

data_files:
  - sample-data.json
item_properties:
  id_key: "id"
  text_key: "text"

output_annotation_dir: "annotation_output/"
output_annotation_format: "json"

annotation_schemes:
  - annotation_type: radio
    name: sentiment
    description: "Classify the sentiment of this social media post"
    labels:
      - Positive
      - Negative
      - Neutral
      - Speech Act
      - Skip
    keyboard_shortcuts:
      Positive: "1"
      Negative: "2"
      Neutral: "3"
      "Speech Act": "4"
      Skip: "5"
    tooltips:
      Positive: "Post expresses positive emotion or favorable attitude (explicit or implicit)"
      Negative: "Post expresses negative emotion or unfavorable attitude (explicit or implicit)"
      Neutral: "Post contains no sentiment markers; purely informational"
      "Speech Act": "Formulaic posts: greetings, thank-yous, congratulations, wishes (may not reflect true sentiment)"
      Skip: "Unclear posts, excessive noise, user-generated content like poems or lyrics"

  # Optional: For mixed sentiment posts
  - annotation_type: radio
    name: mixed_sentiment
    description: "Does this post contain mixed sentiment?"
    labels:
      - "No - single sentiment"
      - "Yes - but positive dominant"
      - "Yes - but negative dominant"
      - "Yes - balanced/unclear"
    keyboard_shortcuts:
      "No - single sentiment": "n"
      "Yes - but positive dominant": "p"
      "Yes - but negative dominant": "g"
      "Yes - balanced/unclear": "b"
    tooltips:
      "No - single sentiment": "The post expresses only one type of sentiment"
      "Yes - but positive dominant": "Mixed, but overall more positive"
      "Yes - but negative dominant": "Mixed, but overall more negative"
      "Yes - balanced/unclear": "Cannot determine dominant sentiment"

allow_all_users: true
instances_per_annotator: 500
annotation_per_instance: 3
allow_skip: false