config/config.yaml

# ═══════════════════════════════════════════════════════════
# Fake News Detection System — Configuration
# ═══════════════════════════════════════════════════════════

paths:
  # Raw dataset root (relative to project root)
  dataset_root: "../Dataset"
  # Processed data output
  processed_dir: "data/processed"
  # Train/val/test splits
  splits_dir: "data/splits"
  # Saved model weights
  models_dir: "models/saved"
  # Logs
  logs_dir: "logs"
  # GloVe embeddings
  glove_path: "../glove.6B.100d.txt"

dataset:
  min_domain_samples: 20
  dedup_threshold: 0.92
  dedup_batch_size: 64

preprocessing:
  max_tfidf_features: 50000
  lstm_max_len: 256
  bert_max_len: 128
  short_text_threshold: 50
  min_word_count: 3

training:
  lstm_batch_size: 64
  lstm_epochs: 10
  bert_batch_size: 8
  bert_epochs: 3
  lr_learning_rate: 2e-5
  roberta_learning_rate: 1e-5

inference:
  true_threshold: 0.55
  fresh_threshold: 0.70
  outdated_threshold: 0.40
  undated_freshness_score: 0.35
  max_multiplier: 10

rag:
  top_k: 5
  max_result_age_days: 90
  support_threshold: 0.65
  conflict_threshold: 0.30

drift:
  word_count_std_alert: 2.0
  fake_ratio_upper: 0.80
  fake_ratio_lower: 0.20
  rolling_window: 100

holdout:
  stratified_test_size: 0.10
  random_state: 42