Update README.md

README.md

@@ -8,7 +8,7 @@ pinned: false
 ---
 
 
-# Climate Disinformation Classification using XGBOOST
+# Climate Disinformation Classification using XGBOOST over TI-IDF vectorized input optimized using RandomizedSearchCV
 
 ## Model Description
 
@@ -16,7 +16,7 @@ This is a model based on XGBOOST classifier for TF-IDF vectorized texts for the
 
 ### Intended Use
 
-- **Primary intended uses**: Baseline comparison for climate disinformation classification models
+- **Primary intended uses**:  Comparison for climate disinformation classification models
 - **Primary intended users**: Researchers and developers participating in the Frugal AI Challenge
 - **Out-of-scope use cases**: Not intended for production use or real-world classification tasks
 
@@ -40,10 +40,10 @@ The model uses the QuotaClimat/frugalaichallenge-text-train dataset:
 ## Performance
 
 ### Metrics
-- **Accuracy**:
+- **Accuracy**: 0.9815384615384616
 - **Environmental Impact**:
-  - Emissions tracked in gCO2eq
-  - Energy consumption tracked in Wh
+  - Emissions tracked in gCO2eq: 0.19426531051455168
+  - Energy consumption tracked in Wh: 0.5262726046395284
 
 ### Model Architecture
 The model implements a random choice between the 8 possible labels, serving as the simplest possible baseline.
@@ -58,10 +58,9 @@ This tracking helps establish a baseline for the environmental impact of model d
 
 ## Limitations
 - Text Classification using XGBOOST 
-- No learning or pattern recognition
-- Input text vectorized/tokenized with TF-IDF
-- XGBOOST parameter search 
-- Serves only as baseline reference
+- Input text vectorized with TF-IDF
+- XGBOOST parameter search with RandomizedSearchCV
+- Serves as baseline reference
 - Not suitable for any real-world applications
 
 ## Ethical Considerations