mdash

README.md

@@ -131,15 +131,15 @@ print(pipe(cleaned["text"]))
 
 ### Results
 
-- Classical ML models (Random Forest, SVM, Bagging, Boosting, and Decision Trees) were trained on LaBSE-generated sentence embeddings. The best performing classical model---Random Forest---achieved a **macro F1 score of approximately 0.61**, indicating that embeddings alone provide meaningful but limited discrimination for the multilabel classification task.
-- In contrast, the **fine-tuned LaBSE model**, trained end-to-end with a classification head, outperformed all baseline classical models by achieving a **ROC-AUC score of 0.7238** on the validation set and **0.6988** on the test set.
+- Classical ML models (Random Forest, SVM, Bagging, Boosting, and Decision Trees) were trained on LaBSE-generated sentence embeddings. The best performing classical model—Random Forest—achieved a **macro F1 score of approximately 0.61**, indicating that embeddings alone provide meaningful but limited discrimination for the multilabel classification task.
+- In contrast, the **fine-tuned LaBSE model**, trained end-to-end with a classification head, outperformed all baseline classical models by achieving a **ROC-AUC score of 0.7238** on the validation set.
 - These results demonstrate the value of supervised fine-tuning over using frozen embeddings with classical classifiers, particularly in tasks involving subtle multilingual and spatio-temporal signal detection.
 
 ## Model Examination
 
 - Embedding analysis was conducted using a two-stage dimensionality reduction process: Principal Component Analysis (PCA) reduced the 768-dimensional LaBSE sentence embeddings to 50 dimensions, followed by Uniform Manifold Approximation and Projection (UMAP) to reduce to 2 dimensions for visualization.
 - The resulting 2D projections revealed coherent clustering of sentence embeddings by label, particularly in post-violence scenarios and at smaller spatial scales (10 km), indicating that the model effectively captures latent structure related to spatio-temporal patterns of collective violence.
-- Examination of classification performance across labels further confirmed that the model is most reliable when predicting post-violence instances near the epicenter of an event, while its ability to detect pre-violence signals---especially at broader spatial radii (50 km)---is weaker and more prone to noise.
+- Examination of classification performance across labels further confirmed that the model is most reliable when predicting post-violence instances near the epicenter of an event, while its ability to detect pre-violence signals—especially at broader spatial radii (50 km)—is weaker and more prone to noise.
 
 ## Environmental Impact