We are excited to introduce the newest member of our model family: the LS-W4-Mini-RF_Addiction_Impact. This model is our seventh and it was developed to shed light on the complex relationship between social media use and student academic performance. Based on a Random Forest Classifier, this model uses data from the public "Social Media Addiction versus Relationships" dataset from Kaggle, which contains survey responses from students aged 16 to 25. This model serves as a statistical tool that can predict whether social media use has an effect on a student's academic performance. It is packaged within a scikit-learn pipeline, making it easy to integrate into any Python environment. It only requires a pandas DataFrame with the same column structure as the original training data. The training was based on the "Social Media Addiction versus Relationships" dataset, which contains 705 records and 13 features. The model is a scikit-learn RandomForestClassifier and the pipeline includes a ColumnTransformer for one-hot encoding categorical features. The key hyperparameters are n_estimators=100 and random_state=42. The model achieved an accuracy of 0.93 on a held-out test set. It is important for us to emphasize that this model is a statistical tool for trend analysis and it should not be used for clinical or psychological diagnoses. The data is based on self-reported survey responses. The model may not generalize well to other populations or age groups and it reflects biases present in the original dataset. The results should therefore be interpreted with caution.
0 Comments