| \n", " | Unnamed: 0.1 | \n", "Unnamed: 0 | \n", "Text | \n", "Sentiment | \n", "Timestamp | \n", "User | \n", "Platform | \n", "Hashtags | \n", "Retweets | \n", "Likes | \n", "Country | \n", "Year | \n", "Month | \n", "Day | \n", "Hour | \n", "
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0 | \n", "0 | \n", "0 | \n", "Enjoying a beautiful day at the park! ... | \n", "Positive | \n", "2023-01-15 12:30:00 | \n", "User123 | \n", "#Nature #Park | \n", "15.0 | \n", "30.0 | \n", "USA | \n", "2023 | \n", "1 | \n", "15 | \n", "12 | \n", "|
| 1 | \n", "1 | \n", "1 | \n", "Traffic was terrible this morning. ... | \n", "Negative | \n", "2023-01-15 08:45:00 | \n", "CommuterX | \n", "#Traffic #Morning | \n", "5.0 | \n", "10.0 | \n", "Canada | \n", "2023 | \n", "1 | \n", "15 | \n", "8 | \n", "|
| 2 | \n", "2 | \n", "2 | \n", "Just finished an amazing workout! 💪 ... | \n", "Positive | \n", "2023-01-15 15:45:00 | \n", "FitnessFan | \n", "#Fitness #Workout | \n", "20.0 | \n", "40.0 | \n", "USA | \n", "2023 | \n", "1 | \n", "15 | \n", "15 | \n", "|
| 3 | \n", "3 | \n", "3 | \n", "Excited about the upcoming weekend getaway! ... | \n", "Positive | \n", "2023-01-15 18:20:00 | \n", "AdventureX | \n", "#Travel #Adventure | \n", "8.0 | \n", "15.0 | \n", "UK | \n", "2023 | \n", "1 | \n", "15 | \n", "18 | \n", "|
| 4 | \n", "4 | \n", "4 | \n", "Trying out a new recipe for dinner tonight. ... | \n", "Neutral | \n", "2023-01-15 19:55:00 | \n", "ChefCook | \n", "#Cooking #Food | \n", "12.0 | \n", "25.0 | \n", "Australia | \n", "2023 | \n", "1 | \n", "15 | \n", "19 | \n", "
MultinomialNB()In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook.
MultinomialNB()
LinearSVC(random_state=42)In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook.
LinearSVC(random_state=42)
RandomForestClassifier(n_estimators=200, n_jobs=-1, random_state=42)In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook.
RandomForestClassifier(n_estimators=200, n_jobs=-1, random_state=42)
XGBClassifier(base_score=None, booster=None, callbacks=None,\n",
" colsample_bylevel=None, colsample_bynode=None,\n",
" colsample_bytree=None, device=None, early_stopping_rounds=None,\n",
" enable_categorical=True, eval_metric='mlogloss',\n",
" feature_types=None, feature_weights=None, gamma=None,\n",
" grow_policy=None, importance_type=None,\n",
" interaction_constraints=None, learning_rate=0.1, max_bin=None,\n",
" max_cat_threshold=None, max_cat_to_onehot=None,\n",
" max_delta_step=None, max_depth=6, max_leaves=None,\n",
" min_child_weight=None, missing=nan, monotone_constraints=None,\n",
" multi_strategy=None, n_estimators=200, n_jobs=None, num_class=3, ...)In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. XGBClassifier(base_score=None, booster=None, callbacks=None,\n",
" colsample_bylevel=None, colsample_bynode=None,\n",
" colsample_bytree=None, device=None, early_stopping_rounds=None,\n",
" enable_categorical=True, eval_metric='mlogloss',\n",
" feature_types=None, feature_weights=None, gamma=None,\n",
" grow_policy=None, importance_type=None,\n",
" interaction_constraints=None, learning_rate=0.1, max_bin=None,\n",
" max_cat_threshold=None, max_cat_to_onehot=None,\n",
" max_delta_step=None, max_depth=6, max_leaves=None,\n",
" min_child_weight=None, missing=nan, monotone_constraints=None,\n",
" multi_strategy=None, n_estimators=200, n_jobs=None, num_class=3, ...)Model: \"sequential\"\n",
"\n"
]
},
"metadata": {}
},
{
"output_type": "display_data",
"data": {
"text/plain": [
"┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓\n",
"┃\u001b[1m \u001b[0m\u001b[1mLayer (type) \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1mOutput Shape \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1m Param #\u001b[0m\u001b[1m \u001b[0m┃\n",
"┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩\n",
"│ embedding (\u001b[38;5;33mEmbedding\u001b[0m) │ ? │ \u001b[38;5;34m0\u001b[0m (unbuilt) │\n",
"├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
"│ lstm (\u001b[38;5;33mLSTM\u001b[0m) │ ? │ \u001b[38;5;34m0\u001b[0m (unbuilt) │\n",
"├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
"│ dropout (\u001b[38;5;33mDropout\u001b[0m) │ ? │ \u001b[38;5;34m0\u001b[0m │\n",
"├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
"│ dense (\u001b[38;5;33mDense\u001b[0m) │ ? │ \u001b[38;5;34m0\u001b[0m (unbuilt) │\n",
"├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
"│ dropout_1 (\u001b[38;5;33mDropout\u001b[0m) │ ? │ \u001b[38;5;34m0\u001b[0m │\n",
"├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
"│ dense_1 (\u001b[38;5;33mDense\u001b[0m) │ ? │ \u001b[38;5;34m0\u001b[0m (unbuilt) │\n",
"└─────────────────────────────────┴────────────────────────┴───────────────┘\n"
],
"text/html": [
"┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓\n",
"┃ Layer (type) ┃ Output Shape ┃ Param # ┃\n",
"┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩\n",
"│ embedding (Embedding) │ ? │ 0 (unbuilt) │\n",
"├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
"│ lstm (LSTM) │ ? │ 0 (unbuilt) │\n",
"├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
"│ dropout (Dropout) │ ? │ 0 │\n",
"├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
"│ dense (Dense) │ ? │ 0 (unbuilt) │\n",
"├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
"│ dropout_1 (Dropout) │ ? │ 0 │\n",
"├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
"│ dense_1 (Dense) │ ? │ 0 (unbuilt) │\n",
"└─────────────────────────────────┴────────────────────────┴───────────────┘\n",
"\n"
]
},
"metadata": {}
},
{
"output_type": "display_data",
"data": {
"text/plain": [
"\u001b[1m Total params: \u001b[0m\u001b[38;5;34m0\u001b[0m (0.00 B)\n"
],
"text/html": [
"Total params: 0 (0.00 B)\n", "\n" ] }, "metadata": {} }, { "output_type": "display_data", "data": { "text/plain": [ "\u001b[1m Trainable params: \u001b[0m\u001b[38;5;34m0\u001b[0m (0.00 B)\n" ], "text/html": [ "
Trainable params: 0 (0.00 B)\n", "\n" ] }, "metadata": {} }, { "output_type": "display_data", "data": { "text/plain": [ "\u001b[1m Non-trainable params: \u001b[0m\u001b[38;5;34m0\u001b[0m (0.00 B)\n" ], "text/html": [ "
Non-trainable params: 0 (0.00 B)\n", "\n" ] }, "metadata": {} } ] }, { "cell_type": "code", "source": [ "history = lstm_model.fit(\n", "\n", " X_train_pad,\n", "\n", " y_train_pad,\n", "\n", " validation_split=0.2,\n", "\n", " epochs=15,\n", "\n", " batch_size=32,\n", "\n", " verbose=1\n", "\n", ")" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "w-CZVBUX0Z7_", "outputId": "296a9b8b-ce30-42f4-f9e8-008443a7a5de" }, "execution_count": 68, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "Epoch 1/15\n", "\u001b[1m15/15\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m6s\u001b[0m 37ms/step - accuracy: 0.6026 - loss: 0.9903 - val_accuracy: 0.5897 - val_loss: 0.9284\n", "Epoch 2/15\n", "\u001b[1m15/15\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 16ms/step - accuracy: 0.6453 - loss: 0.8922 - val_accuracy: 0.5897 - val_loss: 0.9147\n", "Epoch 3/15\n", "\u001b[1m15/15\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 16ms/step - accuracy: 0.6368 - loss: 0.8993 - val_accuracy: 0.5897 - val_loss: 0.9187\n", "Epoch 4/15\n", "\u001b[1m15/15\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 15ms/step - accuracy: 0.6496 - loss: 0.9034 - val_accuracy: 0.5897 - val_loss: 0.9232\n", "Epoch 5/15\n", "\u001b[1m15/15\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 16ms/step - accuracy: 0.6474 - loss: 0.8981 - val_accuracy: 0.5897 - val_loss: 0.9059\n", "Epoch 6/15\n", "\u001b[1m15/15\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 15ms/step - accuracy: 0.6453 - loss: 0.9125 - val_accuracy: 0.5897 - val_loss: 0.9167\n", "Epoch 7/15\n", "\u001b[1m15/15\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 15ms/step - accuracy: 0.6474 - loss: 0.8988 - val_accuracy: 0.5897 - val_loss: 0.9148\n", "Epoch 8/15\n", "\u001b[1m15/15\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 15ms/step - accuracy: 0.6474 - loss: 0.8974 - val_accuracy: 0.5897 - val_loss: 0.9083\n", "Epoch 9/15\n", "\u001b[1m15/15\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 15ms/step - accuracy: 0.6474 - loss: 0.8902 - val_accuracy: 0.5897 - val_loss: 0.9051\n", "Epoch 10/15\n", "\u001b[1m15/15\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 15ms/step - accuracy: 0.6496 - loss: 0.9081 - val_accuracy: 0.5897 - val_loss: 0.9122\n", "Epoch 11/15\n", "\u001b[1m15/15\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 15ms/step - accuracy: 0.6474 - loss: 0.8931 - val_accuracy: 0.5897 - val_loss: 0.9205\n", "Epoch 12/15\n", "\u001b[1m15/15\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 15ms/step - accuracy: 0.6474 - loss: 0.9072 - val_accuracy: 0.5897 - val_loss: 0.9120\n", "Epoch 13/15\n", "\u001b[1m15/15\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 15ms/step - accuracy: 0.6474 - loss: 0.9114 - val_accuracy: 0.5897 - val_loss: 0.9107\n", "Epoch 14/15\n", "\u001b[1m15/15\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 15ms/step - accuracy: 0.6474 - loss: 0.9077 - val_accuracy: 0.5897 - val_loss: 0.9051\n", "Epoch 15/15\n", "\u001b[1m15/15\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 15ms/step - accuracy: 0.6474 - loss: 0.9072 - val_accuracy: 0.5897 - val_loss: 0.9137\n" ] } ] }, { "cell_type": "code", "source": [ "y_prob_lstm = lstm_model.predict(X_test_pad)\n", "\n", "y_pred_lstm = np.argmax(\n", " y_prob_lstm,\n", " axis=1\n", ")" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "IeRIegf40Z5J", "outputId": "8c8500ff-2729-4011-cebe-b13ddc0a5840" }, "execution_count": 69, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "\u001b[1m5/5\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 38ms/step\n" ] } ] }, { "cell_type": "code", "source": [ "accuracy_lstm = accuracy_score(\n", " y_test_pad,\n", " y_pred_lstm\n", ")\n", "\n", "precision_lstm = precision_score(\n", " y_test_pad,\n", " y_pred_lstm,\n", " average=\"weighted\"\n", ")\n", "\n", "recall_lstm = recall_score(\n", " y_test_pad,\n", " y_pred_lstm,\n", " average=\"weighted\"\n", ")\n", "\n", "f1_lstm = f1_score(\n", " y_test_pad,\n", " y_pred_lstm,\n", " average=\"weighted\"\n", ")\n", "\n", "print(\"\\n========== LSTM RESULTS ==========\\n\")\n", "\n", "print(f\"Accuracy : {accuracy_lstm:.4f}\")\n", "print(f\"Precision : {precision_lstm:.4f}\")\n", "print(f\"Recall : {recall_lstm:.4f}\")\n", "print(f\"F1 Score : {f1_lstm:.4f}\")" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "gguttfPX2nh-", "outputId": "c638b98f-6295-4b04-f19f-a94c5940bf05" }, "execution_count": 70, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "\n", "========== LSTM RESULTS ==========\n", "\n", "Accuracy : 0.6395\n", "Precision : 0.4089\n", "Recall : 0.6395\n", "F1 Score : 0.4988\n" ] } ] }, { "cell_type": "code", "source": [ "print(\"\\nClassification Report\\n\")\n", "\n", "print(\n", " classification_report(\n", " y_test_pad,\n", " y_pred_lstm,\n", " target_names=label_encoder.classes_\n", " )\n", ")" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "7PaVTXQa2pLV", "outputId": "0c5d7150-290b-4c1a-fc50-d0e88af86d52" }, "execution_count": 71, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "\n", "Classification Report\n", "\n", " precision recall f1-score support\n", "\n", " Negative 0.00 0.00 0.00 37\n", " Neutral 0.00 0.00 0.00 16\n", " Positive 0.64 1.00 0.78 94\n", "\n", " accuracy 0.64 147\n", " macro avg 0.21 0.33 0.26 147\n", "weighted avg 0.41 0.64 0.50 147\n", "\n" ] } ] }, { "cell_type": "code", "source": [ "cm = confusion_matrix(\n", " y_test_pad,\n", " y_pred_lstm\n", ")\n", "\n", "disp = ConfusionMatrixDisplay(\n", " confusion_matrix=cm,\n", " display_labels=label_encoder.classes_\n", ")\n", "\n", "fig, ax = plt.subplots(figsize=(6,6))\n", "\n", "disp.plot(\n", " cmap=\"Reds\",\n", " ax=ax,\n", " colorbar=False\n", ")\n", "\n", "plt.title(\"LSTM Confusion Matrix\")\n", "\n", "plt.show()" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 564 }, "id": "UuBNzYT82q6V", "outputId": "fe82c215-62a2-4213-cc04-705f192a5b74" }, "execution_count": 72, "outputs": [ { "output_type": "display_data", "data": { "text/plain": [ "
| \n", " | text | \n", "label | \n", "
|---|---|---|
| 0 | \n", "enjoying beautiful day park | \n", "2 | \n", "
| 1 | \n", "traffic terrible morning | \n", "0 | \n", "
| 2 | \n", "finished amazing workout 💪 | \n", "2 | \n", "
| 3 | \n", "excited upcoming weekend getaway | \n", "2 | \n", "
| 4 | \n", "trying new recipe dinner tonight | \n", "1 | \n", "
| \n", " | Model | \n", "Accuracy | \n", "Precision | \n", "Recall | \n", "F1-Score | \n", "ROC-AUC | \n", "
|---|---|---|---|---|---|---|
| 0 | \n", "BERT | \n", "0.8095 | \n", "0.7224 | \n", "0.8095 | \n", "0.7626 | \n", "0.9065 | \n", "
| 1 | \n", "SVM | \n", "0.7551 | \n", "0.7398 | \n", "0.7551 | \n", "0.7125 | \n", "NaN | \n", "
| 2 | \n", "XGBoost | \n", "0.7211 | \n", "0.6769 | \n", "0.7211 | \n", "0.6673 | \n", "0.8296 | \n", "
| 3 | \n", "Random Forest | \n", "0.6939 | \n", "0.6646 | \n", "0.6939 | \n", "0.6187 | \n", "0.8279 | \n", "
| 4 | \n", "Naïve Bayes | \n", "0.6599 | \n", "0.6202 | \n", "0.6599 | \n", "0.5519 | \n", "0.8891 | \n", "
| 5 | \n", "LSTM | \n", "0.6395 | \n", "0.4089 | \n", "0.6395 | \n", "0.4988 | \n", "0.5035 | \n", "