added two more experiments with features of emotion lexicons

lexicon/emojis.txt

+emoji emotion
+😒 anger
+😠 anger
+😡 anger
+😣 anger
+😤 anger
+😾 anger
+👿 anger
+👊 anger
+🤮 disgust
+😨 fear
+😰 fear
+😱 fear
+😧 fear
+🙀 fear
+🆘 fear
+😁 joy
+😂 joy
+😃 joy
+😄 joy
+😅 joy
+😆 joy
+😉 joy
+😊 joy
+😋 joy
+😌 joy
+😍 joy
+😏 joy
+😘 joy
+😚 joy
+😬 joy
+😜 joy
+😝 joy
+🙃 joy
+😸 joy
+😹 joy
+😺 joy
+😻 joy
+😽 joy
+😎 joy
+🙆 joy
+🙋 joy
+🙌 joy
+❤ joy
+🧡 joy
+💛 joy
+💚 joy
+💙 joy
+💜 joy
+❣ joy
+💕 joy
+💑 joy
+💏 joy
+💋 joy
+♥ joy
+🙎 sad
+😓 sad
+😔 sad
+😖 sad
+😞 sad
+😢 sad
+😥 sad
+😩 sad
+😪 sad
+😫 sad
+😭 sad
+😿 sad
+🙍 sad
+🤒 sad
+💔 sad
+😲 surprise
+😳 surprise
+😵 surprise

results_evaluation

@@ -53,3 +53,33 @@ Macro-Precision: 0.6040684610078678
 Macro-Recall: 0.6040370418815006
 Macro-Recall: 0.6040370418815006
 Macro-F1: 0.6024329096077434
 Macro-F1: 0.6024329096077434
 Accuracy: 0.604003753518924
 Accuracy: 0.604003753518924
+
+Experiment 3: 
+
+
+vocab_embeddings = 500000
+max_lenght_tweet = 30
+
+Layers: 
+
+ e = Embedding(feature_size, EMBEDDING_DIM, input_length=max_len_input, weights=[embedding_matrix], trainable=False)
+model.add(e)
+model.add(LSTM(128, return_sequences=True))
+model.add(Dense(64, activation='relu', kernel_initializer=glorot_uniform(seed=RANDOM_SEED), activity_regularizer=regularizers.l2(0.0001)))
+model.add(Dropout(0.25))
+model.add(Flatten())
+model.add(Dense(32, activation='relu', kernel_initializer=glorot_uniform(seed=RANDOM_SEED), activity_regularizer=regularizers.l2(0.0001)))
+model.add(Dropout(0.5))
+model.add(Dense(len(CLASSES), activation='softmax'))
+
+Accuracy trainning: 84.375061
+
+Results evaluation:
+
+
+*** Results RNN_LSTM ***
+Macro-Precision: 0.552099234158447
+Macro-Recall: 0.5516921635572564
+Macro-F1: 0.550307950647363
+Accuracy: 0.5516630174121573
+