!pip install tensorflow keras numpy pandas scikit-learn gensim requests tqdm nltk
import nltk
nltk.download('stopwords')
from nltk.stem.isri import ISRIStemmer

df = pd.read_csv(csv_path, encoding="utf-8")
df = df.dropna()
# columns: text, Sentiment (1 = positive)

stemmer = ISRIStemmer()
stop_words = set(stopwords.words("arabic"))

def preprocess_arabic_text(text):
    text = text.replace("،", "").replace(".", "").replace("؟", "").replace("!", "")
    words = text.split()
    words = [stemmer.stem(w) for w in words if w not in stop_words]
    return " ".join(words)

tokenizer = Tokenizer(num_words=10000)
tokenizer.fit_on_texts(df["processed_text"])
X_sequences = tokenizer.texts_to_sequences(df["processed_text"])
X_padded = pad_sequences(X_sequences, maxlen=100)

trainable_model = Sequential([
    Embedding(input_dim=10000, output_dim=300, trainable=True),
    LSTM(64, return_sequences=True),
    LSTM(32),
    Dense(1, activation='sigmoid')
])
trainable_model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])

Epoch 5/5 - accuracy: 0.9962 - val_accuracy: 0.8496
Trainable Embedding Model Accuracy: 0.85

word2vec_model = gensim.models.Word2Vec.load(
    './aravec/full_grams_cbow_300_twitter.mdl')

embedding_matrix = np.zeros((len(tokenizer.word_index) + 1, embedding_dim))
for word, i in tokenizer.word_index.items():
    if word in word2vec_model.wv:
        embedding_matrix[i] = word2vec_model.wv[word]
# Embedding matrix shape: (11710, 300)

pretrained_model = Sequential([
    Embedding(input_dim=len(tokenizer.word_index) + 1, output_dim=300,
              weights=[embedding_matrix], trainable=False),
    LSTM(128, return_sequences=True),
    Dropout(0.3),
    LSTM(64),
    Dense(32, activation='relu'),
    Dense(1, activation='sigmoid')
])

Epoch 5/5 - accuracy: 0.9760 - val_accuracy: 0.8555
Pretrained Word2Vec Model Accuracy: 0.86

Trainable Embedding Model Accuracy:   0.85
Pretrained Word2Vec Model Accuracy:   0.86