def analyze_sentiment_sentiwordnet_lexicon(review, verbose=False):
# tokenize and POS tag text tokens
tagged_text = [(token.text, token.tag_) for token in tn.nlp(review)]
pos_score = neg_score = token_count = obj_score = 0
# get wordnet synsets based on POS tags
# get sentiment scores if synsets are found
for word, tag in tagged_text:
ss_set = None
if 'NN' in tag and list(swn.senti_synsets(word, 'n')):
ss_set = list(swn.senti_synsets(word, 'n'))[0]
elif 'VB' in tag and list(swn.senti_synsets(word, 'v')):
ss_set = list(swn.senti_synsets(word, 'v'))[0]
elif 'JJ' in tag and list(swn.senti_synsets(word, 'a')):
ss_set = list(swn.senti_synsets(word, 'a'))[0]
elif 'RB' in tag and list(swn.senti_synsets(word, 'r')):
ss_set = list(swn.senti_synsets(word, 'r'))[0]
# if senti-synset is found
if ss_set:
# add scores for all found synsets
pos_score += ss_set.pos_score()
neg_score += ss_set.neg_score()
obj_score += ss_set.obj_score()
token_count += 1
# aggregate final scores
final_score = pos_score - neg_score
norm_final_score = round(float(final_score) / token_count, 2)
final_sentiment = 'positive' if norm_final_score >= 0 else 'negative'
return final_sentiment
def analyze_sentiment_sentiwordnet_lexicon(review, verbose=False):
# tokenize and POS tag text tokens
tagged_text = [(token.text, token.tag_) for token in tn.nlp(review)]
pos_score = neg_score = token_count = obj_score = 0
# get wordnet synsets based on POS tags
# get sentiment scores if synsets are found
for word, tag in tagged_text:
ss_set = None
if 'NN' in tag and list(swn.senti_synsets(word, 'n')):
ss_set = list(swn.senti_synsets(word, 'n'))[0]
elif 'VB' in tag and list(swn.senti_synsets(word, 'v')):
ss_set = list(swn.senti_synsets(word, 'v'))[0]
elif 'JJ' in tag and list(swn.senti_synsets(word, 'a')):
ss_set = list(swn.senti_synsets(word, 'a'))[0]
elif 'RB' in tag and list(swn.senti_synsets(word, 'r')):
ss_set = list(swn.senti_synsets(word, 'r'))[0]
# if senti-synset is found
if ss_set:
# add scores for all found synsets
pos_score += ss_set.pos_score()
neg_score += ss_set.neg_score()
obj_score += ss_set.obj_score()
token_count += 1
# aggregate final scores
final_score = pos_score - neg_score
if token_count == 0:
token_count = 1
norm_final_score = round(float(final_score) / token_count, 2)
final_sentiment = 'positive' if norm_final_score >= 0 else 'negative'
result = [norm_final_score, final_sentiment]
if verbose:
norm_obj_score = round(float(obj_score) / token_count, 2)
norm_pos_score = round(float(pos_score) / token_count, 2)
norm_neg_score = round(float(neg_score) / token_count, 2)
# to display results in a nice table
sentiment_frame = pd.DataFrame(
[[
final_sentiment, norm_obj_score, norm_pos_score,
norm_neg_score, norm_final_score
]],
columns=pd.MultiIndex(levels=[['SENTIMENT STATS:'],
[
'Predicted Sentiment',
'Objectivity', 'Positive',
'Negative', 'Overall'
]],
labels=[[0, 0, 0, 0, 0], [0, 1, 2, 3, 4]]))
print(sentiment_frame)
return result
def analyze_sentiment_sentiwordnet_lexicon(review,
verbose=False):
# tokenize and POS tag text tokens
tagged_text = [(token.text, token.tag_) for token in tn.nlp(review)]
pos_score = neg_score = token_count = obj_score = 0
# get wordnet synsets based on POS tags
# get sentiment scores if synsets are found
for word, tag in tagged_text:
ss_set = None
if 'NN' in tag and list(swn.senti_synsets(word, 'n')):
ss_set = list(swn.senti_synsets(word, 'n'))[0]
elif 'VB' in tag and list(swn.senti_synsets(word, 'v')):
ss_set = list(swn.senti_synsets(word, 'v'))[0]
elif 'JJ' in tag and list(swn.senti_synsets(word, 'a')):
ss_set = list(swn.senti_synsets(word, 'a'))[0]
elif 'RB' in tag and list(swn.senti_synsets(word, 'r')):
ss_set = list(swn.senti_synsets(word, 'r'))[0]
# if senti-synset is found
if ss_set:
# add scores for all found synsets
pos_score += ss_set.pos_score()
neg_score += ss_set.neg_score()
obj_score += ss_set.obj_score()
token_count += 1
# aggregate final scores
final_score = pos_score - neg_score
norm_final_score = round(float(final_score) / token_count, 2)
final_sentiment = 'positive' if norm_final_score >= 0 else 'negative'
if verbose:
norm_obj_score = round(float(obj_score) / token_count, 2)
norm_pos_score = round(float(pos_score) / token_count, 2)
norm_neg_score = round(float(neg_score) / token_count, 2)
# to display results in a nice table
sentiment_frame = pd.DataFrame([[final_sentiment, norm_obj_score, norm_pos_score,
norm_neg_score, norm_final_score]],
columns=pd.MultiIndex(levels=[['SENTIMENT STATS:'],
['Predicted Sentiment', 'Objectivity',
'Positive', 'Negative', 'Overall']],
labels=[[0,0,0,0,0],[0,1,2,3,4]]))
print(sentiment_frame)
return final_sentiment
def analyze_setiment_sentiwordnet_lexicon(review, verbose=False):
tagged_text = [(token.text, token.tag_) for token in tn.nlp(review)]
pos_score = neg_score = token_count = obj_score = 0
for word, tag in tagged_text:
ss_set = None
if 'NN' in tag and list(swn.senti_synsets(word, 'n')):
ss_set = list(swn.senti_synsets(word, 'n'))[0]
elif 'VB' in tag and list(swn.senti_synsets(word, 'v')):
ss_set = list(swn.senti_synsets(word, 'v'))[0]
elif 'JJ' in tag and list(swn.senti_synsets(word, 'a')):
ss_set = list(swn.senti_synsets(word, 'a'))[0]
elif 'RB' in tag and list(swn.senti_synsets(word, 'r')):
ss_set = list(swn.senti_synsets(word, 'r'))[0]
if ss_set:
pos_score += ss_set.pos_score()
neg_score += ss_set.neg_score()
obj_score += ss_set.obj_score()
token_count += 1
final_score = pos_score - neg_score
norm_final_score = round(float(final_score) / token_count, 2)
final_sentiment = 'positive' if norm_final_score >= 0 else 'negative'
if verbose:
norm_obj_score = round(float(obj_score) / token_count, 2)
norm_pos_score = round(float(pos_score) / token_count, 2)
norm_neg_score = round(float(neg_score) / token_count, 2)
sentiment_frame = pd.DataFrame(
[[
final_sentiment, norm_obj_score, norm_pos_score,
norm_neg_score, norm_final_score
]],
columns=pd.MultiIndex(levels=[['SENTIMENT STATS:'],
[
'Predicted Sentiment',
'Objectivity', 'Positive',
'Negative', 'Overall'
]],
labels=[[0, 0, 0, 0, 0], [0, 1, 2, 3, 4]]))
print(sentiment_frame)
return final_sentiment
# In[16]:
# generate averaged word vector features from word2vec model
avg_wv_train_features = averaged_word2vec_vectorizer(corpus=tokenized_train,
model=w2v_model,
num_features=500)
avg_wv_test_features = averaged_word2vec_vectorizer(corpus=tokenized_test,
model=w2v_model,
num_features=500)
# In[17]:
# feature engineering with GloVe model
train_nlp = [tn.nlp(item) for item in norm_train_reviews]
train_glove_features = np.array([item.vector for item in train_nlp])
test_nlp = [tn.nlp(item) for item in norm_test_reviews]
test_glove_features = np.array([item.vector for item in test_nlp])
# In[18]:
print('Word2Vec model:> Train features shape:', avg_wv_train_features.shape,
' Test features shape:', avg_wv_test_features.shape)
print('GloVe model:> Train features shape:', train_glove_features.shape,
' Test features shape:', test_glove_features.shape)
# ## Modeling with deep neural networks
# ### Building Deep neural network architecture
return np.array(features)
# In[16]:
# generate averaged word vector features from word2vec model
avg_wv_train_features = averaged_word2vec_vectorizer(corpus=tokenized_train, model=w2v_model,
num_features=500)
avg_wv_test_features = averaged_word2vec_vectorizer(corpus=tokenized_test, model=w2v_model,
num_features=500)
# In[17]:
# feature engineering with GloVe model
train_nlp = [tn.nlp(item) for item in norm_train_reviews]
train_glove_features = np.array([item.vector for item in train_nlp])
test_nlp = [tn.nlp(item) for item in norm_test_reviews]
test_glove_features = np.array([item.vector for item in test_nlp])
# In[18]:
print('Word2Vec model:> Train features shape:', avg_wv_train_features.shape, ' Test features shape:', avg_wv_test_features.shape)
print('GloVe model:> Train features shape:', train_glove_features.shape, ' Test features shape:', test_glove_features.shape)
# ## Modeling with deep neural networks
# ### Building Deep neural network architecture