Aspect-based sentiment analysis - NLP

Aspect-based sentiment analysis is about identifying different aspects in a given topic. TextBlob will help us to calculate the polarity of the sentiments

	!pip install TextBlob
	import nltk
	nltk.download('brown')
	nltk.download('punkt')
	#Aspect-based sentiment analysis is about identifying different aspects in a given topic. TextBlob will help us to calculate the polarity of the sentiments.
	from textblob import TextBlob
	text = 'The sound quality of this phone is incredible. But the battery life is quite poor.'
	blob = TextBlob(text)
	# Noun phrases in the text
	aspects = blob.noun_phrases
	polarity = []
	for sentence in blob.sentences:
	polarity.append(sentence.sentiment.polarity)
	# Mapped aspects and their sentiment polarity
	aspect_sentiment = dict(zip(aspects, polarity))
	print(aspect_sentiment)
	#A polarity of 0 is considered neutral, above 0 is positive, and below 0 is negative.
	#https://neurosys.com/blog/intro-to-coreference-resolution-in-nlp
	#Co-reference resolution is about detecting all expressions that refer to the same entity in a text.
	#We can use Hugging Face's transformers library. Please note that it requires PyTorch to be installed.
	from transformers import pipeline
	nlp = pipeline('feature-extraction')
	text = 'Jim is a programmer. He loves coding.'
	result = nlp(text)
	print(result)
	#In the 'text' variable, "Jim" and "He" are referring to the same entity.

view raw aspectbasedsentiment.py hosted with ❤ by GitHub

• context exclusion
• intent extraction
• co-reference resolution
• sentiment analysis

Keep Exploring!!!