Welcome to PyDataMCR Episode 12, This episode is all about Natural Language Processing, specifically Sentiment Analysis. Listen for our take on the approach to the complexity of text data, how we prepare the data, and the tools we can use to tease out sentiment.

Sponsors

LadBible - ladbible.com/

Cathcart Associates - cathcartassociates.com/

Horsefly Analytics - horseflyanalytics.com/

Resources

Tutorials

Natural Language Processing

https://www.kaggle.com/learn/natural-language-processing

Word embeddings for sentiment analysis https://towardsdatascience.com/word-embeddings-for-sentiment-analysis-65f42ea5d26e

Sentiment Analysis in R

https://www.kaggle.com/rtatman/tutorial-sentiment-analysis-in-r

Tools

NLTK - https://www.nltk.org/

SpaCy - https://spacy.io/

TextBlob - https://textblob.readthedocs.io/en/dev/

VADER - https://github.com/cjhutto/vaderSentiment

Google Natural Language API - https://cloud.google.com/natural-language

Azure Text Analytics API https://azure.microsoft.com/en-gb/services/cognitive-services/text-analytics/

Social

Meetup - meetup.com/PyData-Manchester/

Slack -  http://bit.ly/35KGOgR

Twitter - @PyDataMCR