Skip to content

srenna/ABSASentiment

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

8 Commits
 
 
 
 
 
 

Repository files navigation

Aspect Based Sentiment Analysis (ABSA)

The developed function will take as input a list of reviews and return a dataframe with the review id (i.e. the index of the review in the list), dish, corresponding sentiment score, and confidence.

To use, import the function from the submitted PY file.

from absa import absa
reviews = ["the first restaurant review. it can contain multiple sentences.",
           "the second restaurant review",
           ...]
results = absa(reviews)

The script will return a dataframe with the results!

About

Did the guest like the dish or not? This project uses a custom-trained Named Entity Recognition (NER) model to identify the dishes in a review and then use a pre-trained ABSA model to analyze the sentiment expressed about those dishes.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors