This is a project for a computer science course.
I was tasked with creating python code that would read reviews from a supplied .csv dataset.
The code then preprocesses the text and then analyses the sentiment of sample reviews. Finally, it compares the chosen reviews to a sample review to test the similarity function.
The result is printed at the end in a report.
Note: Overall the results of this model are not very accurate but this task was very useful as a starting point into learning NLP. Any recommendations would be very welcome.
This project uses:
Pandas - for working with the dataset
and
Spacy and SpacyTextBlob - for implementing NLP
Simply download the python file along will the 1429_1.csv dataset prodived here on Kaggle, be sure to make sure they are in the same folder, and then run the .py file.
- Help with this ReadMe from - Awesome README and How To... ReadMe
- Thanks to all the team at coding bootcamp Hyperion Dev