amartyanambiar / profanityscore

ProfanityScore

Run the main.py file python main.py

Assumptions

1. You have a text file called 'tweets.txt' which contains one tweet per sentence.
2. You have a CSV file named 'racial_slurs.csv' which contain a column slur.

Output

When you run this code, it will provide you with the tweet number where profanity is detected, along with the precise profanity score.

profanityscore's Issues

Create a racial_slurs.csv file for racial slurs data

Currently, the code makes an assumption that racial_slurs.csv file is read and that contains a column of racial slurs.
Now lets get working to make that assumption real.

Proposed Solution:
The data for this file should be researched and collected from various sources, such as online databases, community forums, or academic studies. The data should be clean(no duplicates) and each slur should have a brief definition or context defining it.

Skills Required :
Research skills, data processing using pandas