Project information

• Category: API and Exploratory Data Analysis
• Associate: Binar Academy
• Project URL: View My Github Repository

I created an API to clean and detect hate speech and harassment in Twitter data. I gathered a diverse dataset, cleaned the data, and detected hate speech using natural language processing techniques. I compared the distribution of non-hate/non-abusive content with hate/abusive content in the dataset and analyzed key words in harmful content.

I developed the API using Python and conducted testing and evaluation. My analysis showed that non-hate/non-abusive content is more prevalent on Twitter than harmful content, which can be used to address online toxicity.