In today’s digital world, where online platforms like Facebook, Twitter, and WhatsApp are ubiquitous, it is imperative to address the challenges faced by women in various roles, including as employees or team leaders within organizations. Unfortunately, women often encounter situations involving harassment, abusive language, toxic remarks, and hate speech on a daily basis. To tackle this issue effectively, it is crucial to employ efficient automatic detection tools capable of identifying such problematic comments across online forums, websites, blogs, YouTube, and social media networks. Manually searching for each toxic word within comments is time-consuming and inefficient. To address this, we conducted an analysis on a toxic comment dataset, utilizing natural language processing (NLP) techniques. NLP plays a vital role in processing text effectively and understanding its meaning. In our approach, we employed a transformer model for comment classification. Transformer models are powerful neural networks that grasp the semantics of sequential data by capturing relationships between different parts, such as words within a sentence. By leveraging the capabilities of transformer models, we aimed to identify and address toxic comments in a more efficient manner.