Twitter Cyber Bullying Sentiment NLP Streamlit in Python Projects

Twitter Cyber Bullying Sentiment NLP Streamlit in Python Projects
Abstract
Cyberbullying on social media platforms, particularly Twitter, has become a significant social problem, affecting mental health and user safety. This project focuses on Twitter Cyberbullying Sentiment Analysis using Natural Language Processing (NLP) and Streamlit in Python, which automatically detects cyberbullying-related tweets and analyzes their sentiment. The system collects tweets from the Twitter API, preprocesses text data by removing stopwords, emojis, and special characters, and applies NLP techniques such as tokenization, lemmatization, and TF-IDF vectorization. Machine learning classifiers like Logistic Regression, Random Forest, or Support Vector Machines are used to classify tweets as bullying or non-bullying, while sentiment analysis detects positive, negative, or neutral tones. Streamlit is used to create an interactive web application for visualizing results. The project aims to help social media platforms monitor harmful content, raise awareness, and promote safer online environments.

Existing System
Existing systems for detecting cyberbullying rely heavily on manual moderation, keyword-based filtering, or basic sentiment analysis. Manual moderation is time-consuming and cannot scale effectively, while keyword-based approaches often miss context, sarcasm, or subtle forms of bullying. Basic sentiment analysis methods fail to accurately capture the nuances of cyberbullying content, resulting in false positives and negatives. Most existing solutions also lack interactive platforms for visualizing trends, analyzing sentiment, and providing actionable insights for social media administrators or researchers. Consequently, current systems are inefficient, inconsistent, and unable to provide real-time detection and analysis.

Proposed System

The proposed system introduces a Python-based NLP and Streamlit framework for Twitter cyberbullying detection and sentiment analysis. Tweets are collected using the Twitter API and preprocessed for noise removal and text normalization. Feature extraction is performed using techniques like TF-IDF or word embeddings (Word2Vec, GloVe, or BERT). Machine learning classifiers such as Logistic Regression, Random Forest, or Support Vector Machines are trained on labeled datasets to detect cyberbullying tweets. Sentiment analysis is integrated to classify detected tweets into positive, negative, or neutral categories. Streamlit provides a user-friendly interactive interface to input Twitter handles or keywords, visualize detected cyberbullying instances, sentiment trends, and generate reports. By combining NLP, machine learning, and interactive visualization, the system provides a scalable, automated, and accurate solution for monitoring cyberbullying, supporting proactive intervention, and promoting safer online communities.

Customer Reviews (0)

Share Your Experience

Rating

Your Comment

Submit Review Cancel

No reviews yet. Be the first!