Improving cyberbullying detection on Instagram comments using machine learning. The motivation for this project was to address the growing concern of cyberbullying, especially on social media platforms such as Instagram. Cyberbullying is a form of online harassment that involves the use of electronic communication to intimidate, humiliate, or threaten others. This type of bullying can be difficult to detect and prevent, as it often occurs anonymously, making it challenging to identify the perpetrators.
To address this issue, I used machine learning algorithms to develop a model that could automatically detect cyberbullying in Instagram comments. The first step was to preprocess the data by cleaning and transforming the text data into a format that could be used by the machine learning algorithms.
Next, I used two feature extraction techniques, Counter Vectorizer and Tfidf Transformer, to convert the text data into numerical vectors. Counter Vectorizer is a technique that counts the frequency of each word in the text, while Tfidf Transformer takes into account the importance of each word in the text by weighting it based on its frequency and rarity.
Finally, I used machine learning algorithms to train and test the model. The goal was to develop a model that could accurately classify comments as either cyberbullying or not cyberbullying.