Sentiment Analysis of Harmful Comments and personalized support for users receiving them

[Nabanita29]

Is your feature request related to a problem? Please describe.

The objective of this project is to develop an Emotion Recognition and Sentiment Analysis system for harmful comments. The system will use machine learning techniques to classify harmful comments into different sentiment categories (e.g., positive, negative, neutral) and recognize the associated emotions expressed in the comments. By doing so, we aim to create a tool that can help identify harmful content on online platforms and respond to such content with appropriate and encouraging messages.

Describe the solution you'd like

The proposed solution involves building an Emotion Recognition and Sentiment Analysis system for harmful comments. The system utilizes a Support Vector Machine (SVM) classifier trained on a dataset of harmful comments with sentiment labels. After preprocessing the input text to clean and extract relevant features, the SVM model predicts the sentiment of the comments. The user can interact with the system by providing their own text, which is processed and classified. To enhance the user experience, the system also integrates with an Encouragement Bot through the PoE API, responding with positive and supportive messages for negative comments and appropriate replies for positive ones. This solution aims to identify harmful content and foster a more positive online environment by addressing harmful comments with encouraging responses.

Describe alternatives you've considered

No response

Additional context

I am a gssoc contributor
The project will be done in a week of assigning since it is already being worked on.

Code of Conduct

• I agree to follow this project's Code of Conduct