Clickbait Post Detection using NLP for Sustainable Content

Abstract

Clickbait is a significant problem on online media platforms. It misleads users and manipulates their engagement. A user who clicks on a clickbait link may be taken to a website full of ads, or that requires them to pay for something. The goal of this project is to create a system that can recognize clickbait posts so that user can access only to sustainable content. The system will analyze data using natural language processing (NLP) and machine learning techniques. NLP pre-processing techniques, such as tokenization, lemmatization, and stemming, will be utilized to extract essential elements from the headlines. These features will subsequently be used to train a machine learning model, specifically a supervised classifier, to distinguish between clickbait and non-clickbait news headlines. The project will explore a range of algorithms and techniques, including popular text representation models such as TF-IDF or word embeddings, as well as classifier models like logistic regression or random forests. The model will be evaluated using a variety of metrics, such as Accuracy, Precision, Recall, and F1 score. By making it easier for users to identify clickbait, the system can help to reduce the amount of time and money wasted on this type of content.