Balanced Content Consumption Using Machine Learning Techniques
Joshua Ilangovan, P. Vidhya Saraswathi · 2024
The rapid growth of Digital Media and communication technologies over the past two decades has led to various emerging platforms that have become an integral part of an individual's life. People share and connect through social media and other digital platforms, leading to a growth of closed communities categorized by similarities in their interests and beliefs. Recommendation systems and Personalization Algorithms have become extremely sophisticated in their ability to make inferences and provide users with content based on data collected by their engagement on these platforms. This has led to the dominance of effects like filter bubbles and echo chambers which narrows content consumption and leads to intellectual isolation, misinformation, and uninformed decision-making. To address these effects, we propose an approach that leverages deep learning and statistical techniques to provide legitimate means of measuring a user's content consumption against a "balanced content consumption" standard which would develop a sense of awareness as well as control over content consumption for a user.