Abbasi, A., Javed, A. R., Iqbal, F., Kryvinska, N., & Jalil, Z. (2022). Deep Learning for Religious and Continent-Based Toxic Content Detection and Classification. Scientific Reports, 12, Article No. 17478.
https://doi.org/10.1038/s41598-022-22523-3

has been cited by the following article:

• TITLE: Media Diversity Forecasting: A Longitudinal Study Using Hybrid Machine Learning Model for Predictive Insights into Community Representation (2004-2024)

  AUTHORS: Siddharth Yadav, Nicole Lee, Rezza Moieni

  KEYWORDS: Media Diversity, Communities Representation, Social Media Analytics, News Media, Entertainment Media

  JOURNAL NAME: Open Journal of Social Sciences, Vol.14 No.1, January 16, 2026

  ABSTRACT: This research addresses the growing interest in diverse media representation by investigating long-term trends across six communities: African, Asian, European, Hispanic, Indigenous, and Middle Eastern. Spanning news, social media, and entertainment, our study introduces a novel forecasting system using a hybrid of Long-Term Memory (LSTM) neural networks, Autoregressive Integrated Moving Average (ARIMA), and Prophet models. Two decades of data (2004-2024) were scraped from diverse open sources and media archives, and a unique engagement metric was proposed. The models demonstrated high accuracy, significantly improving upon benchmark studies in social media forecasting. This project also features a user-friendly web application, enabling stakeholders to gain predictive insights. This work offers actionable, data-driven insights to evaluate and improve media inclusivity, setting groundwork for future cultural analytics, policy development and ethical media production.