A Spatio-demographic Analysis over Twitter Data Using Artificial Neural Networks

The demographic and population modeling methods have been under investigation trends since the 1980s. Extrapolation, prediction, and theoretical computational analysis of exogenous variables are approaches to the forecasting of population processes. Such methods can be exploited to predict individual birth preferences or experts’ views at the population level. Predicting demographic changes have been problematic while its precision usually depends on the case or pattern; numerous methods have been explored; however, so far there is no clear guidelines where the proper approach ought to be. Like certain fields of industry and policy, planning is focused on projections for the future composition of the population, the potential creation of population sizes and institutions which are significant. In order to recognize potential social security issues as one determinant of overall macroeconomic growth, countries that have reduced mortality and low fertility, the case with some of the Asian nations, desperately require accurate demographic estimates. This introduction provides a stochastic cohort model that uses stochastic fertility, migration, and mortality modeling approaches to forecast the population by gender and literacy. This work focus on the population and literacy ratio of India as this nation holds the second largest population in the world. Our approach is based on artificial neural network algorithm that can forecast the population literacy ratio and gender differences based on living states populations using social networks data. We concentrated primarily on quantifying future planning challenges as previous research appeared to neglect potential risks. Our model is then used to forecast/predict gender-wise population for each major state/city. The findings offer clear perspectives on the projected gender demographic composition, and our model holds high precision results.