Geo-social Networks have major impact on human life and the Geo-social Network such as twitter, facebook have fetched the interest of researchers for its enormous amount of user generated content including tweets, blog posts, and forum messages is created. This data can provide benefits to governments, normal citizens and business people. Geo-social Network data can be served as an asset for the authorities to make real-time decisions and future planning by analyzing Geo-social media posts. However, there are millions of Geo-social Network users who are producing overwhelming of data, called “Big Data” that is challenging to be analyzed and make real-time decisions. In this proposed architecture Twitter data are analyzed in order to identify current events or disasters. The proposed system consists of five layers i.e., Tweet collection, Data Preprocessing, Feature Extraction, Classification, and Decision Making. During the training phase, the tweets are used to classify the emotions depending on the words which are extracted and processed using Natural Language Processing (NLP) techniques. The posts, texts, tweets, comments, statuses, and smiley are analyzed using text analytics, statistical analytics, complex machine learning and data mining techniques in order to monitor and determine what is occurring, where and why. Such type of data can be used to predict future events based on the current user trends that correspond to various areas.