Emotion aware big data system for prediction human behavioural shifts

“Emotion Aware Big Data System for Prediction of Human Behavioural Shifts” is an area that is a huge step ahead in predictive analysis. This project exemplifies and proves that by going ahead of mere transaction data and using the unstructured mine of human emotions we can effectively and meaningfully understand human behavior in a more sophisticated manner. It has successfully designed and conceptualized an efficient construction that is equipped to transaction with the Velocity and Variety of Big Data. This system bridges the gap that results from traditional methods of analysis that involve an analysis tool based on a singular channel of information. It has proven that an emotion that lasts for an instant can be quantified and analysed and predictive of an action that will occur in the future. Technologically it has been proven that a hybrid system of distributed computing platforms (Hadoop/Spark) with superior Deep Learning algorithms (CNNs & LSTMs) can be highly effective. This hybrid model would therefore confirm that the planned arrangement has the capability to scale up for processing global streaming data effectively and be smart enough to identify subtle human micro-expressions. The feasibility study and analysis of requirements for this system would therefore mean a system that can be theoretically correct and implementable in various sectors such as mental health care public protection retail and marketing which will enable decision-takers to be proactive instead of being reactive while anticipating a change that will soon be required.

Cambria, E., & Hussain, A. (2015). Sentic Computing: A Common-Sense-Based Framework for Concept-Level Sentiment Analysis. Springer International Publishing. 2. Picard, R. W. (2000). Affective Computing. The MIT Press. 3. Dean, J., & Ghemawat, S. (2008). "MapReduce: Simplified Data Processing on Large Clusters." Communications of the ACM, 51(1), 107-113. 4. Ekman, P. (1992). "An Argument for Basic Emotions." Cognition & Emotion, 6(3-4), 169-200. 5. Hochreiter, S., & Schmidhuber, J. (1997). "Long Short-Term Memory." Neural Computation, 9(8), 1735-1780.