Erik Cambria, MIT Media Lab, US
The focus of the proposed full-day tutorial is sentic computing, a multi-disciplinary approach to sentiment analysis at the crossroads between affective computing and common sense computing, which exploits both computer and social sciences to better recognise, interpret, and process opinions and sentiments over the Web. The main aim of the tutorial is to discuss ways to further develop and apply publicly available sentic computing resources for the development of applications in fields such as big social data analysis, human-computer interaction, and e-health. To this end, the tutorial will provide means to efficiently handle sentic computing models, e.g., the Hourglass of Emotions, techniques, e.g., sentic activation, tools, e.g., IsaCore, and services, e.g., Sentic API. The tutorial will also include insights resulting from the forthcoming IEEE Intelligent System Special Issue on Concept-Level Opinion and Sentiment Analysis and a hands-on session to illustrate how to build a sentic-computing-based opinion mining engine step-by-step.