SenticNet

In human cognition, thinking and feeling are mutually present: emotions are often the product of our thoughts as well as our reflections are often the product of our affective states. Emotions, in fact, are intrinsically part of our mental activity and play a key role in communication and decision-making processes. They are special states, shaped by natural selection, to adjust various aspects of our organism in order to make it better face particular situations, e.g., anger evolved for reaction, fear evolved for protection and affection evolved for reproduction. For these reasons we cannot prescind from emotions in the development of intelligent systems: if we want computers to be really intelligent, not just have the veneer of intelligence, we need to give them the ability to understand and express emotions.

Sentic computing is a multi-disciplinary approach to opinion mining and sentiment analysis that exploits both computer and social sciences to better recognize, interpret and process opinions and sentiments over the Web. In sentic computing, whose term derives from the Latin sentire (root of words such as sentiment and sentience) and sensus (intended both as capability of feeling and as common sense), the analysis of natural language is based on affective ontologies and common sense reasoning tools, which enable the analysis of text not only at document, page or paragraph level but also at sentence and clause level. In particular, sentic computing involves the use of AI and Semantic Web techniques, for knowledge representation and inference; mathematics, for carrying out tasks such as graph mining and multi-dimensionality reduction; linguistics, for discourse analysis and pragmatics; psychology, for cognitive and affective modeling; sociology, for understanding social network dynamics and social influence; finally ethics, for understanding related issues about the nature of mind and the creation of emotional machines.

TECHNIQUES
Within sentic computing, a variety of techniques has been developed for the extraction of semantics and sentics from natural language text, namely:
•  Affective Blending: the process for building the matrix representation of AffectNet from ConceptNet and WordNet-Affect;
•  Sentic Medoids: a novel clustering technique for organizing affective common sense concepts in AffectiveSpace;
•  Sentic Activation: a bio-inspired two-level framework that exploits an ensemble application of dimensionality reduction and graph mining techniques;
•  Sentic Neural Networks: an MLP-based architecture for a more brain-inspired affective common sense recognition;
•  CF-IOF Weighting: a technique similar to TF-IDF weighting that evaluates how important a concept is to a set of opinions concerning the same topic;
•  Sentic Panalogy: an approach that models the switch between different reasoning strategies and between the foci around which such strategies are developed.

TOOLS
The above-mentioned techniques have been employed within this research work for the design of a set of tools for the automatic analysis of opinions and sentiments, videlicet:
•  AffectiveSpace: a vector space representation of AffectNet for reasoning by analogy on affective common sense knowledge;
•  The Hourglass of Emotions: a biologically-inspired and psychologically-motivated model for the representation and the analysis of human emotions;
•  Open Mind Common Sentics: an emotion-sensitive IUI for collecting affective common sense knowledge from general public;
•  SenticNet: a publicly available semantic resource for opinion mining built using both AI and Semantic Web techniques;
•  Isanette: a semantic network of common and common sense knowledge for auto-categorization built upon ConceptNet and Probase;
•  Opinion Mining Engine: an intelligent engine for concept-level open-domain opinion mining and sentiment analysis.

APPLICATIONS
Eventually, the above-mentioned opinion mining tool has been exploited for the development of emotion-sensitive applications in fields such as Social Web, HCI, and e-health, namely:
•  Troll Filter: a system for automatically filtering inflammatory and outrageous posts within online communities;
•  Social Media Marketing Tool: an intelligent web application for managing social media information about products and services through a faceted interface;
•  Sentic Album: a content, concept and context based online personal photo management system;
•  Sentic Chat: an IM platform that enriches social communication through semantics and sentics;
•  Sentic Corner: an IUI that dynamically collects audio, video, images and text related to the user’s emotions and motions;
•  Sentic Avatar: an emotion-sensitive avatar built through the integration of sentic computing with a facial emotional classifier;
•  Crowd Validation: a process for mining patient opinions and bridging the gap between unstructured and structured health-care data;
•  Sentic PROMs: a new framework for measuring health care quality that exploits the ensemble application of standard PROMs and sentic computing.