PROJECT TITLE :

Sentiment Data Flow Analysis by Means of Dynamic Linguistic Patterns

ABSTRACT:

Emulating the human brain is one in every of the core challenges of computational intelligence, which entails several key issues of artificial intelligence, together with understanding human language, reasoning, and emotions. During this work, computational intelligence techniques are combined with common sense computing and linguistics to research sentiment knowledge flows, i.e., to automatically decode how humans express emotions and opinions via natural language. The increasing availability of social knowledge is extraordinarily helpful for tasks like branding, product positioning, company reputation management, and social media selling. The elicitation of helpful info from this huge quantity of unstructured data, however, remains an open challenge. Though such information are easily accessible to humans, they're not appropriate for automatic processing: machines are still unable to effectively and dynamically interpret the which means associated with natural language text in terribly giant, heterogeneous, noisy, and ambiguous environments like the Internet. We present a completely unique methodology that goes beyond mere word-level analysis of text and allows a more efficient transformation of unstructured social knowledge into structured data, readily interpretable by machines. In explicit, we describe a unique paradigm for real-time concept-level sentiment analysis that blends computational intelligence, linguistics, and commonsense computing so as to boost the accuracy of computationally expensive tasks like polarity detection from huge social information. The most novelty of the paper consists in an algorithm that assigns contextual polarity to ideas in text and flows this polarity through the dependency arcs in order to assign a final polarity label to each sentence. Analyzing how sentiment flows from concept to concept through dependency relations allows for a better understanding of the contextual role of every concept in text, to achieve a dynamic polarity inference that outperforms state-of-the- art statistical strategies in terms of both accuracy and training time.