OPINION MINING AND SENTIC ANALYSIS IN SOCIAL NETWORK BASED ON ELM.

Abstract

Extreme Learning Machine (ELM) is a new learning algorithm for feed forward neural network for classification or regression with a single layer of hidden nodes where the weights connecting inputs to hidden nodes are randomly assigned. Extreme Learning Machine allow polarity associated with natural language concept to be calculated in a more dynamic way to explore twitter user classification using content and context which are induced by hash tags and social communication in twitter. However, the explosive nature of the unstructured information generated around the world brings a challenge for sentiment-based information retrieval and analysis. This aims to solve the problem of extraction from product reviews that exploits commonsense knowledge by enabling fast reconfiguration of vector space.