Objectives: The main objective of this research is to improve the topical relations by extracting the opinion targets as well as opinion words, and achieve the higher performance using word alignment model concept.
Methods: Partially Supervised Word Alignment Model (PSWAM) is used for word alignment in existing system. The Latent Dirichlet Allocation (LDA) model is used for discovering opinion word relation extraction in proposed system.
Findings: The proposed method achieves high performance in terms of sensitivity and specificity.
Application/Improvements: The proposed system is done by using Latent Dirichlet Allocation (LDA) which is used to increase the performance for number of dataset more efficiently.
Keywords
Opinion Mining, Word Alignment Model, Opinion Targets Extraction, Opinion Words Extraction.
User
Information