A Unique Approach for Extracting Online Opinion Words from Online Reviews

Abstract

      M.Tech Student, Department of CSE,                                                                       Assistant Professor, Department of CSE,

   PVKK Institute of Technology,                                                                                      PVKK Institute of Technology,

             Sanapa Road, Rudrampeta,                                                                                           Sanapa Road, Rudrampeta,

       Anantapuramu-515004, A.P, India                                             Anantapuram-515004, A.P, India

ABSTRACT: Mining opinion targets and opinion words from online reviews are important tasks for fine-grained opinion mining, this involves detecting opinion relations among words. A novel approach based on the partially-supervised alignment model, which identifies opinion relations as an alignment process. Graph-based co-ranking algorithm is exploited to estimate the confidence of each candidate. Finally, candidates with higher confidence is extracted as opinion targets or opinion words. Compared to previous methods based on the nearest-neighbor rules, our model explores a very friendly use environment to the customers.

Key Words- Opinion mining, opinion targets extraction, opinion words extraction