High Impact Factor : 4.396 icon | Submit Manuscript Online icon |

ASPECT BASED OPINION MINING: IN CONTEXT OF HINDI ROMAN LANGUAGE USING NLP

Author(s):

MARIYA ZAFAR , Dr. A.P.J. Abdul Kalam Technical University (Lko) U.P; Masood Ahmad, Dr. A.P.J. Abdul Kalam Technical University (Lko) U.P; Dr. Shafeeq Ahmad, Dr. A.P.J. Abdul Kalam Technical University (Lko) U.P

Keywords:

Natural Language Processing (NLP), Context-Free Grammar, Opinion Mining, Auto-Correction, Feature Extraction, POS Tagging, Roman Hindi Language

Abstract

The internet revolution has brought about a new way of expressing an opinion. It has become a medium through which people openly express their views on various subjects. These opinions contain useful information which can be utilised in many sectors which require constant customer feedback. Analysis of the opinion and it's classification into different classes is gradually produced as a key factor in decision-making These strategies usually attempt to extract the overall sentiment revealed in a sentence or document, either positive or negative, or somewhere in between. However, a downside of those strategies is that the information is often degraded, particularly in texts wherever a loss of information may occur due to mismatch of grammar in global language. In this paper, we tackle such situation Firstly with the implementation of Autocorrect feature, Secondly by acknowledging those Aspects based words which user writes in their home language. Then we apply our limited datasets to regain such words in its standard form. This method helps us to make our sentiment analysis more efficient.

Other Details

Paper ID: IJSRDV5I30983
Published in: Volume : 5, Issue : 3
Publication Date: 01/06/2017
Page(s): 1480-1483

Article Preview

Download Article