Submit Manuscript  

Article Details


Design of GA and Ontology based NLP Frameworks for Online Opinion Mining

[ Vol. 13 , Issue. 2 ]

Author(s):

Manik Sharma*, Gurvinder Singh and Rajinder Singh   Pages 159 - 165 ( 7 )

Abstract:


Background: For almost every domain, a tremendous degree of data is accessible in an online and offline mode. Billions of users are daily posting their views or opinions by using different online applications like WhatsApp, Facebook, Twitter, Blogs, Instagram etc.

Objective: These reviews are constructive for the progress of the venture, civilization, state and even nation. However, this momentous amount of information is useful only if it is collectively and effectively mined.

Methodology: Opinion mining is used to extract the thoughts, expression, emotions, critics, appraisal from the data posted by different persons. It is one of the prevailing research techniques that coalesce and employ the features from natural language processing. Here, an amalgamated approach has been employed to mine online reviews.

Results: To improve the results of genetic algorithm based opining mining patent, here, a hybrid genetic algorithm and ontology based 3-tier natural language processing framework named GAO_NLP_OM has been designed. First tier is used for preprocessing and corrosion of the sentences. Middle tier is composed of genetic algorithm based searching module, ontology for English sentences, base words for the review, complete set of English words with item and their features. Genetic algorithm is used to expedite the polarity mining process. The last tier is liable for semantic, discourse and feature summarization. Furthermore, the use of ontology assists in progressing more accurate opinion mining model.

Conclusion: GAO_NLP_OM is supposed to improve the performance of genetic algorithm based opinion mining patent. The amalgamation of genetic algorithm, ontology and natural language processing seems to produce fast and more precise results. The proposed framework is able to mine simple as well as compound sentences. However, affirmative preceded interrogative, hidden feature and mixed language sentences still be a challenge for the proposed framework.

Keywords:

Genetic algorithm, ontology, natural language processing, pos tagging, discourse analysis, opinion mining.

Affiliation:

Department of Computer Science and Applications, DAV University, Jalandhar, Department of Computer Science, GNDU, Amritsar, Department of Computer Science, GNDU, Amritsar

Graphical Abstract:



Read Full-Text article