Open AccessDomain specific opinion mining
Author(s) -
Surabhi Thorat,
C. Namrata Mahender
Publication year - 2018
Publication title -
international journal of engineering and technology
Language(s) - English
Resource type - Journals
ISSN - 2227-524X
DOI - 10.14419/ijet.v7i4.5.21173
Subject(s) - trigram , bigram , n gram , social media , computer science , polarity (international relations) , domain (mathematical analysis) , artificial intelligence , natural language processing , association (psychology) , sentiment analysis , association rule learning , data science , machine learning , information retrieval , world wide web , psychology , language model , mathematics , mathematical analysis , genetics , biology , psychotherapist , cell
The manuscript Social media is a very promising platform of communication between the peoples. Remarkable work has been done re- cently focusing on the analysis of social media in order to analyze the people thinking and behavioral trends about current topics of inter- est but still many challenges are yet to be uncovered. In this paper, we focused on analyzing the domain specific tweets collected from social media. To improve the result accuracy firstly we had done the polarity test to find the polarity of tweets categorized in negative, positive and neural labels. Secondly we applied N-gram model that assigns probabilities to sentences and sequences of words started from unigram, bigram, and trigram up-to four gram. Lastly, we performed association mining on the tweets to find the association of do- main specific data with its back and forth paired text.