Open Access
ARTICLE
Enhancing the Classification Accuracy in Sentiment Analysis with Computational Intelligence Using Joint Sentiment Topic Detection with MEDLDA
PCD Kalaivaani1,*, Dr. R Thangarajan2
1 Assistant Professor (Selection Grade), Department of CSE, Kongu Engineering College, Perundurai, Erode, Tamil Nadu 638052, India
2 Professor, Department of CSE, Kongu Engineering College, Perundurai, Erode, Tamil Nadu 638052, India
* Corresponding Author: PCD. Kalaivaani,
Intelligent Automation & Soft Computing 2020, 26(1), 71-79. https://doi.org/10.31209/2019.100000152
Abstract
Web mining is the process of integrating the information from web by
traditional data mining methodologies and techniques. Opinion mining is an
application of natural language processing to extract subjective information
from web. Online reviews require efficient classification algorithms for analysing
the sentiments, which does not perform an in–depth analysis in current
methods. Sentiment classification is done at document level in combination with
topics and sentiments. It is based on weakly supervised Joint Sentiment-Topic
mode which extends the topic model Maximum Entropy Discrimination Latent
Dirichlet Allocation by constructing an additional sentiment layer. It is assumed
that topics generated are dependent on sentiment distributions and the words
generated are conditioned on the sentiment topic pairs. MEDLDA is used to
increase the accuracy of topic modeling.
Keywords
Cite This Article
P. Kalaivaani and D. R. Thangarajan, "Enhancing the classification accuracy in sentiment analysis with computational intelligence using joint sentiment topic detection with medlda,"
Intelligent Automation & Soft Computing, vol. 26, no.1, pp. 71–79, 2020.