Analyzing Internet statistics, the most popular
online activities are communication via e-mail and searching
for information on goods and services. For getting the idea
about buying items customer reads reviews and feedback for
evaluation of a product. Sentiment analysis is a Natural
Language Processing (NLP) and Computational Linguistics
(CL) processing technique that defines extract, identifies,
analyzes and characterizes the sentiments or opinions in the
form of textual information. Most of the existing work done
in this domain is by using machine learning. Statistical
approach has been proposed for extraction of features, their
intensity and polarity.
Nilesh Shelke : Research Scholor, S.G.B. Amravati University, Amravati. (MS)
Shriniwas Deshpande : Associate Professor and Head in
P. G. Department of Computer Science and Technology,
DCPE, HVPM, Amravati. (MS) India.
Vilas Thakare : Professor and Head,
Post Graduate Department of Computer Science and Engg.,
SGB Amravati University, Amravati.
Sentiment Features, Sentiment Score, Aspects,
LSA
Despite all the challenges and potential issues that
threatens Sentiment analysis, one cannot ignore the value
that it adds to the industry. Because Sentiment analysis
bases its results on factors that are so inherently humane, it
is bound to become one the major drivers of many
business decisions in future. We have used Statistical
approach for product feature sentiment analysis. User
interface has developed using MatLab. The method used
here is very simple and domain independent. In this paper
we present our experiment with restaurant reviews.
However it is working same for the other domains like
camera, vehicles, books etc.
[1] Erik Cambria, Amir Hussain, “Sentic Computing”, A
book on Socio-Affective Computing Series, Springer
International Publishing, Series Vol. 1, ed. 1, 2015, pp
1-10. 10.1007/978-3-319-23654-4.
[2] Erik Cambria,“Affective Computing and Sentiment
Analysis”, published by IEEE Computer Society,
published in IEEE Intelligent Systems Vol. 31 (2), 17
March 2016, pp 2-5.
[3] Esuli Baccianella Stefano, Esuli Andrea and Sebastiani
Fabrizio, “SentiWordNet 3.0: An Enhanced
Lexical Re-source for Sentiment Analysis and Opinion
Mining”. Published in proceeding of the 7th Conference
on Language Resources and Evaluation, 2010, p. p.
2200-2204.
[4] Ohana, B. & Tierney, B.,“Sentiment classification of
reviews using SentiWordNet”, 9th IT&T Conference,
Dublin Institute of Technology, Dublin, Ireland,
October, 2009, pp 22-23.
[5] Wiebe J, Riloff E, “Finding Mutual Benefit between
Subjectivity Analysis and Information Extraction”,
IEEE Transactions on Affective Computing, Vol. 2,
No.(4), 2011, p.p. 175-191.
[6] Paltoglou G, Theunis M, Kappas A, Thelwall M,
“Predicting Emotional Responses to Long Informal
Text”, IEEE Transactions on Affective Computing,
Vol. 4, No. (1), 2013, p. p. 106 – 115.
[7] Ghose A, Ipeirotis P.G., "Estimating the Helpfulness
and Economic Impact of Product Reviews: Mining
Text and Reviewer Characteristics”, IEEE Transactions
on Knowledge and Data Engineering, Vol. 23, No.
(10), 2011, pp 1498 – 1512.
[8] Turney Mohammad, S. and Turney, P.D., “Emotions
Evoked by Common Words and Phrases: Using
Mechanical Turk to Create an Emotion Lexicon”. Proceedings of the NAACL-HLT Workshop on
Computational Approaches to Analysis and Generation
of Emotion in Text, Los Angeles, ACM publications,
2010, pp 26-34.
[9] Isa Maks, Piek Vossen, “A Verb Lexicon Model for
Deep Sentiment Analysis and Opinion Mining
Applications”, Proceedings of the 2nd Workshop on
Computational Approaches to Subjectivity and
Sentiment Analysis, ACL-HLT 2011, Portland,
Oregon, USA, ACM publications, 201),p.p. 10–18.
[10] Jerome R. Bellegarda, “Emotion Analysis using Latent
Affective Folding and Embedding”, Proceedings of the
NAACL HLT 2010 Workshop on Computational
Approaches to Analysis and Generation of Emotion in
Text, Los Angeles, CA, ACM publications, June
2010, p. p 1-9.
[11] Jingbo Zhu, Chunliang Zhang, Matthew Y. Ma,
“Multi-Aspect Rating Inference with Aspect-Based,
Segmentation”, IEEE Transactions on Affective
Computing, 2012, p.p. 469-480.
[12] Jingbo Zhu, Member, Huizhen Wang, Muhua Zhu,
Benjamin K. Tsou, “Aspect-Based Opinion Polling
from Customer Reviews”, published in IEEE
Transactions on Affective Computing, Vol. 2 (1),
2011, p.p. 37-49.
