Classifying Product Reviews from Balanced Datasets for Sentiment Analysis and Opinion Mining

Periakaruppan Sudhakaran, Shanmugasundaram Hariharan, Joan Lu

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Citations (Scopus)

Abstract

The Online reviews provided for a product enables web user to make decisions appropriately. These reviews may be positive, negative or neutral in nature. Analyzing and classifying such product reviews have attracted reasonable interest. It has become quite hard to make decisions since we aren't able to obtain the decisions quickly. Hence it is required to classify the reviews from balanced data sets for analysis and opinion mining of any applications. The reason for considering balanced data sets is that the decision will not be biased on the category of reviews considered. We have carried out investigations using similarity measures to categorize the reviews correctly. Experiments reveal that the reviews that were mixed in nature were able to be grouped correctly.

LanguageEnglish
Title of host publicationProceedings - 6th International Conference on Multimedia, Computer Graphics and Broadcasting, MulGraB 2014
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages29-34
Number of pages6
ISBN (Electronic)9781479977642
DOIs
Publication statusPublished - 27 Jan 2015
Event6th International Conference on Multimedia, Computer Graphics and Broadcasting - Hainan, China
Duration: 20 Dec 201423 Dec 2014
Conference number: 6
http://www.conferen.org/MulGraB2014/ (Link to Conference Website )

Conference

Conference6th International Conference on Multimedia, Computer Graphics and Broadcasting
Abbreviated titleMulGraB 2014
CountryChina
CityHainan
Period20/12/1423/12/14
Internet address

Fingerprint

Experiments

Cite this

Sudhakaran, P., Hariharan, S., & Lu, J. (2015). Classifying Product Reviews from Balanced Datasets for Sentiment Analysis and Opinion Mining. In Proceedings - 6th International Conference on Multimedia, Computer Graphics and Broadcasting, MulGraB 2014 (pp. 29-34). [7024252] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/MulGraB.2014.14
Sudhakaran, Periakaruppan ; Hariharan, Shanmugasundaram ; Lu, Joan. / Classifying Product Reviews from Balanced Datasets for Sentiment Analysis and Opinion Mining. Proceedings - 6th International Conference on Multimedia, Computer Graphics and Broadcasting, MulGraB 2014. Institute of Electrical and Electronics Engineers Inc., 2015. pp. 29-34
@inproceedings{6bfa07c9c4764ee8ab38f5ce0ac88e01,
title = "Classifying Product Reviews from Balanced Datasets for Sentiment Analysis and Opinion Mining",
abstract = "The Online reviews provided for a product enables web user to make decisions appropriately. These reviews may be positive, negative or neutral in nature. Analyzing and classifying such product reviews have attracted reasonable interest. It has become quite hard to make decisions since we aren't able to obtain the decisions quickly. Hence it is required to classify the reviews from balanced data sets for analysis and opinion mining of any applications. The reason for considering balanced data sets is that the decision will not be biased on the category of reviews considered. We have carried out investigations using similarity measures to categorize the reviews correctly. Experiments reveal that the reviews that were mixed in nature were able to be grouped correctly.",
keywords = "Opinion mining, sentiment analysis, user reviews",
author = "Periakaruppan Sudhakaran and Shanmugasundaram Hariharan and Joan Lu",
year = "2015",
month = "1",
day = "27",
doi = "10.1109/MulGraB.2014.14",
language = "English",
pages = "29--34",
booktitle = "Proceedings - 6th International Conference on Multimedia, Computer Graphics and Broadcasting, MulGraB 2014",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

Sudhakaran, P, Hariharan, S & Lu, J 2015, Classifying Product Reviews from Balanced Datasets for Sentiment Analysis and Opinion Mining. in Proceedings - 6th International Conference on Multimedia, Computer Graphics and Broadcasting, MulGraB 2014., 7024252, Institute of Electrical and Electronics Engineers Inc., pp. 29-34, 6th International Conference on Multimedia, Computer Graphics and Broadcasting, Hainan, China, 20/12/14. https://doi.org/10.1109/MulGraB.2014.14

Classifying Product Reviews from Balanced Datasets for Sentiment Analysis and Opinion Mining. / Sudhakaran, Periakaruppan; Hariharan, Shanmugasundaram; Lu, Joan.

Proceedings - 6th International Conference on Multimedia, Computer Graphics and Broadcasting, MulGraB 2014. Institute of Electrical and Electronics Engineers Inc., 2015. p. 29-34 7024252.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Classifying Product Reviews from Balanced Datasets for Sentiment Analysis and Opinion Mining

AU - Sudhakaran, Periakaruppan

AU - Hariharan, Shanmugasundaram

AU - Lu, Joan

PY - 2015/1/27

Y1 - 2015/1/27

N2 - The Online reviews provided for a product enables web user to make decisions appropriately. These reviews may be positive, negative or neutral in nature. Analyzing and classifying such product reviews have attracted reasonable interest. It has become quite hard to make decisions since we aren't able to obtain the decisions quickly. Hence it is required to classify the reviews from balanced data sets for analysis and opinion mining of any applications. The reason for considering balanced data sets is that the decision will not be biased on the category of reviews considered. We have carried out investigations using similarity measures to categorize the reviews correctly. Experiments reveal that the reviews that were mixed in nature were able to be grouped correctly.

AB - The Online reviews provided for a product enables web user to make decisions appropriately. These reviews may be positive, negative or neutral in nature. Analyzing and classifying such product reviews have attracted reasonable interest. It has become quite hard to make decisions since we aren't able to obtain the decisions quickly. Hence it is required to classify the reviews from balanced data sets for analysis and opinion mining of any applications. The reason for considering balanced data sets is that the decision will not be biased on the category of reviews considered. We have carried out investigations using similarity measures to categorize the reviews correctly. Experiments reveal that the reviews that were mixed in nature were able to be grouped correctly.

KW - Opinion mining

KW - sentiment analysis

KW - user reviews

UR - http://www.scopus.com/inward/record.url?scp=84933525181&partnerID=8YFLogxK

U2 - 10.1109/MulGraB.2014.14

DO - 10.1109/MulGraB.2014.14

M3 - Conference contribution

SP - 29

EP - 34

BT - Proceedings - 6th International Conference on Multimedia, Computer Graphics and Broadcasting, MulGraB 2014

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Sudhakaran P, Hariharan S, Lu J. Classifying Product Reviews from Balanced Datasets for Sentiment Analysis and Opinion Mining. In Proceedings - 6th International Conference on Multimedia, Computer Graphics and Broadcasting, MulGraB 2014. Institute of Electrical and Electronics Engineers Inc. 2015. p. 29-34. 7024252 https://doi.org/10.1109/MulGraB.2014.14