Product reviews can provide great benefits for consumers and producers. Number of reviews could be ranging from hundreds to thousands and containing various opinions. These make the process of analyzing and extracting information on existing reviews become increasingly difficult. In this research, sentiment analysis was used to analyze and extract sentiment polarity on product reviews based on a specific aspect of the product. This research was conducted in three phases, such as data preprocessing which involves part-of-speech (POS) tagging, feature selection using Chi Square, and classification of sentiment polarity of aspects using Naive Bayes. Based on evaluation results, it is known that the system is able to perform aspect-based sentiment analysis with its highest F1-Measure of 78.12%.Product reviews can provide great benefits for consumers and producers. Number of reviews could be ranging from hundreds to thousands and containing various opinions. These make the process of analyzing and extracting information on existing reviews become increasingly difficult. In this research, sentiment analysis was used to analyze and extract sentiment polarity on product reviews based on a specific aspect of the product. This research was conducted in three phases, such as data preprocessing which involves part-of-speech (POS) tagging, feature selection using Chi Square, and classification of sentiment polarity of aspects using Naive Bayes. Based on evaluation results, it is known that the system is able to perform aspect-based sentiment analysis with its highest F1-Measure of 78.12%.
[1]
Caroline Brun,et al.
XRCE: Hybrid Classification for Aspect-based Sentiment Analysis
,
2014,
*SEMEVAL.
[2]
Pablo Gamallo,et al.
Citius: A Naive-Bayes Strategy for Sentiment Analysis on English Tweets
,
2014,
*SEMEVAL.
[3]
Josef Steinberger,et al.
UWB: Machine Learning Approach to Aspect-Based Sentiment Analysis
,
2014,
SemEval@COLING.
[4]
Bing Liu,et al.
Mining and summarizing customer reviews
,
2004,
KDD.
[5]
Saif Mohammad,et al.
NRC-Canada-2014: Detecting Aspects and Sentiment in Customer Reviews
,
2014,
*SEMEVAL.
[6]
J. Roscoe.
Fundamental Research Statistics for the Behavioral Sciences
,
2004
.
[7]
Roger G. Stone,et al.
Naive Bayes vs. Decision Trees vs. Neural Networks in the Classification of Training Web Pages
,
2009
.
[8]
Mihai Surdeanu,et al.
The Stanford CoreNLP Natural Language Processing Toolkit
,
2014,
ACL.
[9]
Charu C. Aggarwal,et al.
Mining Text Data
,
2012
.