Dual Sentiment Analysis: Considering Two Sides of One Review

Abstract

Bag-of-words (BOW) is now the most popular way to model text in statistical machine learning approaches in sentiment analysis. However, the performance of BOW sometimes remains limited due to some fundamental deficiencies in handling the polarity shift problem. We propose a model called dual sentiment analysis (DSA), to address this problem for sentiment classification. We first propose a novel data expansion technique by creating a sentiment-reversed review for each training and test review. On this basis, we propose a dual training algorithm to make use of original and reversed training reviews in pairs for learning a sentiment classifier, and a dual prediction algorithm to classify the test reviews by considering two sides of one review. We also extend the DSA framework from polarity (positive-negative) classification to 3-class (positive negative- neutral) classification, by taking the neutral reviews into consideration. Finally, we develop a corpus-based method to construct a pseudo-antonym dictionary, which removes DSA’s dependency on an external antonym dictionary for review reversion. We conduct a wide range of experiments including two tasks, nine datasets, two antonym dictionaries, three classification algorithms and two types of features. The results demonstrate the effectiveness of DSA in addressing polarity shift in sentiment classification.

Aim

The aim is to generate a new model called dual sentiment analysis (DSA), to address the problem for sentiment classification.

Scope

The scope of DSA (data expansion technique) is to create reversed reviews that are sentiment-opposite to the original reviews, and make use of the original and reversed reviews in pairs to train a sentiment classifier and make predictions.

Existing System

Bag-of-words (BOW) is now the most popular way to model text in statistical machine learning approaches in sentiment analysis.

n recent years, with the growing volume of online reviews available on the Internet, sentiment analysis and opinion mining, as a special text mining task for determining the subjective attitude (i.e., sentiment) expressed by the text, is becoming a hotspot in the field of data mining and natural language processing. Sentiment classification is a basic task in sentiment analysis, with its aim to classify the sentiment (e.g., positive or negative) of a given text. The general practice in sentiment classification follows the techniques in traditional topic-based text classification, where the Bag-of-words (BOW) model is typically used for text representation. In the BOW model, a review text is represented by a vector of independent words. The statistical machine learning algorithms (such as naïve Bayes, maximum entropy classifier, and support vector machines) are then employed to train a sentiment classifier.

Disadvantages

·      The performance of BOW sometimes remains limited due to some fundamental deficiencies in handling the polarity shift problem.

·      BOW is actually not very suitable for sentiment classification because it disrupts the word order, breaks the syntactic structures, and discards some semantic information.

Proposed System

We propose a simple yet efficient model, called dual sentiment analysis (DSA), to address the polarity shift problem in sentiment classification. By using the property that sentiment classification has two opposite class labels (i.e., positive and negative), we first propose a data expansion technique by creating sentiment reversed reviews. The original and reversed reviews are constructed in a one-to-one correspondence. Thereafter, we propose a dual training (DT) algorithm and a dual prediction (DP) algorithm respectively, to make use of the original and reversed samples in pairs for training a statistical classifier and make predictions. In DT, the classifier is learnt by maximizing a combination of likelihoods of the original and reversed training data set. In DP, predictions are made by considering two sides of one review. That is, we measure not only how positive/ negative the original review is, but also how negative/ positive the reversed review is. We further extend our DSA framework from polarity (positive vs. negative) classification to 3-class (positive vs. negative vs. neutral) sentiment classification, by taking the neutral reviews into consideration in both dual training and dual prediction.To reduce DSA’s dependency on an external antonym dictionary, we finally develop a corpus-based method for constructing a pseudo-antonym dictionary. The pseudo antonym dictionary is language-independent and domain- adaptive. It makes the DSA model possible to be applied into a wide range of applications.

Advantages

·      DSA model is very effective for polarity classification and it significantly outperforms several alternative methods of considering polarity shift.

·      DSA-MI has major implications especially for sentiment analysis tasks with limited lexical resource and domain knowledge.

·      Pseudo - antonym dictionary reduces DSA’s dependency on an external antonym dictionary.

  

System Architecture

 

 System Specification

Hardware Requirements

• Speed                  -    1.1 Ghz
• Processor              -    Pentium IV
• RAM                    -    512 MB (min)
• Hard Disk            -    40 GB
• Key Board                    -    Standard Windows Keyboard
• Mouse                  -    Two or Three Button Mouse
• Monitor                -     LCD/LED

 Software requirements

• Operating System              : Windows 7             
•  Front End                           : ASP.Net and C#
• Database                             : MSSQL
• Tool                                    : Microsoft Visual studio

References

Feng Xu ; Chengqing Zong ; Qianmu Li,Rui Xia ," DUAL SENTIMENT ANALYSIS: CONSIDERING TWO SIDES OF ONE REVIEW" , IEEE Transactions on  Knowledge and Data Engineering, Volume:27 ,  Issue: 8 ,  February 2015