et al.(2012) have used the NLP and the Sentiwordnet dictionary. The purpose of
their work is to track the behavior of the users about a particular topic on
the social networks. The proposed model in this article also identifies the
social structures, types of the communications and the specific individuals.
et al.(2015) have used the Sentiwordnet dictionary in a feature-based research.
In this paper, the sentiment analysis is carried out in certain places using
the demographic characteristics such as being male and female. To analyze the
data, the tweets in seven cities have been explored about the features of the
iPhone 6 mobile phones.
Abbasi et al.(2008) is an instance of the
studies conducted in the field of studying with an observer. This paper focuses
on the recognition of the common, syntactic and independent language features.
These features are derived from the Arabic and English associations of genetic
first study done on Persian language was conducted by Mohammad Reza Shams et al.(2012)
who used the LDA’s unattended method in order to learn the model. The dataset
used in this article is 400 comments on the mobile phone products that are categorized
into two groups of 200.
Nekah et al.(2014)
used the method of learning based on the sentence-based monitoring in their
research. In this study, a method is proposed in order to define the semantic labels
and combine them with the syntax tags to have a better understanding of the
Vamerzani & Khademi
conducted a research analyzing the users’ reviews, visualizing the results and
enhancing the business intelligence using an analysis of the opinions and
considering the challenges of Persian language in its preprocessing. They used
an algorithm with a backup vector machine and the TFIDF feature selection
method. The F criterion in this study is 90.15 (Vamerzani & Khademi, 2015).
al.(2011) consider a vector of the words in the space of the multi-dimensional
relationships. In this paper, they examine the data on a film and use the
combination of LDA and LSA, two observer and non-observer algorithms, in order
to overcome the syntactic and semantic relations simultaneously.
Chen & Qi use the machine learning algorithms to
examine the impact of the social networks on the customer purchases. In this
paper, the linear model of CRFs is used for opinion mining. The results reveal
that it functions better than the other algorithms of machine learning. It has
developed, for the first time, a three-dimensional architecture in order to
influence the users’ decision-making process. It tracks the users’ decision
making and behaviors, shows the users a matrix comparison for better
comparisons of the products, and has given more weight to the negative opinions
(Chen & Qi, 2011).
the proposed methods for extracting the features in a domain require the
educational data related to that specific domain. Therefore, we use the double
propagation method in order to extract the features(Qiu, Liu, Bu, & Chen, 2011). Due to
the lack of a comprehensive Persian dictionary, we use the translation of the
comprehensive Bing Liu Dictionary, which contains the general vocabulary
containing feelings in English.
researches carried out so far, especially on the Persian language, less
attention has been paid to solving the problems of the pre-processing stages.
The quantitative researches have focused on extracting the product features and
determining the polarity of these features. In the double propagation method
used in research (Golpar-Rabooki et al., 2015), only
the adjectives are considered as the opinion words, while some verbs also
include the role of a feature or the opinion words. For example the verb
“use” is an feature in the sentence “the ease of use”, and the
word “liked” in the sentence “I liked the quality of this
phone” contains opinion. To better understand the features and the opinion
words, the verbs and the adverbs that have these features should be identified.
One of the disadvantages of this method is that for determining the polarity of
the sentences whose opinion words are not polarized, the polarity of the
sentences before and after them is considered in order to determine the
polarity of the current sentence. Better methods can be used to determine the
polarity of these sentences.
to increase the accuracy of classifying the opinions, it is possible to
eliminate the additional and the neutral words in determining their polarity.