sentiment analysis

Sentiment analysis, also called opinion mining, is one of the sub-areas of natural language processing that aims to classify texts according to the sentiments, beliefs and attitudes expressed in them. In the most current research, texts are divided into two "positive" and "negative" categories. However, there are also other categories such as good/bad" and agree/disagree, every one of which has its applications. The purpose of this paper is to analyze the opinions expressed by users on social media about the reopening of schools during the Covid-19 outbreak using supervised machine learning techniques, and to classify them into two "agree" and "disagree" categories. Users' opinions, in this paper, are in Persian. The lack of sufficient datasets and also the low accuracy of natural language processing tools are the most important problems of text processing in Persian. Due to the mentioned limitations, the use of supervised machine learning algorithms and also the extraction of effective features for training machine learning classifiers in Persian are facing a serious challenge. In this paper, first, a small dataset of the users' opinions about the reopening of schools was collected and manually labeled. Then, a combined method was used for data augmentation of the dataset. In the proposed method, first, Persian sentences were translated into English. Then nouns, verbs and adjectives of the English sentences were replaced with their synonyms. Next, the English sentences were translated into Persian again. The new sentence with the class label of the initial sentence was added to the training set. Thus, the size of the training set increased by 97 percent. After that, the efficiency of employing the common pre-processing steps and using common feature sets in sentiment analysis of the English texts for Persian were evaluated and the best of them were selected. Considering the low accuracy of the Persian natural language processing tools, it was tried to select those features that were less dependent on the tools. Finally, machine learning classification was used to determine agree/disagree class of the user opinions of the test sets. The results of the experiments indicated that by applying the proposed method for data augmentation and using selected features in this paper, 81 and 79 percent precision was obtained for the polarity classification of opinions using SVM and CNN algorithms, respectively.

In recent years, the massive growth of generated content by users in social networks and online marketing sites, allows people to share their feelings and opinions on a variety of opinions about different products and services. Sentiment analysis is an important factor for better decision-making that is done using natural language processing (NLP), computational methods, and text analysis to extract the polarity of unstructured documents. The complexity of human languages and sentiment analysis have created a challenging research context in computer science and computational linguistics. Many researchers used supervised machine learning algorithms such as Naïve Bayes (NB), Stochastic Gradient Descent (SGD), Support Vector Machine (SVM), Logistic Regression (LR) Random Forest (RF), and deep learning algorithms such as Convolution Neural Network (CNN) and Long Short-Term Memory (LSTM). Some researchers have used Dictionary-based methods. Despite the existence of effective techniques in text mining, there are still unresolved challenges. Note that user comments are unstructured texts; Therefore, in order to structure the textual inputs, parsing is usually done along with adding some features, linguistic interpretations and removing additional items, and inserting the next terms in the database, then extracting the patterns in the structured data and finally the outputs will evaluate and interpret. The imbalance of data with the difference in the number of samples in each class of a dataset is an important challenge in the learning phase. This phenomenon breaks the performance of the classifications because the machine does not learn the features of the unpopulated classes well. In this paper, words are weighted based on the prescribed dictionary to influence the most important words on the result of the opinion mining by giving higher weight. On the other hand, the combination of the adjacent words using n-gram methods will improve the outcome. The dictionaries are highly related to the domain of the application. Some words in an application are important but in mobile comments are not impressive. Another challenge is the unbalanced train data, in which the number of positive sentences is not equal to the number of negative sentences. In this paper, two ideas are applied to build an efficient opinion mining algorithm. First, we build a precise dictionary for mobile Persian comments, and the second idea is to balance the positive and negative comments in train data. In summary, the main achievements of the current research can be mentioned: creating a weighted comprehensive dictionary in the field of mobile phone opinions to increase the accuracy of opinion analysis, balancing positive and negative opinions to improve the accuracy of opinion analysis, and eliminating the negative effect of overfitting and providing a precise approach to Determining the polarity of users' opinions about mobile phones using machine learning and recurrent deep learning algorithms. This new method is presented on mobile phone products from the Digikala site and Senti-Pers data. The result is performed with Naive Bayesian, Support Vector Machine, Stochastic Gradient Descent, Logistic Regression, Random Forest, and deep learning methods such as Convolutional Neural Network and Long Short-Term Memory based on parameters such as Accuracy, Precision, Retrieval, and F-Measure. The proposed method increases accuracy on Digikala, with NB between 10% and 34% and SVM between 5% and 24%, SGD between 7% and 38%, LR between 5% to 38%, and RF between 4% Up to 22% and CNN by 4%. The results show an accuracy increment on Senti-Pers, with NB between 12% and 46% and SVM between 5% and 46%, SGD between 5% and 35%, LR between 6% to 46%, and RF between 4% Up to 46%.

With the significant growth of social media, individuals and organizations are increasingly using public opinion in these media to make their own decisions. The purpose of Sentiment Analysis is to automatically extract peoplechr('39')s emotions from these social networks. Social networks related to financial markets, including stock markets, have recently attracted the attention of many individuals and organizations. People on these social networks share their opinions and ideas about each share in the form of a post or tweet. In fact, sentiment analysis in this area is measuring peoplechr('39')s attitudes toward each share. One of the basic approaches in automatic analysis of emotions is lexicon-based methods. Most conventional lexicon is manually extracted, which is a very difficult and costly process. In this article, a new method for extracting a lexicon automatically in the field of stock social networks is proposed. A special feature of these networks is the availability of price information per share. Taking into account the price information of the share on the day of tweeting for that share, we extracted lexicon to improve the quality of opinion mining in these social networks. To evaluate the lexicon produced using the proposed method, we compared it with the Persian version of the SentiStrength lexicon, which is designed for general purpose. Experimental results show a 20% improvement in accuracy compared to the use of general lexicon.

In the Corona crisis, we face a wide range of thoughts, feelings, attitudes, and behaviors on social media. This data contains valuable information for responding to the crisis by the people and administrators. The goal of this study is to identify the characteristics of messages that lead to different emotional polarities. This study aims to investigate the information posted by Twitter, Instagram, and Telegram users and news related to the COVID-19 pandemic in Iran. The data extracted from social networks are focused on the period of January 21, to April 29, 2020, which were shared in Iran and in Persian. It should be noted that the data set and their labels were published by the Cognitive Sciences and Technologies Council (CSTC) in Iran. In this work, the content of each post was pre-processed. Pre-processing was performed by removing stop words, normalizing the words, tokenizing, and stemming. The emotion labels were based on plutchik’s model and included joy, trust, fear, surprise, sadness, anticipation, anger, disgust, stress, and other emotions. In this study, clustering algorithms were used to analyze social media posts. We applied a two-stage clustering method. The proposed clustering algorithm was a combination of self-organized neural network and K-means algorithms. According to our proposed algorithm, the data were clustered through SOM at first, the results of which provided the initial cluster centers for the K-means algorithm. Implementations were built in Python version 3.7 and MATLAB R2015a. Hazm Tools was used for pre-processing data, and clustering was done in MATLAB. The Davies-Bouldin clustering evaluation was applied to find the optimal number of clusters. This measure was calculated for the number of clusters in the range of 2-50 in the two-stage clustering method. The results showed that the optimal number of clusters was ten. Analysis of the results showed that posts related to health and culture with negative polarity led to negative emotions such as fear, hatred, sadness, and anger. Messages about people's emotional and improper functioning have led to feelings of sadness, fear, and stress, and reduced hope in society. The results revealed a strong correlation between anger and disgust. Also, a positive correlation between fear, stress, and sadness was observed. In order to reduce the negative feelings and to create a sense of trust in the authorities, we suggest clarifying about the corona pandemic

Today, the Internet, especially social networks such as Twitter, Facebook, and Telegram, has become a platform for exchanging ideas and sharing user opinions. Sentiment analysis based on user opinions in these networks can help explain and predict social phenomena and find suitable products or services for individuals, companies, and organizations. So far, a lot of research has been done on social media data in English; But limited research has been done for the Persian language. In this paper, a Sentiment analysis system on Persian Telegram data is proposed. For this purpose, several feature extraction methods including Countvectorizer, TF-IDF, and word embedding matrix have been studied to represent textual data numerically. Then, to classify the data, different classical machine learning methods including support vector machine, decision tree, K-nearest neighbor, Naïve Bayes, and logistic regression, the combination of classical methods as well as deep learning methods including deep neural network (DNN), convolutional neural network (CNN), long short-term memory network and bidirectional long short-term memory network has been investigated. Finally, the evaluation and analysis of the results on the data collected from Persian Telegram shows that the best performance has been obtained by word embedding and bidirectional long short-term memory network with an accuracy of 90.67%, precision of 90.01%, recall of 89.54% and F1 of 89.77%.

Today, due to the large volume of opinions published by people in cyberspace, sentiment analysis plays a key role in extracting information. One of the new techniques based on studies has been done to determine the exact polarity of the sentence in sentiment analysis is deep learning algorithms. In this research, two deep learning algorithms, namely RNN and LSTM, has been used to determine sentence polarity in order to achieve more accurate results. Moreover, in the proposed technique, pre-trained word embedding algorithm, namely Wordtovec, was used to determine the semantic relationships between words to increase the accuracy of the proposed method. The proposed method was evaluated on two data sets; airline-tweet and IMDB. The evaluation results show that on the airline-tweet dataset, the proposed method has an accuracy of 0.78 and accuracy of 0.84 on the IMDB data set.

With the explosive growth of social media such as Twitter and Instagram, reviews on e-commerce websites, and comments on news websites, individuals and organizations are increasingly using analyzing opinions in these media for their decision-making and designing strategies. Sentiment analysis is one of the techniques used to analyze users' opinions in recent years. The Persian language has specific features and thereby requires unique methods and models to be adopted for sentiment analysis, which are different from those in English and other languages. This paper identifies the characteristics and limitations of the Persian language. Sentiment analysis in each language has specified prerequisites; hence, the direct use of methods, tools, and resources developed for the English language in Persian has its limitations. The present study aims to investigate and compare previous sentiment analysis studies on Persian texts and describe views presented in articles published in the last decade. First, the sentiment analysis levels, approaches, and tasks are described. Then, a detailed survey of the applied sentiment analysis methods used for Persian texts is presented, and previous works in this field are discussed. The advantages and disadvantages of each proposed method are demonstrated. Moreover, the publicly available sentiment analysis resources of Persian texts are studied, and the characteristics and differences of each are highlighted. As a result, according to the recent development of the sentiment analysis field, some issues and challenges not being addressed in Persian texts are listed, and some guidelines are provided for future research on Persian texts. Future requirements of Persian text for improving the sentiment analysis system are detailed.

People's opinions about a specific concept are considered as one of the most important textual data that are available on the web. However, finding and monitoring web pages containing these comments and extracting valuable information from them is very difficult. In this regard, developing automatic sentiment analysis systems that can extract opinions and express their intellectual process has attracted considerable attention in recent years. Sentiment analysis is considered as one of the most active research areas in the field of natural language processing which tries to classify a piece of text containing opinions based on its polarity and determine whether an expressed opinion about a specific topic, event or product is positive or negative. Since about a decade ago, many studies have been carried out to investigate the effects of traditional classification models, such as Support Vector Machine (SVM), Naïve Bayes, Logistic Regression, etc. in the task of sentiment analysis. Although machine learning models have achieved great success in this filed, they are still confronted with some limitations, notably manual feature engineering requirements. In other words, the classification performance of machine learning models is highly dependent on the extracted features and they play an important role in obtaining higher classification accuracy. To deal with these problems, deep learning models have been extensively employed as an alternative to traditional machine learning models and have achieved impressive results. It is worth mentioning that despite the remarkable performance of these methods, they are still confronted with some limitations and they are on their first steps of progress. Therefore, the goal of this paper is to propose a combinational deep learning model that can overcome their problems as well as utilizing their benefits. In this regard, an efficient method based on combination of convolutional and recursive neural networks is proposed in this paper that employs a generalized recursive neural network, where an intermediate feature is obtained by combining children's nodes, as an alternative of pooling layer in attention-based convolutional neural network with the aim of capturing long term dependencies and decreasing the loss of local information. Based on empirical results, the proposed method with the accuracy of 53.92% and 92.89% respectively on SST1 and SST2 datasets not only outperforms other existing models but also can be trained much faster.