Minoo Sayyadpour

Ali Nazarizadeh, Touraj Banirostam, Minoo Sayyadpour

Sentiment analysis aims to extract people's emotions and opinion from their comments on the web. It widely used in businesses to detect sentiment in social data, gauge brand reputation, and understand customers. Most of articles in this area have concentrated on the English language whereas there are limited resources for Persian language. In this review paper, recent published articles between 2018 and 2022 in sentiment analysis in Persian Language have been collected and their methods, approach and dataset will be explained and analyzed. Almost all the methods used to solve sentiment analysis are machine learning and deep learning. The purpose of this paper is to examine 40 different approach sentiment analysis in the Persian Language, analysis datasets along with the accuracy of the algorithms applied to them and also review strengths and weaknesses of each. Among all the methods, transformers such as BERT and RNN Neural Networks such as LSTM and Bi-LSTM have achieved higher accuracy in the sentiment analysis. In addition to the methods and approaches, the datasets reviewed are listed between 2018 and 2022 and information about each dataset and its details are provided.

Minoo Sayyadpour, Ali Nazarizadeh

Much unstructured data has been produced with the growth of the Internet and social media. A significant volume of textual data includes users' opinions about products in online stores and social media. By exploring and categorizing them, helpful information can be acquired, including customer satisfaction, user feedback about a particular event, predicting the sale of a specific product, and other similar cases. In this paper, we present an approach for sentiment analysis with a deep learning model and use it to recommend products. A two-channel convolutional neural network model has been used for opinion mining, which has five layers and extracts essential features from the data. We increased the number of comments by applying the SMOTE algorithm to the initial dataset and balanced the data. Then we proceed to cluster the aspects. We also assign a weight to each cluster using tensor decomposition algorithms that improve the recommender system's performance. Our proposed method has reached 91.6% accuracy, significantly improved compared to previous aspect-based approaches.

Minoo Sayyadpour, Nasibe Moghaddamniya, Touraj Banirostam

Leukemia is one of the most common and death-threatening types of cancer that threaten human life. Medical data from some of the patient's critical parameters contain valuable information hidden among these data. On this subject, deep learning can be used to extract this information. In this paper, AutoEncoders have been used to develop valuable features to help the precision of leukemia diagnosis. It has been attempted to get the best activation function and optimizer to use in AutoEncoder and designed the best architecture for this neural network. The proposed architecture is compared with this area's classical machine learning models. Our proposed method performs better than other machine learning in precision and f1-score metrics by more than 11%.