Sentiment classification of opinions is a field of Natural Language Processing which has been considered in recent years by researchers due to popularity of Internet stores and the possibility of expressing opinions about sold goods or services. To train classifier models, we need labeled datasets, but as there are not rich labeled samples and as labeling is a difficult and time-consuming process, we must employ labeled samples of other domains. In this article, a new method for binary classification of opinions is proposed based on multi-domain transfer Learning. The proposed method tries to adapt different domains by using Structural Correspondence Learning; and based on repetitive procedure of the boosting algorithm, a weight is assigned to classified samples of different domains and the class of each opinion is specified by merging these classifiers. Weighting the dataset samples to boost the process of classification based on the Adaboost algorithm and combining it with the Structural Corresponding Learning is the most important innovation of the current research. The Amazon dataset of four different domains, each one containing 1000 positive and 1000 negative opinions is used for training the proposed model. Accuracy measures of %89. 64, %93. 97, %92. 39 and %90. 17 are obtained for Electronics, DVD, Books and Kitchen domains, respectively. It illustrates that the proposed method is very effective compared with the similar methods.

This article presents a review of selected articles about Structural engineering applications of Machine Learning (ML) in the past few years. It is divided into the following areas: Structural system identification, Structural health monitoring, Structural vibration control, Structural design, and prediction applications. Deep neural network algorithms have been the subject of a large number of articles in civil and Structural engineering. There are, however, other ML algorithms with great potential in civil and Structural engineering that are worth exploring. Four novel supervised ML algorithms developed recently by the senior author and his associates with potential applications in civil/Structural engineering are reviewed in this paper. They are the Enhanced Probabilistic Neural Network (EPNN), the Neural Dynamic Classification (NDC) algorithm, the Finite Element Machine (FEMa), and the Dynamic Ensemble Learning (DEL) algorithm.

To test the hypothesis “does using the Learning strategies guide increase the level of Learning in teachers attending in Correspondence education on work and decrease the needed time to  study reading materials?”, 156 people were chosen to attend in the experiment. They included 92 women teachers and 64 men teachers, who were randomly chosen among registered teachers in one of on service education examinations in region number 16 of Tehran. They were randomly allocated to control and experimental groups. The experimental group was provided with Learning strategies guide to help them with reading the relevant book, while the control group, without using the guide, studied the relevant book. An examination was held for both groups in the same time and date, in which they answered to the same questions, while they were demanded to determine the time they spared to complete their answers. The analyzing results by t test showed that using Learning strategies guide decreases the time spared on reading materials, but does not affect the extent of Learning. Co-variance analysis demonstrated that with an invariable time for reading, Learning strategies guide has improved Learning. This was a significant impact for the group with little or medium time to study, but not such meaningful for the group, who had spared a long time on reading.

The main objective of this study was to investigate the reciprocal relationship between innovation and exports in small and medium-sized enterprises (SME’ s). The statistical population of this research is the SME’ s of West Azarbaijan province. The analyzes of this research are based on a questionnaire derived from the IDEIS project entitled the process of innovation in French’ s small and medium-sized firms, which was changed and adopted in accordance with the conditions of Iran and the existing export barriers. The questionnaire have been completed from September 2016 to April 2017, addressing the managers of small and medium enterprises of West Azarbaijan Province. To this end, the intensity of input and output innovation were calculated using Multiple Correspondence Analysis (MCA) and then the econometric model was estimated using the Generalized Structural Equation Model (GSEM). The results show that the effect of exports on innovation is positive and significant, but on the contrary, the effect of innovation on exports is negative which indicates that the level of innovation of Iranian firms is small. Also, the barriers to exports index has a negative effect on firms' exports. According to the results, the Learning effect of exports on SME’ s is evident. In this regard, the government must support export-oriented measures, such as marketing for new products, as well as finding new export markets, providing export subsidies which will increase exports.

Nowadays the amount of textual information on the web is grown rapidly. The huge textual data needs more accurate classification algorithms. Sentiment analysis is a branch of text classification that is used to classify user opinions in case of market decisions, product evaluations or measuring consumer confidence. With the rise of the production rate of Persian text data in a commercial area, improvement of the efficiency of algorithms in Persian is a must. The structure of the Persian language such as word and sentence structures poses some challenges in this area. Deep Learning algorithms are recently used in NLP and especially sentiment text classification for many dominant languages like Persian. The goal is to improve the performance of classification using deep Learning issues. In this work, the authors proposed a hybrid method by a combination of Structural Correspondence Learning (SCL) and convolutional neural network (CNN). The SCL method selects the most effective pivot features so the adaptation from one domain to similar ones cannot drop the efficiency drastically. The results showed that the proposed hybrid method that is learned from one domain can act efficiently in a similar domain. The result showed that applying a combination of SCL+CNN can improve the result of sentiment classification for two domains more than 10 percent.