بابک سهرابی

Technical and fundamental analysis are the two principal methods for studying financial markets. However, access to internet and social media helps investors make better decisions. Social media has turned into a source of information for investors. Surowiecki (2005) found social media can predict better than individuals, known as the Wisdom of the Crowd. In this study, we tried to evaluate the wisdom of the crowd’s potential to improve stock price prediction accuracy. So, we developed a prediction model by Long Short-Term Memory based on the wisdom of the crowd. Persian users' opinions on Tehran Stock Exchange stocks were gathered for 8 months and classified as buying, sell, or neutral. During the research period, people mentioned 823 stocks and 52 stocks, which had over 100 recommendations, were chosen. Prediction model accuracy was increased for 19 stocks. While, for 33 stocks were not more accurate with the wisdom of the crowds and social media features. It is important to note that investors apply critical thinking. The wisdom of the crowd can be one input to the decision-making process, along with other related factors. The wisdom of the crowd provides an opportunity to access vast and diverse information. Getting opinions from various people can provide valuable insights into economics and investment preferences. The wisdom of the crowd can help reveal the flow of money. The combination of the wisdom of the crowd, fundamental, and technical analysis can be a useful tool for traders in detecting capital flow and profitable opportunities.

Fire insurance is a type of insurance that provides financial protection against property damage caused by events such as fire, theft, and weather-related damage. The use of modern analytics methods in analyzing policies and predicting potential losses is of great interest to insurance companies and those involved in property insurance services. Claim prediction is a crucial measure for predicting future losses in insurance companies, particularly in property insurance, where it helps evaluate the Probable Maximum Loss (PML) based on risk theory.

This study focuses on developing claim prediction models for occurrence probability, severity, and time by creating a dataset, training various algorithms, and comparing their performance. Exploratory Data Analysis (EDA) is conducted to select relevant features, resulting in the selection of 44 fields from insurance policy and claim information. Recursive Field Elimination (RFE) is used to reduce the dataset dimensions, and informative fields are selected for each prediction model. The dataset consists of over 780,000 policy records and approximately 70,000 loss payments from the Iran Insurance Company’s actual fire application database spanning 10 years (2011-2021). Linear regression, random forest regression (RFR), support vector regression (SVR), and deep neural network algorithms are implemented for each prediction model. The accuracy of the algorithms is evaluated using mean squared error (MSE) and mean absolute error (MAE) values.

The results of the prediction models show that the deep multi-layer perception (MLP) algorithm performs the best. After hyperparameter tuning and multiple runs, the final MSE values are determined as 0.117 for occurrence probability prediction, 0.042 for loss severity prediction, and 0.106 for claim time prediction. The comparison of the innovative model results with test data demonstrates that intelligent models provide more accurate predictions. Accurate prediction is highly valuable for insurance companies as it allows them to mitigate financial losses. The use of deep learning in loss time prediction, in addition to severity and probability prediction, is a significant innovation in this research.

Machine learning techniques, such as deep learning, can help insurance companies optimize their services with higher accuracy, strengthen risk management practices, and provide tools for better decision-making. The application of deep learning in loss prediction can replace complex and inaccurate manual processes in insurance, leading to advancements in risk management, reinsurance management, and improvement of fire insurance pricing.

Predicting students’ performance is important for their parents and their teachers. In recent years, learning analytics has been used to evaluate educational data and factors affecting academic performance. Numerous factors, including individual, family, social and environmental characteristics affect this issue. One of the most important individual factors is personality, which we will examine the impact of this factor on academic performance. For this purpose, we analyze the data of a school students in District One of Tehran. Researches in this field has focused on the correlation of different dimensions, but the main purpose of this study is predicting student performance in order to identify students at risk of academic failure, which with the knowledge of the family to improve They take action. The methodology used is CRISP-DM. The Auto ML data mining technique was used for analysis. According to the Accuracy criterion, the classification is more accurate than the artificial neural network method. According to the findings of this study, the conscientious dimension had the greatest effect and the neurotic dimension had the least effect on predicting students' performance.

Mobile applications (mobile apps) are expanding rapidly in the age of modern economics. At the same time, a new paradigm has been formed in the field of e-commerce called social commerce which depends significantly on the platform of mobile apps. The rapid development and growth of mobile computing, smartphones, and Web 2.0 technology have facilitated social commerce. This study seeks to find components related to the proposed business model of Osterwalder and Pigneur in mobile social commerce apps using text mining (k-means clustering algorithm) of previous studies. To collect the body of text mining, abstracts and keywords of 2913 articles on mobile app, social commerce and business model were collected from Scopus repository, and after conducting the pre-processing steps, these articles were clustered into seven clusters. Later by analyzing the articles of each cluster and identifying their subject, a mapping of these topics was created with six components of the Osterwalder business model. These six components included key activities, key resources, key partnerships, value propositions, channels, and customer relationships. Finally, suggestions are made for conducting research on the other three missing components of the business model, including customer segmentation, revenue streams, and cost structure.

Given the importance of business intelligence, organizations need tools to evaluate their capabilities in this area that can help them not only in evaluating but also in planning the upgrade path and comparing the level of capabilities at different times. Maturity models are very useful tools to solve this problem. In the path of assessing the level of maturity, a picture of the status of the organization according to the desired indicators is obtained. To this end, several studies have been conducted on the development of business intelligence maturity models and several organizations have taken steps to develop these models experimentally. In the present study, with a systematic literature review in this field, maturity models related to the business intelligence have been extracted and then the theoretical foundations of the model, development methodology and key process areas of the models have been reviewed. This study helps an organization to benefit from one or a combination of the introduced models according to the complexities of their industry and, if they need to develop their own model, it helps them to recognize the essential aspects in developing the business intelligence maturity model.

As people use social networking sites (SNS) more than ever before, disclosing personal information continues to be an issue of increasing concern both for practice and research. In spite of existing privacy concerns, people paradoxically continue to disclose personal information. Information Systems (IS) literature has provided partial explanations for this paradox. However, recent studies have recommended the consideration of spontaneous privacy-related behaviors. The emerging research on IT identity (ITID) – the extent to which an individual views use of an IT as integral to his or her sense of self – has opened a new window on better explaining IT use behaviors. This study aims to investigate the role of ITID in self-disclosure behavior of SNS users. To meet this end, a survey was administered among 467 students at University of Tehran who were also Instagram users. The results of this research, shows that ITID is positively associated with self-disclosure behavior on SNS. Furthermore, it also shows that ITID is indirectly associated with self-disclosure behavior through the mediating constructs of trust, perceived benefits and risks. This study contributes to the research by providing a better explanation of privacy paradox phenomenon and considering the role of ITID in predicting privacy-related behaviors.

Theories of human basic psychological needs have been always one of the researchers’ answers to human behaviors. Nowadays, application of existing theories of human basic needs in other domains is being more trended rather than emergence of a new theory; However, lack of comprehensiveness in reviewing and analyzing of these theories has always been a fundamental gap in past research.

The present study attempts to collect theories of basic psychological needs in first step and then to analyze them with a metatheoretical approach.

In this study, a systematic review method has been used to collect theories. The statistical population of the study is all related Persian and English researches that have been published in valid scientific databases without time limit. Out of 1152 reviewed studies, 29 valid theories were finally extracted. Then, based on previous studies, the three variables "theory structure", "level of theory analysis" and "provided categories" were used as the basis of meta-theory analysis.

Most of human basic needs theories follow the structure of independent set of needs, so far, the three needs of "hedonism", "survival" and "belonging" have been considered as root needs in three different theories and the hierarchical model has not been repeated in any other theory but Maslow’s. Four theories believe that there are connections between the mentioned components. The level of "psychological needs" analysis is a common feature of all theories, and finally, less than one-third of theories have provided categorization.

Each theory of psychological needs has its own unique structure. Applying these theories to solve various problems inside and outside the field of psychology requires understanding the structural similarities and differences of these theories and the presented needs in them

First, this study aims to identify and review the primary studies in which user psychological needs have been applied to solve problems related to the field of Information Technology; then, it tries to provide a suitable framework for researchers and designers of IT products by classifying these studies and investigating the contexts of user needs application.

Having a qualitative approach, the research carried out a Systematic Mapping Study (SMS) based on the 5-step framework presented by Petersen et al. (2008). In total, 1152 research with full access were identified without any time limit, by searching valid domestic and foreign scientific databases. Finally, a group of 45 studies was selected through selection criteria. Then, the selected researches were classified based on the obtained criteria and were analyzed using quantitative content analysis and descriptive statistics.

In the last two decades, the application of user psychological needs for solving problems related to a wide range of IT products has grown increasingly in the form of using well-known theories or exploiting the components of needs (without referring to a specific theory) or as a general concept. The review of primary studies shows three thematic contexts for applying psychological needs: 1) user experience design 2) analysis of product quality aspects and 3) analysis of user behavior.

The review of the literature background of these three contexts and mapping them with the classification criteria of selected researches (time, type of product, application of needs, and methodology) has clarified the boundaries and characteristics of these three thematic contexts as a mind map for researchers. Finally, by analyzing these criteria, especially the application of needs in the field of IT, suggestions are presented for future studies.

The growing population density in cities and the need for infrastructure services to meet the demands of citizens on the one hand and the increasing development of digital technologies on the other hand, have led governments to form smart cities. Smart cities employ the capabilities of emerging technologies such as the Internet of Things and Big Data to collect and analyze smart devices’ data for improving infrastructure and enhancing the quality of public services. These issues lead planners to a huge amount of financial investment and innovation in business models. The smart city encompasses a variety of stakeholder groups and IoT creates novel business opportunities through collecting and analyzing the data of sensors and smart devices. In this regard, identifying effective indicators for designing a business model is needed to ensure value creation. The purpose of this research is to identify and classifying the main indicators for designing business models of IoT Big Data projects in the smart city. For fulfilling this purpose, the meta-synthesis methodology is employed. Among the 212 articles identified, 48 met all inclusion criteria and were reviewed in-depth. After content analysis, a conceptual model was designed and 21 Indicators were extracted based on the structure of the conceptual model. These indicators are classified into five categories: value creation drives, value creation nodes, value exchange, value capture, and environmental drivers.

Today, social networks are fast and dynamic communication intermediaries that are a vital business tool. This study aims at examining the views of those involved with Facebook stocks so that we can summarize their views to predict the general behavior of this stock and collectively consider possible Facebook stock price movements, and create a more accurate pattern compared to previous patterns. In this study, we have analyzed two statistical samples, the first being a large dataset containing a variety of tweets with an emotional tag. That is, it needed a set that had already been extracted from each individual tweet by a trusted human or machine. Consequently, we have collected posts on Facebook in an eighty-day period. In this study, we used a tagged dataset using Pythonchr('39')s programming language and vector-to-word algorithm. The research results show that, we need stock change information, machine learning and sentiment analysis, and on paper we conclude that positive news about a company excites people to have positive opinions about it which in turn results in people encouraging each other to buy and hold stocks. Meanwhile, the opposite trend is also true, but everything will not always be easy and clear, and it is in areas of high complexity and mental uncertainty that the art of using the three elements mentioned above is evident.

Despite abundant research on data quality, no research has so far been conducted which can provide a comprehensive view of data quality methodologies. In the present study, 3909 articles and related researches in the period before 2020 were selected from Web of Science (WOS) and Scopus citation indexes, from among which 27 articles were finally evaluated in line with the research goals, using meta-synthesis method and inclusion criteria. In this regard, while applying the system view and using the open coding method, the related codes to the three main categories of the systemic approach (input, process and output) were extracted. The similar concepts were categorized in sub-codes and then the sub-codes in main codes. The main inputs included the context and status of organization, data and information resources, and data quality dimensions. Steps of data quality methodologies were also classified into three main stages: state reconstruction, measurement/ evaluation, and improvement. In addition, data quality outputs fell into six general categories: list of activities and the related techniques for data quality improvement, controlled or redesigned processes, measured or improved flows and databases, data quality status results, revised data quality policies or rules, and costs and benefits. The results of this study can provide an appropriate instrument for identifying the existing data quality methodologies as well as evaluating the strengths and weaknesses of data quality methodologies.

Prospective sales policies are one of the essential components of short- and medium-term planning in any business. The correct and accurate formulation of sales policies can play an effective role in managing cash flows and allocating resources. In general, the above statement indicates the fact that in todaychr('39')s competitive world, customer satisfaction and increased market share is vital, estimating the issues about customer buying behavior and decision making is the main theme of any organization that this can be improved by using advanced prospective analysis in the field of sales policy. The purpose of this study is to provide a model for customer clustering, extract the product portfolio of each cluster and allocate the appropriate sales policies for them. Finally, the results were confirmed by experts. Apart from current customers and with the entrance of new customers, using clustering algorithms, the appropriate policies for different categories of these customers are provided to improve their loyalties.

With the advent of digital marketing and the subsequent emergence of social networks such as Facebook and Instagram, as well as the emergence of entities called influencers on these networks, numerous subcategories have arisen to optimize marketing activities with the purpose of having a larger, more effective, more targeted audience aiming at lowering the cost of advertising for businesses and obtaining greater efficiency. Influencer marketing is a branch of marketing that identifies and focuses on a specific person or a particular style of society and then observes potential audiences to lead other marketerschr('39') activities such as defining methods and markets, selecting the right target influencers, how to properly convey the message and attract the target audience in order to reach more efficiency and increase in the value of brands, businesses and products / services. The purpose of this study was to present a decision making model for selecting the most effective influencer(s) out of the existing influencer community in the  case study, Instagram social network, for the product / service being marketed. The criteria for identifying influencers in the present study were obtained by collecting those criteria that were studied sporadically in other studies previously. The data collection tool was a standard Likert 5point scale questionnaire in which these criteria were purposefully examined through distribution among100 experts in the relevant areas of the research subject, and were analyzed through Fuzzy Delphi Method.
Content validity was used to verify its validity and Cronbachchr('39')s alpha coefficient was used to measure the reliability of the questionnaire. The reliability of the questionnaire was higher than 0.8 which is scientifically accepted.
The weights of the final criteria were then determined for each of the five proposed products/services by SWARA Method. Finally, with those measurements, each criteria was individually assessed for 14 persons out of the community Instagram influencers using Multi-Criteria Decision Making (MCDM). The analysis showed a positive and significant relationship between the selected influencers and the proposed product / service.

The implementation of modern ERP solutions has introduced tremendous opportunities as well as challenges into the realm of intensely competent businesses. The ERP implementation phase is a very costly and time-consuming process. The failure of the implementation may result in the entire business to fail or to become incompetent. This fact along with the complexity of data streams has led the researchers to develop a hierarchical multi-level predictive solution to automatically predict the implementation success of ERP solution. This study exploits the strength and precision of the Adaptive Neuro-Fuzzy Inference System (ANFIS) for predicting the implementation success of ERP solutions before the initiation of the implementation phase. This capability is obtained by training the ANFIS system with a data set containing a large number of ERP implementation efforts that have led to success, failure, or a mid-range implementation. In the initial section of the paper, a brief review of the recent ERP solutions as well as ANFIS architecture and validation procedure is provided. After that, the major factors of ERP implementation success are deeply studied and extracted from the previous literature. The major influential implementation factors in the businesses are titled as Change Orchestration (CO), Implementation Guide (IG), and Requirements Coverage (RC). The factors represent the major elements that guide the implementation project to a final success or to a possible failure if mismanaged. Accordingly, three initial ANFIS models are designed, trained, and validated for the factors. The models are developed by gathering data from 414 SMEs located in the Islamic Republic of Iran during a three-year period. Each model is capable of identifying the weaknesses and predicting the successful implementation of major factors. After this step, a final ANFIS model is developed that integrates the outputs of three initial ANFIS models into a final fuzzy inference system, which predicts the overall success of the ERP implementation project before the initiation phase. This model provides the opportunity of embedding the previous precious experiences into a unified system that can reduce the heavy burden of implementation failure.

The present study aims to provide a precise definition of "user basic psychological needs" in using interactive products and also to extract its elements.

This research uses Meta-Synthesis method to collect and analyze data. The statistical population of the research is Persian and English dissertations and articles related to the subject, which have been published in reputable databases and scientific research journals in the country and abroad without any time limit. 45 research met the criteria and were selected to enter the Meta-Synthesis method.

The present study distinguished concepts of "human basic psychological needs" and "user basic psychological needs" and define them at first step and subsequently extracts and defines 37 basic psychological needs at the second step.

Originality: 

Application of human need theories was always limited to a particular pervasive theory, while performing a meta-study has potential capacity for providing more opportunities to generate new ideas related to design and development of interactive products. The results of this study facilitate a deeper understanding of “user psychological needs” concept to design interactive products. The psychological needs presented in this research can be considered as the starting point for the design of interactive products while this new approach can provide a great capacity to create novel and creative ideas.

One key factor in the formation of organizational ERP systems is the requirement of integration at the organization's internal and external levels to survive in competitive markets. These systems have gained a lot of popularity not only by increasing the pace and accuracy of registering the organizational information but also by providing a quick reporting infrastructure. Registration, storing, and recovery of integrated and reliable information throughout the organization is another feature that has affected the penetration of ERP systems in organizations. However, the argument about the high cost of purchasing and implementing such systems between financial and IT departments have always been a challenge in the way of ERP expansion; Therefore, in such a case, it seems necessary to provide evidence of the efficiency or inefficiency of them in the form of an analytical model with a predictive approach and through quantitative indicators to resolve these contradictions. It should be considered that if a clear vision, accurate and quantitative information based on the performance indicators of the organization is given to the decision-makers, the disagreement in such issues will be meaningless. Now, the question is that what tool can provide such valuable information? Predictive models depict the probable future, given the current terms and variables, so that they can solve the issue around using the ERP systems. The present study has extracted the raw, reliable, and not manipulated quantitative data from the ERP system's database and has designed a quantitative predictive analytic model by them to provide clear and accurate answers to existing questions based on quantitative performance indicators. An approach that has not been seen before.

One of today's major research trends in the field of information systems is the discovery of implicit knowledge hidden in dataset that is currently being produced at high speed, large volumes and with a wide variety of formats. Data with such features is called big data. Extracting, processing, and visualizing the huge amount of data, today has become one of the concerns of data science scholars. The impact of big data on information analysis can be traced to four different parts. The first part is data extraction and processing, the second part is data analysis, the third part is data storage, and finally the visualization of the data. In the field of big data processing, in various studies, different categories have been presented. For example, in the studies of Hashim et al., big data processing is divided into two categories. These two types are: batch and real time. These two categories of processing, which nowadays are standard in any comprehensive big data solution, also have been introduced in Abawajy studies: batch processing is related to offline processing, and real-time processing is usually used to analyze the streaming data without any need to storage of data on disk. As data flows from various sources, the data is analyzed and processed real time, for immediate insight. As today's world is rapidly changing and survival in today's competitive world requires instant decision-making based on flows of data, streaming data analysis is becoming increasingly important. On the other hand, one of the great valuable sources of streaming data is the data generated by social networks’ users such as Twitter. Social networks data sources are very rich sources for analysis as they come from the opinions and opinions of their users. As discussed earlier, and since previous studies such as Flash's studies have focused more on batch analysis (offline data), this study has attempted to investigate a variety of tools and infrastructures related to big streaming data, and finally design a real-time dashboard based on Twitter social network streaming data. The following article addresses two research questions: 1) How to design and implement a real-time dashboard based on social networks data? 2) Which different configurations are best suited for real-time dashboard analysis and visualization? In other words, the purpose of this article is to provide a solution for extracting and visualizing Twitter's social network streaming data by deleting databases, as an examples of big data real time analysis. In this research, we used Twitter streaming data as an input, Apache Storm as a processing platform and D3.js as a visualization tool. Finally, the designed dashboard was evaluated using Design of Experiment method and other statistical tests in various types of Apache Storm configurations and eventually it was proved that the dashboard is real time with an average response time for 1 minute and 30 seconds.

Despite the widespread effects of cyberspace on various aspects of social life, especially in the commercial and economic spheres, due to the novelty of this area, no systematic framework has been provided to explain the value network in cyberspace. This study aims to provide a framework for explaining the value network of services in cyberspace. So, throught the systematic reviewing of prior studies using framework analysis approach, actors of cyberservices value network were identified. For this purpose, the main themes were extracted using the Van Manen interpretive approach through three phses of Holistic, Selective, and Descriptive review of qualitative data. The emergent thems were introduced as the actors of cyberservices value network. based on the identified actors, initial framework was presented. Then, appling the Delphi method, the main drivers of final framework were identified. Once again, with the use of the Delphi method, the position of the components was determined in the final framework. using the combined approach, in this study, it was attempted to surmount the methodological limitations of previous studies, as far as possible, so that, the proposed framework provides a process-oriented and integrated view for cyberservice policymaking aimed at supporting service-oriented businesses.

Providing that data mining has been an effective solution of improving the efficiency and the effectiveness of the retail industry, this industry has been the subject of data mining science due to the nature of its data. In this study, the prediction of customer behavior in the retail industry of Fast Moving Consumer Goods is aimed at increasing the quantity and quality of sales in the study of Golpakhsh Avval Co.
The present study is applied in terms of purpose, using data survey to collect data. The research is based on the CRISP-DM process, which uses the RFMCL clustering model, regression classification and regression techniques as well. Eventually, a collaborative recommendation method has been applied for recommendation.
The result is a forecasting model recommended to the best customers goods that they have not bought on a particular date and to a certain amount, so that, the order-based sale is changed to hot sale method. The final solution involves three sub models of customer clustering, sale forecasting and a recommendation system. The five variables model –with MSE/Range accuracy of 2.24% – is solved for recommendation of sales amount.
By implementing the developed recommender system in Golpakhsh Avval Co., the proactive production master plan would be possible to execute. In addition, the marketing approach could be transformed from visiting sales to hot sales in the future which provides considerable savings in shipping and personnel costs.

Customer lifetime value (CLV) is an invaluable metric which plays a pivotal role in assessing the future worth of the customers and the profitability of them. To elaborate upon, CLV is an index so as to evaluate the potential as well as the practical worth of a wide variety of customers. So, it seems obvious that estimation of this metric in different cooperation, especially IT ones, can cause the organizations to identify the behaving trend of their customers so that the organizations can forecast their future purchase as well as the customers’ loyalty to their cooperation. Therefore, in this paper, we present a model in order to estimate the CLV in an IT cooperation. Hence, in the first step, we explain the concept of CLV metric, and its role in today’s customer analysis. Then, the next step has to do with presenting the RFM method and its parameters for assessing the CLV index. Our proposed case study is included 182 data of customers in an IT cooperation, which we used ordered logistic regression so as to analyze. In the experimental results section, our proposed method applying to this specific cooperation data demonstrates a better performance both in accuracy and precision in comparison with the popular methods.

Nowadays, productive or service organizations consider the customer's satisfaction as a significant criterion to assess their work quality. Since almost all the organizations need to compete in different areas including services, giving a high quality service is so important to achieve a permanent competitive advantage. In order to survive in competitive markets, organizations and companies have to provide high quality customer services. The results of many researches illustrate that the service quality is the necessity for customer's satisfaction. Though, a lot of customer oriented companies have problem in recognizing and evaluating the customers' preferences and they often misunderstand the customers' demands. Because providing a high quality service requires understanding the relationship between the demands of customers and the quality of services provided by company. The organizations and companies which give software service also include this rule. The purpose of this research is to present a model to predict the customer's satisfaction from the provided services , also determine the influence of each effective variable on customer's satisfaction, as well be informed of customer's satisfaction level from provided service by the mentioned company. The proposed study used predictive algorithms such as Regression and Classification on data by Rapid Miner. Finally the method with the highest accuracy and minimum error were selected. In addition, in order to determine the most effective variables in customer's satisfaction, the weighting method was used. In order to make decisions and improve customer satisfaction, the results will be available for managers.

Human resource management has seen a significant change by emergent of information systems. The purpose of this paper is finding the relations of words, recognizing the most frequent words, also study the trends of information systems in the field of human resources management through text mining approach. Among text analytic methods, words-weighting, words-correlation, text clustering algorithms, have been applied to the dataset of high-ranked information systems journals and our data set is obtained from Scopus database between the year of 2013 and 2017, then, this study utilizes text mining algorithm on the titles, abstract and keywords of the papers tries to find the relations of the words and general trends of information systems in the field of human resources management. The results present practical information which can help students and scholars to understand a useful overview and provides them with the opportunity to focus on new topics of new trends of information systems in the field human resources. Some results of this paper are: the importance of knowledge management and especially knowledge-sharing process, virtual teams, use of human resources information systems, and also the key role of social networks in organizations.

Detection of emergence research areas is an important issue for science and technology policy makers and researchers. Despite the importance of this subject, there is no comprehensive study to define the emergence and metrics that needed for its detection. In this study, we selected 1833 papers from web of science (WOS) that are published between 1970 and 2017. Then we used meta-synthesis method on 68 finalized papers that are completely related to the purpose of this research and extracted several metrics. Generalizability, innovation and penetration are the extracted construct. We also extracted 9 concept and 29 codes related to each metric. We also come up with a definition for emergence research area which is "the emergence research area is highly important and novel area that born very fast and have great impact on related research areas and also can attract researchers and other influencers of science".

In recent years, the growth of social networks and, consequently, the increasing content of these networks have led people to use others’ opinions to make decisions for the purchase and use of products, services or even political choices. Given the fact that users' comments are textual and their reading and summarizing is timely and difficult, the automation of the extraction of opinions and sentiments of users' comments is one of the suggested solutions for online sales sites to provide more efficient services to customers for better decision making. Sentiment analysis or opinion mining is a process where people's opinions, feelings and attitudes are extracted in relation to a particular subject and are recognized as a branch of the text mining. The results of sentiment analysis can be used in recommender systems to provide more effective shopping suggestions. Information derived from the opinion mining can be used in a variety of fields such as libraries for better choices and purchases based on the users' real opinions. In this research, a system for automatically categorizing the sentiments expressed in the opinions of the buyers of the Amazon book website is presented. The system is designed using ensemble voting models to analyze the sentiment of Amazon users' comments. For all analyses, Python text mining packages are used. In ensemble method two methods are used: majority voting and weight-based voting. In the weighting method, a greater weight is assigned to a classifier by higher accuracy. By comparing the performance of the results, the weighting model is chosen as the final model for making the sentiment analysis. Results show that the proposed system can automatically classify positive and negative comments with an accuracy of over 80%.