درخت حوزه‌های تخصصی

Today, users generate various data increasingly using the Internet when choosing a product or service. This leads to the generation of data about the purchases and services of various consumers. In addition, consumers often leave feedback about the purchase. At the same time, consumers discuss their attitudes about goods and services on social networks, messengers, thematic sites, etc. This leads to the emergence of large volumes of data that contain useful information about various manufacturers of goods and services. Such information can be useful to both ordinary users and large companies. However, it is practically impossible to use this information due to the fact that it is located in different places, that is, it has a raw, unstructured character. At the same time, depending on the target group of users, not the entire data set is needed, but a specific target sample. To solve this problem, it is necessary to have a tool for structuring information arrays and their further analysis depending on the set goal. This can be done with the help of various frameworks that use methods of machine learning and work with data. This work is devoted to elucidating the problem of creating means for evaluating consumer preferences based on the analysis of large volumes of data for its further use by the target audience.  The goal of the development of big data analysis systems is obtaining new, previously unknown information. The methodology of application of algorithms of work with large data sets and methods of machine learning is used, namely the pandas library for operations on a data set and logistic regression for information classification As a result, a system was built that allows the analysis of lexical information, translate it into numerical format and create on this basis the necessary statistical samples. The originality of the work lies in the use of specialized libraries of data processing and machine learning to create data analysis systems. The practical value of the work lies in the possibility of creating data analysis systems built using specialized machine learning libraries.

The unpredictability of the stock market makes it a serious area of study and analysis. With the help of the accumulated information available in the current digital age and the power of high-performance computing machines, there is a great focus on using these capabilities to design algorithms that can learn stock market trends and successfully predict stock prices. The main goal is to create an intelligent system that provides these features for predicting short-term stock price trends to facilitate the investment decision process. To increase the accuracy and productivity of these systems and facilitate the routine of using common-sense knowledge in machine learning systems, developing or enriching knowledge bases and ontology for market modeling will be one of the effective measures in this field. In this research, an attempt has been made to strengthen and enrich the basic ontology created by the authors by using other global ontologies related to the subject of the stock market, and parts of the target space that were not addressed have been added to the ontology. By combining reference ontologies, a level of standardization is also created for the ontology and stability in the representation of concepts and relationships is ensured. In the next step, it has been tried to test the impact of the concepts and relations of the ontology in predicting stock price movements. For this purpose, news in the field of economy is considered as input and a model is created that first filters the textual inputs related to the desired stock symbol and then observes their effect on the price changes of the related stock. After improving the performance and comprehensiveness of the ontology, the study conducted in this report presented a model to measure and prove the effect of the relationships in this ontology on price changes. In practice, according to human limitations and the tools used, this effect was observed and confirmed with a proper level of certainty by checking the economic news.

Finding a brain tumor yourself by a human in this day and age by looking through a large quantity of magnetic-resonance-imaging (MRI) images is a procedure that is both exceedingly time consuming and prone to error. It may prevent the patient from receiving the appropriate medical therapy. Again, due to the large number of image datasets involved, completing this work may take a significant amount of time. Because of the striking visual similarity that exists between normal tissue and the cells that comprise brain tumors, the process of segmenting tumour regions can be a challenging endeavor. Therefore, it is absolutely necessary to have a system of automatic tumor detection that is extremely accurate. In this paper, we implement a system for automatically detecting and segmenting brain tumors in 2D MRI scans using a convolutional-neural-network (CNN), classical classifiers, and deep-learning (DL). In order to adequately train the algorithm, we have gathered a broad range of MRI pictures featuring a variety of tumour sizes, locations, forms, and image intensities. This research has been double-checked using the support-vector-machine (SVM) classifier and several different activation approaches (softmax, RMSProp, sigmoid). Since "Python" is a quick and efficient programming language, we use "TensorFlow" and "Keras" to develop our proposed solution. In the course of our work, CNN was able to achieve an accuracy of 99.83%, which is superior to the result that has been attained up until this point. Our CNN-based model will assist medical professionals in accurately detecting brain tumors in MRI scans, which will result in a significant rise in the rate at which patients are treated.

This paper provides a comprehensive overview of the evolving Artificial Intelligence (AI) threat to cybersecurity, emphasizing the urgent need for finance leaders and cybersecurity professionals to adapt their strategies and controls to effectively combat AI-powered scams and cyber-attacks. The study delves into the specific ways in which AI is being used maliciously in cybercrime, such as enhanced phishing and Business Email Compromise (BEC) attacks, the creation of synthetic media including deepfakes, targeted attacks, automated attack strategies, and the availability of black-market AI tools on the dark web. Furthermore, it highlights the critical need for enhanced cybersecurity strategies and international cooperation to combat cyber threats effectively. The findings of this study provide valuable insights for finance leaders, cybersecurity professionals, policymakers, and researchers in understanding and addressing the challenges posed by generative AI in the cyber threat landscape.

Purpose: The purpose of this research was to provide a model for choosing the best content for the activity of service guilds.Method: In inferential statistics, the K-S test is used for the normality of research hypotheses. For this purpose, Pearson's correlation coefficient and linear regression tests have been used through SPSS 21 software, and the best content generated using genetic algorithms and forbidden search were introduced.Findings: Analysis of research and implementation results with two collective intelligence algorithms shows that Instagram has a positive and significant effect on all four dimensions and thus leads to the success of the service classes that have used Instagram.Conclusion: In this article, a combination model of genetic algorithm and forbidden search algorithm was chosen for users so that the best content, which of course does not contain malicious ads and cookies, etc., is introduced for the continuation of the service industry.

Purpose: The development of e-commerce and online shopping has given rise to emerging concepts of consumer behavior, including webrooming. Due to the novelty of the concept of webrooming in this study, an attempt has been made to provide a conceptual framework to explain this behavior and the factors affecting its formation.Method: In this regard, a field survey study was conducted by distributing questionnairy among a sample consisting of 384 gold and jewelry customers in Tehran. The questionnaires consisting of 9 dimensions and 38 items were distributed among the members of the statistical sample after ensuring reliability and validity. Data analysis along with partial least squares technique and Smart PLS software were used.Findings: According to the results, the benefits of online and offline channels have a significant impact on webrooming attitude; It was also discovered that attitude, perceived risk, anticipated regret, subjective norms and behavioral control have a significant impact on behavioral inclination and webrooming.Conclusion: The results of goodness of fit showed that the proposed model in this research has a good validity and fit. Given that webrooming has a negative impact on online sales; the results help online retailers mitigate this phenomenon by targeting webrooming antecedents.

Purpose: This research aims to identify the factors affecting social network marketing based on gaining a competitive advantage and designing a model related to the communication between them.Method: This research is applied in its purpose, and conducted using a mixed approach (qualitative and quantitative). In the qualitative phase, first by reviewing the literature in the field of social network marketing and using the meta-combination method, the factors affecting it were identified and divided into three categories. subsequently, the relationships between these factors were determined and analytically analyzed using the interpretative structural modeling approach. In the modeling section, a questionnaire was distributed among experts selected through snowball sampling.Findings: The results of this research led to the classification of factors affecting social network marketing based on gaining competitive advantage and designing a model of these factors. In this model, the categories of organizational and structural resources (responsiveness to customers, service quality), marketing (attracting more customers, efficiency), and competitive advantage based on social media (branding, profitability), indicate the factors and the way of communication and interaction of these factors.Conclusion: Finally, the interpretation of the model, analysis of its levels, and the relationships among dimensions were discussed and solutions were provided in this regard.

Cyberbullying involves using hurtful or offensive language that goes against basic rules of respect and politeness. It harms the online environment and can negatively affect people by causing harassment, discrimination, or emotional pain. To combat this, it is crucial to develop automated methods for detecting and preventing the dissemination of such content. Deep learning, a branch of artificial intelligence, leverages neural networks to learn from data and perform complex tasks, effectively capturing semantic and grammatical nuances to differentiate between abusive and non-abusive language. This survey paper reviews current techniques and advancements in deep learning-based approaches for detecting cyberbullying content on online platforms, aiming to provide a comprehensive understanding of existing methodologies and identify potential avenues for future research to mitigate the spread and impact of such behaviors on the internet.

With the advent of user-generated text information on the Internet, text sentiment analysis plays an essential role in online business transactions. The expression of feelings and opinions depends on the domains, which have different distributions. In addition, each of these domains or so-called product groups has its vocabulary and peculiarities that make analysis difficult. Therefore, different methods and approaches have been developed in this area. However, most of the analysis involved a single-domain and few studies on cross-domain mood classification using deep neural networks have been performed. The aim of this study was therefore to examine the accuracy and transferability of deep learning frameworks for the cross-domain sentiment analysis of customer ratings for different product groups as well as the cross-domain sentiment classification in five categories “very positive”, “positive”, “neutral”, “negative” and “very negative”. Labels were extracted and weighted using the Long Short-Term Memory (LSTM) Recurrent Neural Network. In this study, the RNN LSTM network was used to implement a deep transfer learning framework because of its significant results in sentiment analysis. In addition, two different methods of text representation, BOW and CBOW were used. Based on the results, using deep learning models and transferring weights from the source domain to the target domain can be effective in cross-domain sentiment analysis.

The eXtensible Business Reporting Language (XBRL) functions as an independent, open platform that facilitates efficient information transmission over the Internet, improving business information utilization. Despite its widespread adoption and numerous benefits, unresolved assurance issues undermine its effectiveness, revealing a significant research gap. This study explores the complex landscape of XBRL data assurance challenges within the Malaysian Business Reporting System (MBRS). Utilizing a qualitative case study methodology, the research highlights key challenges in XBRL data assurance and presents strategic, innovative solutions. Through semi-structured interviews and document analysis, insights from diverse stakeholders are captured, revealing the development of artificial intelligence-enhanced audit software aimed at improving the quality of XBRL filings in Malaysia. Despite its potential, awareness of this advanced software among preparers remains disappointingly low. This research serves as a valuable resource for practitioners and researchers, offering an in-depth analysis of XBRL data assurance challenges and pioneering solutions, thereby making a significant contribution to this critical field.

Purpose: Despite the widespread diffusion and interest aroused by content marketing, little attention has been paid until this moment to building a framework that presents the main currents and studies of the field. Hence, the main aim of this study was to cover this gap by analyzing bibliographic information as complementary sources and enable a wider understanding and grasp of the content marketing field.Method: For this purpose, a bibliometric study of the publications indexed in Web of Science (WoS) between 1985-2022 was conducted. The search process used in this review was informed by PRISMA guidelines. During the search process, a set of 371 documents (research  and review articles) were obtained. Also, the bibliometrix R-package and VOSviewer software were used for quantitative analysis and visualizing bibliometric networks.Findings: The descriptive statistics showed that content marketing studies have rapidly grown since 2011. The US and Spain are the countries with the most publications of the field. The most prominent journal concerning content marketing research is Brand Journalism (with 11 articles), and the most prolific author is Bull A (with 11 articles).The results of the thematic analysis showed that ‘digital marketing’ and ‘brand storytelling’ are emerging themes and have replaced ‘content marketing’. The co-word analysis of author’s keywords defines 8 clusters: 1) platforms and techniques 2) content marketing concepts, 3) influencer marketing and advertising, 4) digital and social media marketing, 5) brand management and brand storytelling, 6) brand journalism, 7) private and native media, and 8) corporate and public communication.Conclusion: Simultaneously with the development of content creation platforms, these platforms have been welcomed in the field of content marketing. Content preparation has undergone changes in recent years. The style of information content based on news and specialized knowledge has shifted its focus to storytelling and narrative messages from the brand. This paper introduces the main areas of interest and possible gaps. It also contributes to the body of knowledge by providing a comprehensive overview of content marketing literature.

Purpose: This research aimed at presenting the consumers’ compulsive buying pattern through internet advertisements of digital content in Iran's TV shopping industry.Method: Research Methodology was practical in terms of purpose and conducted using mixed method (qualitative-quantitative). The research community was based on the purposeful sampling method, and consisted of ten marketing experts. The research tool was interview. MAXQDA software was used to analyze data through database theory. The statistical population in the quantitative section included TV buyers in Mashhad. Based on Morgan table and random sampling, 384 samples were selected. The research tool was a researcher-made questionnaire, and the Structural Equation Method (SEM) in SmartPLS software was used for data analysis. The validity of the questionnaire was confirmed by using face, content, divergent and convergent validities, and its reliability was also confirmed using Cronbach's alpha. Both of Composite and homogeneous reliability were evaluated.Findings: "appropriate digital marketing mix design for TV sales, digital marketing capabilities, individual demographic characteristics, lifestyle, family " constitute the causal conditions in the consumer’s compulsive buying pattern in the TV shopping. According to the findings, “quick and transient purchase and irrational and emotional purchase” were identified as a central phenomenon. “TV's attractiveness from the audience's point of view, broadcasting policies, sales companies' policies, national TV belief and trust, individual awareness and knowledge about buying products and society's culture” acted as intervening conditions. In the field of buying, “intellectual structures of society and executive structures of society” identified as background conditions. Human strategies and structural and organizational strategies” acted as strategies and “Consumers outcomes; families and society outcomes” were identified as outcomes. According to the results of structural modeling, the relationships of the identified pattern were significant.Conclusion: The issue of compulsive buying is one of the most important and common issues, and buying from TV has fueled this issue, and has become the basis for its expansion and, following that, its negative consequences. In this scientific research, efforts were made to reduce the consequences of this phenomenon. The results of this study showed that although the phenomenon of compulsive purchase from TV is negative, but with proper management, useful results can be obtained from it.

The adoption of E-learning in academic environments, particularly in Iran, has accelerated over the past decades. However, the lack of established guidelines for instructional design seems to have hindered the creation of effective online educational environments. Therefore, this study aimed to conduct a comprehensive qualitative research synthesis (QRS) to identify the criteria for an optimal online learning environment for Iranian university students. The study followed Major and Savin-Baden's three-phase QRS model and included 12 studies with 252 participants and 42 researchers. The synthesis integrated findings from multiple studies to gain insights into experts’ opinions and students’ perceptions, preferences, and experiences within online learning environments. The research identified four overarching themes: targeted learning, effective teaching management, socio-affective engagement, and learner empowerment. Targeted learning focuses on problem-oriented and need-oriented teaching; effective teaching management emphasizes balanced content and time management, clear objectives, and diverse presentation and evaluation methods; socio-affective engagement involves interactive feedback, social presence, and emotional communication; learner empowerment stresses autonomy, agency and active learning, including experiential and discovery learning. Applying these findings seems to offer a genuine contribution, leading to the development of culturally relevant and high-quality E-learning experiences and addressing the challenges posed by the nascent E-learning system in Iran.

For investors, predicting stock market changes has always been attractive and challenging because it helps them accurately identify profits and reduce potential risks. Deep learning-based models, as a subset of machine learning, receive attention in the field of price prediction through the improvement of traditional neural network models. In this paper, we propose a model for predicting stock prices of Tehran Stock Exchange companies using a long-short-term memory (LSTM) deep neural network. The model consists of two LSTM layers, one Dense layer, and two DropOut layers. In this study, using our studies and evaluations, the adjusted stock price with 12 technical index variables was taken as an input for the model. In assessing the model's predictive outcomes, we considered RMSE, MAE, and MAPE as criteria. According to the results, integrating technical indicators increases the model's accuracy in predicting the stock price, with the LSTM model outperforming the RNN model in this task.

This study aims to develop an adoption model tailored for service-oriented organizations and then evaluate its effectiveness within the specific context of Tehran Municipality, Iran's foremost service-oriented institution. Utilizing a mixed-method research approach integrating qualitative and quantitative methodologies, this study delineated the dimensions, categories, and indicators pertinent to the adoption of Electronic Human Resource Management (EHRM) systems in service-oriented organizations. Qualitative methodologies were employed to identify and develop the adoption model, which was subsequently evaluated within Tehran Municipality using a quantitative approach. In the qualitative segment of this study, in-depth interviews were conducted using a snowball sampling technique until theoretical saturation was achieved. For the quantitative phase, a sample of 310 experts affiliated with Tehran Municipality's EHRM system was surveyed. Structural equation modeling and Smart PLS 4.0 software were employed for data analysis. Ultimately, this research extracted five dimensions, 14 categories, and 94 indicators for the proposed adoption model. Notably, experts accorded the highest priority to the technological dimension in the adoption model, with specific emphasis on “adaptive architecture, security and privacy of employees, trialability and reliability, organizational citizenship behavior, organizational dynamic capabilities, digital Leadership Policy and Actions, cloud computing, etc…”, as pivotal factors in EHRM adoption. The organizational dimension assumed the second-highest priority, while the individual dimension was assigned a third-place ranking. Micro and macro-environmental factors followed in subsequent priority order.

Predicting the development of cancer has always been a serious challenge for scientists and medical professionals. The prompt identification and prognosis of a disease is greatly aided by early-stage detection. Researchers have proposed a number of different strategies for early cancer detection. The purpose of this research is to use meta-learning techniques and several different kinds of convolutional-neural-networks(CNN) to create a model that can accurately and quickly categorize breast cancer(BC). There are many different kinds of breast lesions represented in the Breast Ultrasound Images (BUSI) dataset. It is essential for the early diagnosis and treatment of BC to determine if these tumors are benign or malignant. Several cutting-edge methods were included in this study to create the proposed model. These methods included meta-learning ensemble methodology, transfer-learning, and data-augmentation. With the help of meta-learning, the model will be able to swiftly learn from novel data sets. The feature extraction capability of the model can be improved with the help of pre-trained models through a process called transfer learning. In order to have a larger and more varied dataset, we will use data augmentation techniques to produce new training images. The classification accuracy of the model can be enhanced by using meta-ensemble learning techniques to aggregate the results of several CNNs. Ensemble-learning(EL) will be utilized to aggregate the results of various CNN, and a meta-learning strategy will be applied to optimize the learning process. The evaluation results further demonstrate the model's efficacy and precision. Finally, the suggested model's accuracy, precision, recall, and F1-score will be contrasted to those of conventional methods and other current systems.

Leveraging supplementary technology such as Blockchain has the potential to alter the stakeholders involved in a system. Paying attention to stakeholders is one of the main pillars of developing a system. Evidence has shown that Blockchain can solve existing challenges and add new capabilities. These actions will change the stakeholders of PHR. If a value is different for everyone, at the first stage, stakeholders should be identified, and that is our goal in this study. The research adhered to the guidelines outlined in the PRISMA statement. To this end, the study utilized databases including MEDLINE, ScienceDirect, and Google Scholar for English language articles, while the "iranjournals.nlai.ir" database was accessed for Persian language articles. Finally, 35 articles were chosen from searching databases, and six extra articles were selected from reviewing the final articles' references. Stakeholders were categorized into 15 groups. The patient (individual) was identified as the most frequent stakeholder (41 times), and infrastructure providers and the token exchange market were mentioned once each. The usage type is categorized into four groups: direct user interaction, data user, impact user, and financial beneficiaries, comprising six, eight, four, and four stakeholders, respectively. Patients (individuals) use the four groups, and health care providers, policymakers, hospitals, and the government each use two groups. Intelligent contracts are neglected in PHR, which can significantly impact the motivation and creation of incentives for using different stakeholders. The grouping presented here can be used in the preparation of the business model of PHR based on Blockchain. Data has the most usage for stakeholders and strengthens and supports investments in technologies such as Blockchain as an infrastructure for creating data markets, new business models, and creating value.

Purpose: The main purpose of this research is to assess the feasibility of using VSAT satellites in the information services of university libraries.Method: The research method is a survey using the TOPSIS model, which indicates that the optimal method of providing the Internet is the method that has the greatest distance from negative factors and the least distance from positive factors. The opinions of user organizations, i.e. academic libraries and information centers, have been examined to clarify the necessity of using this method as well as its characteristics and advantages compared to other ways of providing the Internet.Findings: The findings show that VSAT satellite internet can have better conditions for providing services compared to other services such as ADSL, optical fiber, Wi-Fi and Wi-MAX. Also, their assessment determined that VSAT satellite internet is currently the best way to provide internet based on the criteria of service, support, cost, trust and quality, and ranks second in criteria such as security, confidentiality and service. In conclusion, the priority of solutions to provide library internet using TOPSIS analysis is: VSAT service; Optical fiber; ADSL service; Wi-Max services and wireless services.Conclusion: The results indicate that the VSAT satellite network, with advantages in the use of Internet services by libraries, plays an important role in improving the quality of these services.