مطالب

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 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.

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.

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.

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.