topic modeling

The global cyberspace networks provide individuals with platforms to can interact, exchange ideas, share information, provide social support, conduct business, create artistic media, play games, engage in political discussions, and many more. The term cyberspace has become a conventional means to describe anything associated with the Internet and the diverse Internet culture. In fact, cyberspace is an umbrella term that covers all issues occurring through the interaction of information systems and humans over these networks. Deep evaluation of the scientific articles on the cyberspace domain provides concentrated knowledge and insights about major trends of the field. Text mining tools and techniques enable the practitioners and scholars to discover significant trends in a large set of internationally validated papers. This study utilizes text mining algorithms to extract, validate, and analyze 1860 scientific articles on the cyberspace domain and provides insight over the future scientific directions or cyberspace studies.

In recent years, we have seen an increase in the production of films in a variety of categories and genres. Many of these products contain concepts that are inappropriate for children and adolescents. Hence, parents are concerned that their children may be exposed to these products. As a result, a smart recommendation system that provides appropriate movies based on the user's age range could be a useful tool for parents. Existing movie recommender systems use quantitative factors and metadata that lead to less attention being paid to the content of the movies. This research is motivated by the need to extract movie features using information retrieval methods in order to provide effective suggestions. The goal of this study is to propose a movie recommender system based on topic modeling and text-based age ratings. The proposed method uses latent Dirichlet allocation (LDA) modelling to identify hidden associations between words, document topics, and the levels of expression of each topic in each document. Machine learning models are then used to recommend age-appropriate movies. It has been demonstrated that the proposed method can determine the user's age and recommend movies based on the user's age with 93% accuracy, which is highly satisfactory.

Annually, researchers in various scientific fields publish their research results as technical reports or articles in proceedings or journals. The collocation of this type of data is used by search engines and digital libraries to search and access research publications, which usually retrieve related articles based on the query keywords instead of the article’s subjects. Consequently, accurate classification of scientific articles can increase the quality of users’ searches when seeking a scientific document in databases. The primary purpose of this paper is to provide a classification model to determine the scope of scientific articles. To this end, we proposed a model which uses the enriched contextualized knowledge of Persian articles through distributional semantics. Accordingly, identifying the specific field of each document and defining its domain by prominent enriched knowledge enhances the accuracy of scientific articles’ classification. To reach the goal, we enriched the contextualized embedding models, either ParsBERT or XLM-RoBERTa, with the latent topics to train a multilayer perceptron model. According to the experimental results, overall performance of the ParsBERT-NMF-1HT was 72.37% (macro) and 75.21% (micro) according to F-measure, with a statistical significance compared to the baseline (p<0.05).

This paper examines recent literature in the quest to uncover emerging patterns in the use of business intelligence in marketing. We conducted searches in pertinent academic journals and identified 1044 articles published between 2000 and 2023. To sift through this substantial body of work, we employed text mining techniques to extract pertinent terms in the realms of business intelligence and marketing. Additionally, we applied latent Dirichlet allocation modeling to categorize the articles into various pertinent topics. This analysis was performed within the domains of marketing and business intelligence. This approach enabled us to discover connections between terms and topics, which in turn allowed us to generate hypotheses regarding future research directions. To validate these hypotheses, we gathered and closely examined relevant articles. By pinpointing current research areas, this study underscores potential avenues for future investigation. The findings reveal that the predominant trend in business intelligence applications for marketing is the utilization of business intelligence systems, with a particular emphasis on marketing planning to enhance marketing strategies. Additionally, there is considerable interest in areas such as pricing models for marketing, enhancing brand value through effective social media marketing, employing predictive algorithms for customer data analysis, and harnessing big data for marketing analytics.

This article examines digital transformation in the construction industry, which begins with adopting digital technologies and culminates in comprehensive organizational change. The diverse and often conflicting conceptualizations in this field have created ambiguity in the theoretical framework of digi-tal transformation in construction. Using topic modeling and pattern analysis, this study identifies key themes and trends in the domain. The article analyzes 1,308 articles published between 1990 and 2023 to review research areas related to digital transformation in the construction industry. It identifies six main topics: Security & Safety, Organization & Project Management, Digital Simulation & Interaction, Sustainability, Innovative Building Materials, and Dynamic Monitoring Methods. The analysis reveals that Organization & Project Management is the most researched topic, while Sustainability receives the least attention. The article offers recommendations for advancing research in this field and serves as a valuable reference for researchers and practitioners interested in digital transformation in construction. By addressing existing criticisms, it provides a clear map of the field’s structure and trends, comple-menting previous qualitative studies with a broader, more structured, and objective analysis.