topic modeling

This study examines textual data's ability to nowcast Iran's gross domestic product (GDP). To this end, 301,498 economic news articles from March 2005 to December 2023 were extracted from the Fars news agency website using a web crawling technique. Following initial preprocessing, the news texts were sorted into various categories via the Dirichlet Latent Allocation (LDA) model, wherein each category corresponds to a distinct news topic. Subsequently, to ascertain whether an article conveys a positive or negative sentiment, we executed lexicon-based sentiment analysis utilizing SentiStrength. Ultimately, by aggregating the news sentiment scores seasonally under each topic, we constructed a seasonal sentiment time series. These time series were then assessed for their efficacy in nowcasting Iran's quarterly GDP, employing ridge regression, lasso regression, elastic net, and gradient boosting methods. The findings reveal that incorporating textual data can reduce prediction errors by 12 to 18 percent relative to a univariate time series model. Moreover, our results suggest that sentiment extracted from textual content, particularly news articles, is a viable approach. This strategy could potentially enable the provision of immediate GDP estimates following the end of each reference quarter.

IT's rapid progress and far-reaching impact on other scientific disciplines have not only necessitated significant changes in its own subjects but have also catalyzed extensive changes in the form, amount, and methodology of research in other fields. The objective of the present investigation was to analyze research conducted in the realm of information technology, extract its central themes, and furnish scientometric data pertaining to these themes.

This paper explores the topics of the information technology field by extracting and categorizing the relationships between commonly used terms and their temporal evolution. To achieve this, the researchers employed topic modeling, a well-established method for clustering textual data. Topic modeling algorithms utilize statistical methods to analyze and interpret the primary words in documents, allowing for the examination of the presented issues and their interconnections and changes over time. Considering the rapid changes in the field of information technology, this paper drew upon materials spanning the last decade, including 10,000 papers sourced from top-tier journals featured in the Web of Science database.

The study extracted trends in keyword changes over the past decade and identified important keywords for each paper cluster after grouping them. The papers within the information technology domain were then categorized into eight themes, including hardware, communications, networks, and intelligent applications such as the Internet of Things. The study found that frequently used keywords have been continuously changing over time. The paper highlights that emerging keywords, including the Internet of Things, cloud computing, and Big Data, along with work areas such as Machine Learning and Deep Learning, are shaping the definition of information technology fields in the new era.

Given the shift in research emphasis from hardware and communication to analysis and practical applications, it is likely that future scientific fields will focus on creating value through data analysis and human-machine communication in everyday applications, and information technology's relevance in other sciences will become more apparent. Future research can also concentrate on comparing global trends in information technology with domestic research, enabling the evaluation of the gap between the country's research and that of the world.

In recent years, the rapid growth of virtual space has made people devote more of their time in virtual space, especially to social networks, which can be attributed to the remarkable features of virtual space; including increasing the speed of information exchange, easy and free access to information and variety of knowledge topics. In this regard, the opinions recorded by users in virtual networks have grown day by day and have become very important, and extracting the opinions and feelings of users' opinions for more informed decision-making is of great help to businesses, on the other hand, virtual reality technology in the past few decades It has undergone technical changes and improved immersion and the feeling of remote presence; This technology is used in various fields such as education, tourism, health, sports, entertainment, architecture and construction, etc. The increasing progress of virtual reality technology has caused many businesses to operate in this field, but due to changes Continuous market and the need for timely information, companies should use differentiation and growth strategies, in this regard, they need to ask users' opinions and in line with that, try to grow and improve their business, considering that Users' comments are textual, and reading and summarizing them is time-consuming and difficult. Based on this, the aim of the current research was to categorize comments related to virtual reality technology using machine learning methods and a dictionary-based approach. Therefore, about one million tweets in the field of virtual reality technology were collected by the web crawler, and after data preprocessing, 480,432 samples remained in the data, then Dirichlet's hidden allocation topic modeling was implemented on the data. This modeling separated different topics by examining the distribution of words in tweets; The tweets whose distribution of words were similar were placed into a topic and the number of topics with the highest coherence score was selected, the number of topics 9 had higher coherence and the data were grouped into 9 topics, so once again the Dirichlet hidden allocation modeling was set to 9. The topic was done, with this the tweets were grouped into 9 different topics. To evaluate the model, considering that we had a probability distribution, the confusion criterion was used, the value of which was -9.44, and the coherence score was used for the degree of semantic similarity between words and the distinction between subjects, and the result was 0.47. The lower the confusion criterion and the higher the coherence score, the more efficient the model is. With the help of keyword weights obtained by Dirichlet hidden allocation modeling and examining at least 5 different tweets from each topic, 9 topics related to virtual reality technology were identified: "New Technology", "Creation and Make", "Technological Business", "Education", "Virtual Games", "Progress", "Gadget", "Metaverse", and "Indiegame", the topics were analyzed with the help of several graphs. We found that the number of neutral comments on topics such as "New Technology" and "Metaverse" is more than positive and negative comments, which indicates the lack of sufficient information or the lack of use of these technologies, and it is necessary for businesses in this field, to try more in this regard, in the same way, if we observe the graph of "Virtual Games" and "Technological Business", we can see that it changes almost with the same ratio in different years, in the sense that this The two graphs are related, in fact, businesses should keep in mind that the factors affecting these two issues are the same, but users pay more attention to the issue of "Virtual Games", as a result, if the creators of "Technological Business" Focus specifically on "Virtual Games", they will grow more due to the more attention of users, also the creators of games should consider that "Virtual Games" are a topic of more attention than "Indiegame". Is. In the subjects of "Education" and "Gadget", users lost their attention to these subjects in the field of virtual reality over time, in fact they showed their attention to other subjects, so it is better for businesses that operate in this field to take measures To advertise and attract users or change their user area if there is no growth.

Constant changes in the market and the need for timely information force companies to use differentiation and growth strategies appropriate to the needs of customers. (Sánchez, Folgado-Fernández, & Sánchez, 2022). Companies can check and analyze their customers' opinions through microblogging sites (Facebook, Twitter, etc.) and finally improve the desired products or services (Ahmad, Aftab, Bashir, & Hameed, 2018). Today, users express their opinions and feelings and review products in online social networks. Therefore, user comments and the analysis of these comments have become a valuable resource for businesses (Kim et al., 2015; Loureiro et al., 2019).
Virtual reality and augmented reality have undergone technical developments in the past few decades and have improved immersion and the feeling of remote presence. Several examples of applications of such techniques can be found in stores, the tourism industry, hotels, restaurants, etc. (Loureiro, Guerreiro, & Ali, 2020). Due to the constant changes in the market and the need for timely information, companies should use differentiation and growth strategies, nowadays, due to the rapid evolution of the Internet, instead of collecting their opinions through time-consuming and expensive methods such as questionnaires and interviews, etc., they express in the context of social networks, which is very useful for businesses in their development, and they can measure the feelings of customers towards products and services, and understand the needs of users, and finally make appropriate and appropriate decisions in the direction of adopt growth, but in order to use the produced content correctly, text mining and sentiment analysis techniques should be used, which has not been researched in Iran so far. Analysis of users' opinions and feelings about virtual reality technology can help businesses that operate in the field of metaverse, virtual game production, virtual education, virtual tourism, etc., to make better decisions and plans.

Social media generates a large amount of real-time social signals that can provide new insights into human behavior and emotions. People around the world are constantly engaged with social media. (Al-Samarraie, Sarsam, & Alzahrani, 2023).
On the other hand, the amount of data is increasing day by day. Almost all institutions, organizations and business industries store their data electronically. A huge amount of text is circulating on the Internet in the form of digital libraries, repositories, and other textual information such as blogs, social media networks, and emails (Sagayam, Srinivasan, & Roshni, 2012).
Topic modeling is one of the most powerful techniques in text mining for data mining, discovering hidden data and finding relationships between data and textual documents (Jelodar et al., 2017).
The technological advances of the last century have confronted societies with new realities that have indisputably improved daily life, making it more convenient and interesting. In recent decades, technology using virtual reality and wearable devices have had a significant impact in the fields of education, tourism, health, sports, entertainment, architecture and construction, etc. (Kosti et al., 2023).
Virtual reality is a technology that allows a user to interact with a computer-simulated environment, whether that environment is a simulation of the real world or an imaginary one. With virtual reality, we can experience the most frightening and overwhelming situations with safe play and a learning perspective (Mandal, 2013). Most people are curious about the possibilities and future of new technologies, considering the various applications it is supposed to offer such as virtual meetings, learning environments and many others, however, there are also concerns about potential negative effects. because real world signals can be transmitted in the virtual world. In this regard, people express their feelings in different social networks (Bhattacharyya et al., 2023).

According to the main goal of the research, which is to classify comments related to virtual reality technology using machine learning methods and a dictionary-based approach, therefore, about one million tweets in the field of virtual reality technology were collected by the web crawler and After data preprocessing, 480,432 samples remained in the data, then Dirichlet hidden allocation thematic modeling was implemented on the data. By examining the distribution of words in tweets, this modeling tries to separate different topics by detecting the distribution of words; The tweets whose distribution of words are similar were put into a topic, and the number of topics with the highest score was selected, the number of topics 9 has higher coherence, and the data was grouped into 9 topics, so once again, Dirichlet hidden allocation modeling was applied 9 topics were done, whereby the tweets were grouped into 9 different topics. Considering that we have a probability distribution, the confusion criterion was used to evaluate the model. The lower the confusion criterion and the higher the coherence score, the more efficient the model is. With the help of keyword weights obtained by Dirichlet hidden allocation modeling and examining at least 5 different tweets from each topic, 9 topics related to virtual reality technology were identified: "New Technologies", "Creation and Make", "Technological Business", "Education", "Virtual Games", "Progress", "Gadget", "Metaverse" and "Indiegame" were named.

In this research, by examining topics in different years, we observed that the topic of "Progress" was the most popular topic among users from 2017 to the end of 2021, in early 2022, this topic gave way to "Metaverse", currently "Metaverse" is one of the most popular topics being discussed by users. Businesses in the field of virtual reality should strive for the attractiveness of "Metaverse" and attract users. Likewise, if we observe the "Virtual Games" and "Technological Business" graphs, we can see that they change with almost the same ratio in different years, meaning that these graphs are related to each other, in fact, business and keep in mind that the factors affecting these two issues are the same, but in the case of "Virtual Games" it has more effects, and if "Technological Businesses" specifically focus on virtual games, they will grow more due to the greater attention of users. had Similarly, "Indiegame" which have had a series of changes but in recent years have had a declining trend and then no change, now the creators of these games should check, and in general "Virtual Games" are a more interesting topic than "Indiegame". In the subjects of "Education" and "Gadget" it has been decreasing since the beginning of 2017, which shows that users lost their attention to these subjects in the field of virtual reality over time, in fact to other topics showed their attention, so it is better for businesses that are active in this field to take measures to advertise and attract users, or change their user field if there is no growth.

This study investigates the automatic keyword extraction from the table of contents of Persian e-books in the field of science using LDA topic modeling, evaluating their similarity with the golden standard, and users' viewpoints of the model keywords.

This is mixed text-mining research in which LDA topic modeling is used to extract keywords from the table of contents of scientific e-books. The evaluation of the used approach has been done by two methods of cosine similarity computing and qualitative evaluation by users.

Table of contents are medium-length texts with a trimmed mean of 260.02 words, about 20% of which are stop-words. The cosine similarity between the golden standard keywords and the output keywords is 0.0932 thus very low. The full agreement of users showed that the extracted keywords with the LDA topic model represent the subject field of the whole corpus, but the golden standard keywords, the keywords extracted using the LDA topic model in sub-domains of the corpus, and the keywords extracted from the whole corpus were respectively successful in subject describing of each document.

The keywords extracted using the LDA topic model can be used in unspecified and unknown collections to extract hidden thematic content of the whole collection, but not to accurately relate each topic to each document in large and heterogeneous themes. In collections of texts in one subject field, such as mathematics or physics, etc., with less diversity and more uniformity in terms of the words used in them, more coherent and relevant keywords are obtained, but in these cases, the control of the relevance of keywords to each document is required. In formal subject analysis procedures and processes of individual documents, this approach can be used as a keyword suggestion system for indexing and analytical workforce.

Since the advent of the Internet, we have come across a large amount of data that has been placed on this platform. This has caused the way data is studied and examined to evolve from manual to automatic. This research aims to extract the topics raised in articles in the field of language and linguistics and to study the evolution of topics over time with the help of the topic modeling algorithm. To this end, the Latent Dirichlet allocation algorithm is used. The corpus of this research was developed through crawling; and after filtering and pre-processing of the data, the number of 5, 10 and 15 topics are extracted from the articles; and based on the words of each topic, they are manually labeled. Due to the distribution of articles from 1927 to 2020 (1306 to 1399 according to the solar calendar), the time is divided into 5 time span and the topics related to each time span is identified after the labeling process. Among the 5 extracted topics, including Education, Discourse Analysis, Psychology, Syntax and Dialectology, all topics, except Discourse Analysis, are progressively studied over time. The growth and decline of the topics extracted from the articles can be seen in 10 and 15 topics. The practical achievement of this research is policy-making in the field of science. In addition to introducing a practical, technological methodology in do research, it is possible to identify hot topics among researchers in a scientific field and to find the gaps in research topics and to try to diversify and balance research topics.

Due to the global attention to cryptocurrencies especially bitcoin, governments, banks, and other industries are expected to use cryptocurrencies in their daily transactions. Therefore, as any other financial field, there is a need to identify the challenges in this field to safe investment. On the other hand, by the expansion of social networks, unstructured data is increasing, which can be used to create added value in various areas such as sentiment analysis. Therefore, this study was conducted to investigate the impact of perceived risk by social network users on the price of Bitcoin. According to the research findings, the identified risks in the field of bitcoin include social, economic, security, technological and legal risks., The conversations on the Bitcoin Talk Site were used to extract the bitcoin risks. After collecting these conversations by the web crawler, the conversations were clustered into thematic clusters using the Latent Dirichlet Allocation algorithm, which is one of the most popular methods in Topic Modeling. were analyzed using vocabulary-based method and AFINN dictionary. NARX Neural Network was used to measure the effect of Userschr('39') Sentiment on the price of Bitcoin. The results show a correlation of 0.99 and a mean square error of 0.001, which means that there is a correlation between the actual price and the predicted price of Bitcoin. The findings of this study can attract the attention of financial actors and businessmen in the field of bitcoin to plan a safe investment and reduce risk.

With the development of mobile communications and the advent of the Fifth Generation, increasing Internet speed and capabilities as enablers of the Internet of Things is creating changes in people's daily lives and work. On the other hand, there are environmental issues, the possibility of pathogenicity, and doubts about the realization of the imagined features, which are much debated today. Most researches has paid attention to technical and developmental dimensions of it, while from the social science perspective, the acceptance of new technology and from the marketing perspective, consumer satisfaction can be important for service providers. Accordingly, the purpose of this study is to investigate the perception of Twitter social network users as a microblogging platform about the fifth generation of mobile communication using machine learning methods and Sentiment Analysis .Therefore, a collection of more than 40,000 tweets on this topic was compiled through the Twitter user interface and the Recurrent Neural Network model was created with79% accuracy. Finally, the topic modeling was done by LDA method for further deepening. The results shows that although there is dissatisfaction with the quality provided, the cost and coverage of the fifth generation of mobile communications, health concerns, rumors that Covid19 is related to the fifth generation, but still more people are optimistic about the future of this technology in various fields such as the Internet of Things and artificial intelligence..

Probabilistic topic modeling methods consist of a set of algorithms whose main purpose is to discover the hidden subject structure in a large volume of documents. The purpose of this study is to thematically model the articles of Iranian researchers in the field of endocrinology and metabolism in the citation database of Web of Science.

The present research is of applied type and has been done by text mining and content analysis method. In this study, all required data were retrieved from the Web of Science Citation Database using the keywords registered in the medical subject heading without a time limit until November 6, 2018. Then, using a hidden allocation algorithm, the whole set of documents in MATLAB was analyzed.  

Subject categories were extracted as groups of 20 words in 10 subject categories. Then, by endocrinologists, the subject categories were named based on their relationship to various topics in the field of  endocrinology and metabolism, and each category was assigned a subject title.

The results indicate that the implementation of the latent Dirichlet allocation model has an acceptable performance in presenting the categories of endocrinology and metabolism. The extracted subject categories have good homogeneity and thematic relevance with each  other.

Topic modeling is one of the text mining techniques that allows you to discover unknown topics in a collection of documents, interpret documents based on these topics, and use these interpretations to organize, summarize, and search for texts automatically. Familiarity with the concept and technique of topic modeling, and its application in discovering topics and organizing information is one of the main goals of this research.

The present study is a review-analytical type in which, while introducing topic modeling, it has categorized and reviewed the applications of this technique based on its performance and provided a sample of research that has used this technique.

Topic modeling algorithms is used not only in addition to the three main objectives of discovering hidden topics, interpreting documents based on topics, and finally organizing and classifying texts, but also is used in discovering hidden topics and relationships in the fields of science, information retrieval, categorizing documents based on topics, discovering outstanding patterns and emerging events, clustering the concepts of scientific fields, analyzing the course of conceptual evolution during historical periods, determining the hierarchical relationships of concepts. A specific scientific field or field and vocabulary enrichment.

Topic modeling based on machine learning and artificial intelligence knowledge has been proposed as one of the new approaches to organizing information resources and serious studies are being conducted in this field. Therefore, by using topic modeling algorithms in order to automate the extraction of the subject and discover the hidden issues in the source, it is possible to strengthen and update the new systems of organizing information resources.

According to the variety and diversity of research conducted in the field of internal auditing, the purpose of this research is to gain a deeper understanding of the topic by conducting a systematic review of existing studies to classify topics and outline some potential future research directions.

In order to achieve our purpose and to more efficiently examine a large number of articles, the "Computational Literature Review (CLR)" approach is used, and through this, the content of abstracts is analyzed automatically to provide a set of research topics within internal audit literature (Topic Modeling). The required information is collected from the Thomson Reuters Web of Science (WoS) database for 1401 articles over almost one hundred years (1920 to 2021).

The results of Topic Modeling show the focus of seven areas in internal audit research as follows: internal audit in the healthcare industry; internal audit in the areas of risk management, fraud, and internal controls; competence and training and internal audit quality; and the relationship between the external auditor and the internal auditor. A separate review of each of these identified issues related to internal audit reveals the most critical research conducted in this area and identifies some avenues for future research.

The results of this study indicate that throughout the evolution of internal auditing during its history (almost 100 years), its philosophy has evolved from ensuring the accuracy of financial statements and accounts and preventing the misuse of corporate funds or assets by helping to create and add value to companies. Internal auditing services have been upgraded from assuring financial statements and responding to its limited stakeholders (i.e., senior managers), giving assurance, consulting, forecasting risk, and being accountable to all stakeholders. Also, the change in the accountability direction of internal audit and its greater cooperation with external auditors, and the growth of technology and increasing the complexity of organizations have led to changes in competencies and skills required and improving and promoting its independence and objectivity; also engaging internal auditors in other areas of expertise (other than accounting and auditing), then it is expected that the trend will continue in the future.