Text Mining Techniques Research Articles

Thematic Exploration and Analysis of Cybersecurity Policies of Businesses: An NLP-Based Approach

ABSTRACT Cybersecurity is a prime concern today for businesses due to the rapid increase in cyber-attacks, inadequate security controls, stricter regulations, and lack of security awareness among the workforce. A robust cybersecurity policy can address the security needs of businesses with directives on acceptable actions and behavior. Developing such a policy for business entities requires adequate skill and knowledge. Reviewing voluminous policy texts to identify best practices is also time-consuming. Therefore, the objective of this study is to provide a natural language processing (NLP)-based methodology that can quickly identify the significant topics and themes from the cybersecurity policies of leading global businesses. Text mining and Latent Dirichlet Allocation-based topic modeling technique have been used on cybersecurity policy-related textual contents obtained from 10 leading Fortune Global 500-listed business organizations and the extracted output is then mapped to the globally popular cybersecurity standard ISO/IEC 27,001:2022 to determine the relevancy. The study reveals significant topics and themes that can be used for the development or enhancement of cybersecurity policies to protect businesses from cyber threats.

Evolving research themes in six selected wood science journals: insights from text mining and latent dirichlet allocation

This study analyzes the status, trends, and future directions in wood science research using text-mining techniques. We applied these techniques to a textual dataset constructed from metadata of six major wood science journals, covering the period from 2002 to 2024. The research explores publication trends, international collaborations, keywords, and research networks, and it employs topic modeling using the Latent Dirichlet Allocation model. The descriptive analysis reveals a consistent increase in publication volume throughout the study period, unaffected by the COVID-19 pandemic. In contrast, international collaboration declined after 2020, likely due to the pandemic. In addition, a network analysis identified key research areas, including surface treatments, structural composites, and high-performance wood products, with lignin, mechanical properties, and moisture content emerging as central keywords. Topic modeling reveals a growing interest in wood modification technologies and an increased focus on studying wood as a sustainable material. The study confirms a shift of the field towards sustainable innovations while also highlighting the enduring relevance of traditional research areas. Future research should adapt to these evolving trends and address emerging challenges to maximize the potential of wood for carbon neutrality and sustainable development. This analysis provides a concise overview of current research trends and future directions in wood science.

Applications of Text Mining techniques to extract meaningful information from gastroenterology medical reports

Text mining techniques, particularly topic modeling, can be used for the automatic extraction of information from medical reports. The ability to autonomously analyze texts and identify topics within them can provide meaningful clinical insights that support physicians in diagnostic settings and enhance the characterization of intestinal diseases, leading to more efficient and automated systems.This study evaluates the effectiveness of Latent Dirichlet Allocation (LDA) and BERTopic in modeling topics from colonoscopy reports related to Crohn’s Disease, Ulcerative Colitis, and Polyps. We compared these models in terms of their ability to identify clinically relevant topics, their influence on the performance of machine learning classifiers trained on the derived topic features, and their scalability.Our analysis, based on average results across five iterations of train-test splits, showed that BERTopic generally outperformed LDA in clustering metrics, achieving Adjusted Rand Index (ARI), Normalized Mutual Information (NMI), and Purity scores of 0.5637, 0.5953, and 0.8447, respectively, compared to LDA’s scores of 0.5349, 0.5254, and 0.8149. Additionally, classifiers trained on BERTopic-derived features exhibited improved predictive accuracy and F1-scores, with Logistic Regression reaching a mean accuracy of 0.8464 and a mean F1-score of 0.8507, compared to 0.8319 and 0.8351 for LDA-based features. Despite BERTopic’s overall superior performance, LDA demonstrated greater stability and interpretability, making it a viable option in scenarios where computational efficiency is a priority.

A Study Evaluating the Problems and Challenges Faced by the Employees of the Indian Telecom Industry

The nation's economic expansion, connectivity, and digital transformation are all greatly aided by the telecom sector in India. However, workers in this industry frequently face difficulties including fierce competition, interruptions from technology, changes in regulations, and unstable employment. Despite these challenges, the sector is nevertheless vital to India's society, trade, and communication growth. This research paper was conducted with the focus on evaluating the problems and challenges faced by the employees of the Indian Telecom Industry. Text mining technique using the qualitative tool NVIVO 12 has been used in the current study. It is was found that the most important challenges faced by the employees of the Indian Telecom Industry are High workload, Intense competition among companies, Technological advancements, Network congestion, Poor infrastructure, Security concerns and Work-life balance. Whereas, minor challenges faced by the employees of the Indian Telecom Industry are Gender discrimination, Limited career growth, Language barriers, Increasing Customer expectations, and Rapid changes in consumer preferences

CEO identity and media perception: The influence on family firms’ brand importance

This study expands upon previous research on family firm leadership by exploring the role of CEO identity – i.e., family vs. nonfamily CEO – concerning the way media perceive the brand of the family firm– i.e., brand importance. Drawing on endorsement theory, we suggest that CEO identity influences media perception of the family firm and its brand, thereby affecting the extent of brand importance generated by these external stakeholders. Additionally, we propose that the generation of the family controlling the firm may influence the relationship between CEO identity and brand importance. Employing text mining and social network analysis techniques, we use the Semantic Brand Score to measure the importance that media place on family firm brands. Our analysis of a sample of 63 Italian family firms and 52,555 news articles published about these firms shows a positive and significant relation between the presence of a nonfamily CEO and brand importance; nevertheless, this relation is negatively moderated by the family firm generation.

Analysis of Housing Topics for Middle-Aged Adults in Online News Articles Using Text-Mining Techniques

Middle-aged adults face social isolation and economic insecurity due to limited institutional support, and despite government efforts, their financial, housing, and health challenges persist. This study explored housing welfare support strategies for middle-aged individuals through an analysis of major topics related to "middle-aged housing" in online news articles using text mining techniques. For this purpose, data from Naver articles published between February 2020 and July 2023 were collected and analyzed. The key findings were as follows: term frequency (TF) and term frequency-inverse document frequency (TF-IDF) comparisons revealed that TF focused on social and policy aspects ("support," "youth," "project," "region," "household," "policy," "housing," and "welfare"), highlighting government support characteristics, while TF-IDF emphasized economic aspects ("move-in," "market," "region," "housing," "price," "rise," "subscription," "apartment," "Jeonse," and "sale"), highlighting issues related to the housing market. This suggests that policies to improve housing welfare for middle-aged individuals should consider both social and economic aspects. Network analysis identified six major categories: housing support, support targets, housing economy, job support, housing infrastructure, and health and well-being. Each category was further divided into the following detailed topics: policy support, residential services, economic activities, employment creation, living environment improvement, and personalized health management. These findings indicate the need for comprehensive support that addresses various aspects of middle-aged housing welfare, including family considerations, economic support, social engagement, health, and digital adaptation.

Text-Mining-Based Non-Face-to-Face Counseling Data Classification and Management System

This study proposes a system for analyzing non-face-to-face counseling data using text-mining techniques to assess psychological states and automatically classify them into predefined categories. The system addresses the challenge of understanding internal issues that may be difficult to express in traditional face-to-face counseling. To solve this problem, a counseling management system based on text mining was developed. In the experiment, we combined TF-IDF and Word Embedding techniques to process and classify client counseling data into five major categories: school, friends, personality, appearance, and family. The classification performance achieved high accuracy and F1-Score, demonstrating the system’s effectiveness in understanding and categorizing clients’ emotions and psychological states. This system offers a structured approach to analyzing counseling data, providing counselors with a foundation for recommending personalized counseling treatments. The findings of this study suggest that in-depth analysis and classification of counseling data can enhance the quality of counseling, even in non-face-to-face environments, offering more efficient and tailored solutions.

Sustainable warehouse management: a literature review and future research agenda

Purpose Warehouses, essential nodes in the supply chain, significantly contribute to sustainability issues, accounting for about 11% of emissions related to logistics activities. The purpose of this study is to review articles on sustainable warehouse management (SWM) from the Scopus database to analyze trends, synthesize existing knowledge, and identify research gaps for future studies. Design/methodology/approach The review uses text mining of initial relevant documents to create a search string for paper retrieval. Text mining is further used to generate a dendrogram of the most frequently used words in the research papers, which is then analyzed to identify themes and sub-themes in SWM. Findings The dendrogram reveals four major themes and their sub-themes within SWM, including two novel themes: sustainable warehouse in green logistics and sustainable warehouse location. In addition, 12 research recommendations are identified through content analysis and are subsequently linked to specific Sustainable Development Goals (SDGs). Research limitations/implications The methodological innovation in keyword selection for searching relevant papers and identifying themes serves as a structured template for researchers to explore further. Practical implications The research recommendations, aligned with the SDGs, aim to assist managers in making informed decisions and operational strategies to enhance factors associated with the Building Research Establishment Environmental Assessment Method and the sustainable performance of warehouses. Originality/value This study is novel in its application of text-mining techniques to generate a search string for identifying relevant papers and discerning themes by analyzing the dendrogram.

Deep Learning-Based Freight Recommendation System for Freight Brokerage Platform

Platform-based businesses in the logistics market are evolving under the influence of digital transformation. Transforming the freight market into an environment where various types of freight can be traded across multiple markets and locations. Freight brokerage platforms have revolutionized the trading relationship between freight owners and vehicle owners. However, this type of system has also introduced inefficiencies, such as unestablished contracts, leading to unnecessary costs and delays. To address this issue, a freight recommendation system can assist users in finding what they are looking for while aiming to reduce failed contracts. With current advances in deep learning, complex patterns based on users’ past behaviors and preferences can be learned, enabling more accurate and personalized recommendations. This study proposes a deep learning-based freight recommendation system to provide personalized services and reduce failed contracts on freight brokerage platforms. The system is built by creating a freight transaction dataset, classifying freight categories through natural language processing and text mining techniques, and incorporating externally derived data on transportation distances. The deep learning model is trained using Autoencoder, Word2Vec, and Graph Neural Networks (GNN), with recommendation logic implemented to suggest suitable freight matches for vehicle owners. This system is expected to increase the market efficiency of the freight logistics industry and is a key step toward improving the long-term profit structure.

An Accurate and Efficient Approach to Knowledge Extraction from Scientific Publications Using Structured Ontology Models, Graph Neural Networks, and Large Language Models.

The rapid growth of biomedical literature makes it challenging for researchers to stay current. Integrating knowledge from various sources is crucial for studying complex biological systems. Traditional text-mining methods often have limited accuracy because they don't capture semantic and contextual nuances. Deep-learning models can be computationally expensive and typically have low interpretability, though efforts in explainable AI aim to mitigate this. Furthermore, transformer-based models have a tendency to produce false or made-up information-a problem known as hallucination-which is especially prevalent in large language models (LLMs). This study proposes a hybrid approach combining text-mining techniques with graph neural networks (GNNs) and fine-tuned large language models (LLMs) to extend biomedical knowledge graphs and interpret predicted edges based on published literature. An LLM is used to validate predictions and provide explanations. Evaluated on a corpus of experimentally confirmed protein interactions, the approach achieved a Matthews correlation coefficient (MCC) of 0.772. Applied to insomnia, the approach identified 25 interactions between 32 human proteins absent in known knowledge bases, including regulatory interactions between MAOA and 5-HT2C, binding between ADAM22 and 14-3-3 proteins, which is implicated in neurological diseases, and a circadian regulatory loop involving RORB and NR1D1. The hybrid GNN-LLM method analyzes biomedical literature efficiency to uncover potential molecular interactions for complex disorders. It can accelerate therapeutic target discovery by focusing expert verification on the most relevant automatically extracted information.

텍스트 마이닝을 활용한 이주배경 구성원의 문화적응 스트레스의 연구동향 분석

This study aims to explore research trends in acculturation stress using text mining techniques. To achieve this, 387 papers related to acculturation stress, published in KCI-indexed journals over 16 years since the enactment of the Multicultural Families Support Act in 2008, were selected. Based on the Korean abstracts, a total of 1,762 keywords were extracted. NetMiner 4.5 was utilized to analyze unstructured data, employing keyword network analysis and LDA-based topic modeling. The study analyzed keyword frequency, co-occurrence keyword pairs, and centrality. Through LDA-based topic modeling, it was found that five topics were the most appropriate. Based on the derived results, the study reviewed research directions to advance the academic development of acculturation stress and provided educational implications.

Big Data in Tourism: A Bibliometric Analysis (2014-2024)

The emergence of big data and its related technologies has brought about novel economic models, industry phenomena, and relational networks, instigating revolutionary changes with significant value for tourism sustainability. This study conducts a bibliometric analysis of 212 articles (2014-2024) on big data in tourism from the Web of Science (WoS) Core Collection database, aiming to create a knowledge map based on big data in tourism. This study utilizes VOSviewer software to carry out citation analysis, co-citation analysis, co-authorship analysis, and keyword co-occurrence analysis, revealing trends in publications, national contributions, influential journals and authors, author collaborations, as well as the conceptual structure and research trends in the field of big data in tourism. The findings indicate a concentration of research in seven areas: machine learning, social network analysis, sustainability, tourism demand forecasting, artificial intelligence, smart tourism, and text mining techniques. The research has focused on emerging hot topics since 2022, including destination image, COVID-19, topic modeling, and urban tourism. This study maps the knowledge of big data in tourism, elucidates the academic evolution in this field, and offers future research directions for scholars in the domain.

텍스트 마이닝 기법을 활용한 국어교육 평가 연구의 동향 분석

Objectives This study analyzed KCI-registered academic articles using text mining techniques to interpret the trends of research related to language education evaluation. Methods For this purpose, a total of 206 articles from January 1, 2000 to July 15, 2024 were collected from RISS and KCI, and after supplementing the abstracts, data preprocessing was performed, and finally, a total of 1,955 words were targeted for topic modeling and network analysis. Results As a result of the analysis, 10 topics were extracted and themes were extracted by topic. The themes of each topic in the research on Korean language education assessment are: improvement of Korean language teaching through assessment, school-centered Korean language assessment system, theoretical approaches to the content of Korean language assessment, development of Korean language assessment items, domain-specific characteristics and content of Korean language assessment, Korean language writing assessment, process- oriented Korean language assessment, national-level Korean language academic achievement assessment, importance and implementation of Korean language performance assessment, and assessment expertise of Korean language teachers. Conclusions The research on assessment in Korean language education tends to focus on changes in Korean language assessors' perspectives and teaching innovations, the characteristics of assessment in different areas of Korean language, research centered on writing assessment, the expansion of national-level assessment to unit school-level assessment, and theoretical research on assessment in Korean language education based on practicality.

Patent Keyword Analysis Using Regression Modeling Based on Quantile Cumulative Distribution Function

Patents contain detailed information of researched and developed technologies. We analyzed patent documents to understand the technology in a given domain. For the patent data analysis, we extracted the keywords from the patent documents using text mining techniques. Next, we built a patent document–keyword matrix using the patent keywords and analyzed the matrix data using statistical methods. Each element of the matrix represents the frequency of a keyword that occurs in a patent document. In general, most of the elements were zero because the keyword becomes a column of the matrix even if it occurs in only one document. Due to this zero-inflated problem, we experienced difficulty in analyzing patent keywords using existing statistical methods such as linear regression analysis. The purpose of this paper is to build a statistical model to solve the zero-inflated problem. In this paper, we propose a regression model based on quantile cumulative distribution function to solve this problem that occurs in patent keyword analysis. We perform experiments to show the performance of our proposed method using patent documents related to blockchain technology. We compare regression modeling based on a quantile cumulative distribution function with convenient models such as linear regression modeling. We expect that this paper will contribute to overcoming the zero-inflated problem in patent keyword analysis performed in various technology fields.

The potential of open innovation platforms: driving sustainable development goals through digital collaboration

ABSTRACT Open innovation is a pivotal driver of organisational growth. This concept involves engaging external partners and leveraging diverse knowledge sources, leading to significant advancements in sustainability. With the rise of digital platforms, the potential for open innovation to foster sustainable development has increased. However, the literature on the intersection of digitalisation, open innovation, and sustainability remains sparse and fragmented. This study aims to bridge this research gap by exploring how digital platforms facilitate open innovation practices and their impact on sustainability, particularly in alignment with the United Nations Sustainable Development Goals. By creating a comprehensive database from scientific literature published between 2019 and June 2024, this research compiles a wide range of applications, case studies, and proposed implementations of open innovation platforms. Exploratory analysis maps the landscape of these practices, focusing on their sectoral applications, technologies involved, and business impacts. Text mining techniques are employed to identify patterns and key elements within the dataset. This analysis reveals how open innovation platforms contribute to sustainability, highlighting areas where they are most effective and identifying gaps for future research. The findings offer theoretical and practical insights, providing a detailed understanding of the current state of open innovation in the digital age, and their implications for sustainable development. This study aims to inform practitioners and policymakers about leveraging digital platforms to enhance sustainability efforts.

The effectiveness of social media communication of sustainable fashion brands: evidence from consumer engagement

ABSTRACT The purpose of this study is to identify how sustainable fashion brands communicate with consumers on social media, specifically, Instagram. By applying a data mining technique to analyze brand posts and consumer comments, we thoroughly examine how consumers engage with sustainable messages from each brand and how those engagements are associated with brand posts. A sample of six sustainable fashion brands was selected, including Eileen Fisher, Everlane, Girlfriend Collective, Patagonia, Reformation, and Stella McCartney. Public posts of the six brands and corresponding consumer comments on Instagram between November 1, 2019 and November 1, 2022 were collected. LDA (Latent Dirichlet Allocation) text mining technique was applied to extract topics from each brand’s posts and follower comments. A fixed effects linear panel model was then employed to examine if consumer comments are significantly associated with sustainable messages from each brand. Ten major sustainability-related themes were identified from brand posts, and four major sustainability-related themes were discovered from consumer comments. The linear panel results provide preliminary evidence that the sustainability-related themes from consumer comments are positively influenced by the sustainability-related themes from brand posts, indicating that brand posts indeed affect consumers’ opinions about sustainability.

Decoding Sustainability Reporting: Insights from Text Mining and Classification Models for SDGs

Objective: This study aims to investigate the signaling effects of Sustainability Reporting (SR) in listed Singapore firms, particularly in demonstrating firm capitalization and sustainability performance. The research focuses on identifying distinct SR signals using advanced text mining and classification techniques, and their alignment with the United Nations' Sustainable Development Goals (SDGs). Theoretical Framework: The study is grounded in signaling theory, which posits that firms communicate observable characteristics (SR content) to signal unobservable attributes (firm capabilities and sustainability performance). By applying this framework, we analyze how SR may act as a signaling mechanism for large-cap firms and sustainability leaders. Method: This research collects 1,844 sustainability reports from listed Singapore firms between 2016 and 2022. Using a combination of Structural Topic Modeling (STM) and Random Forest (RF) classification models, we extracted and analyzed the key SR signals that differentiate firms by size and sustainability performance. Results: The results indicate that SR signals such as community engagement, climate risk, and compliance are effective in distinguishing between large firms and firms with strong sustainability performance. The Random Forest models achieved high accuracy in identifying these groups. Community engagement, compliance with the Global Reporting Initiative (GRI), and sustainable construction were among the most impactful topics, with large firms focusing more on scope and governance, while sustainability leaders emphasized environmental risks and compliance. Research Implications: The findings provide insights into the practical and theoretical implications of SR as a signaling tool. Key SR topics are identified as critical signals for firms with large capitalization and high sustainability performance, guiding firms in utilizing SR in the context of SDGs. Originality/Value: The findings show that SR topics such as community engagement, climate risk, and compliance serve as key signals for differentiating firms by size and sustainability performance. Firms can strategically emphasize these areas to enhance their SR practices while contributing to broader SDGs.The findings provide insights into the practical and theoretical implications of SR as a signaling tool. Key SR topics are identified as critical signals for firms with large capitalization and high sustainability performance, guiding firms in enhancing their SR strategies.

A Study on the Characteristics of Real Estate Education in Korean Universities through Text Mining-based Curriculum Analysis

Text mining is a method of analyzing text data to derive the characteristics or status of a described object. Since an educational program's curriculum reflects the content and goals it aims to teach, text analysis of the curriculum can reveal the characteristics of the program. This study employs text mining techniques to analyze the curricula of real estate education programs at Korean universities and proposes strategies for future development. The paper presents three main findings: First, by analyzing the curricula of universities in the UK and US that offer real estate education, the study identifies the unique characteristics of each country’s approach, reaffirming previously identified differences between them. Second, real estate education at Korean universities features an eclectic curriculum that incorporates elements of both UK and US real estate education, resulting in diverse curricular offerings across institutions. Lastly, for individual Korean universities, the study provides guidelines for the development of their departmental education by indicating which UK or US universities have the most similar or different curricula.

The impact of AI on enterprise energy management: from the perspective of carbon emissions

Given the significant impact of artificial intelligence (AI) technology on corporate energy management and the lack of research in this area, this paper employs text mining techniques to objectively assess the relative level of AI adoption among Chinese listed companies. Using econometric modelling methods, we verify these hypotheses and investigate both the direct and indirect effects of AI on corporate carbon emission intensity. our research finds that the carbon emission intensity of Chinese enterprises significantly decreased in the early stage, then stabilized, and has notably decreased again in recent years. The average level of AI among listed Chinese enterprises shows an overall upward trend, but the growth rate has slowed down. The level of AI in private enterprises is significantly higher than that in other types of enterprises, while the level of AI in state-owned enterprises is relatively lower. The level of AI in enterprises has a significant negative impact on carbon emission intensity, presenting an “S”-shaped relationship, characterized by initial emission reduction, mid-term rebound, and subsequent emission reduction. AI technology reduces the level of carbon emissions in enterprises by enhancing their green development standards and promoting technological innovation. There are significant differences in the impact of AI levels on carbon emission intensity across different types and regions of enterprises. The empirical conclusions remain robust after addressing endogeneity issues or variable substitution. This study provides important insights for corporate energy transitions and sustainable development, as well as for the formulation of government energy policies.

텍스트 마이닝을 활용한 국내 기본심리욕구 연구 동향 분석

Objectives The purpose of this study is to examine research trends related to basic psychological needs in Korea and identify major research topics and trends. Methods To this end, we analyzed 327 academic papers related to basic psychological needs, which were more than candidates for KCI registration published on the Academic Research Information Service. The data was preprocessed through an R program, and the results of keyword frequency analysis were visualized in a word cloud, and analyzed by topic modeling. Results First, according to the literature status, 327 journals have been published in 106 societies, including the Learner-Centered Curriculum Education Association and the Korean Youth Association. Second, in keyword frequency analysis, terms such as basic psychology, desire, research, relationship, influence, mediation, analysis, autonomy, effectiveness, satisfaction, and competence appeared as top words. Third, topic modeling results were categorized by effects on individual psychological well-being, research methods, relationships with elementary school students and psychological well-being, the influence of young people's home and school environments, the mental health of college students, and relationships with stressors in modern society. Conclusions This study is significant in that it identified the characteristics of basic psychological needs research trends in Korea by applying text mining techniques to a vast amount of information on basic psychological needs, and it can be used as useful basic data for setting the direction of basic psychological needs research and selecting research topics in the future.