Latent Dirichlet Allocation Model Research Articles

Malaysian Chinese folk beliefs on Facebook based on LDA topic modelling

In the digital age, as social media evolves into a new and significant centre for the dissemination of Chinese folk beliefs, the Malaysian Chinese have actively shared information about these folk beliefs on their social media platforms. The dissemination has transcended regional barriers, encouraging more Malaysian Chinese across various states to actively participate in public discussions on this topic. This study delves into Malaysian Chinese folk beliefs by analysing data from Facebook. A comprehensive examination of 4012 text posts was conducted using the latent Dirichlet allocation (LDA) model for topic modelling. The analysis identified four main themes on social media: ‘Practitioners Worship’, ‘Temple Activities’, ‘Deity Legends’, and ‘Merchandise about Deity Statues’. Based on integrating social construction theory and media ecology theory, the study first explores the varied constructors, including practitioners, temple organisations, media organisations, and merchants. Secondly, Malaysian Chinese folk beliefs on social media present characteristics of utilitarianism, regional diversity, multiple social functions, flowing realms, strong Taoist elements, commercialisation, and a close relationship with the Spring Festival. Furthermore, ‘Safety and Peace’, ‘Pray for Demands’, and ‘Merits and Virtues’ form an interconnected semantic nexus. Hence, the findings theoretically highlight the interaction and significance of social media in the construction and practice of folk beliefs within the Malaysian Chinese community. Practically, this research provides valuable insights into the understanding and dissemination of Malaysian Chinese religious culture in the digital era.

Delineating Source and Sink Zones of Trip Journeys in the Road Network Space

Source–sink zones refer to aggregated adjacent origins/destinations with homogeneous trip flow characteristics. Current relevant studies mostly detect source–sink zones based on outflow/inflow volumes without considering trip routes. Nevertheless, trip routes detail individuals’ journeys on road networks and give rise to relationships among human activities, road network structures, and land-use types. Therefore, this study developed a novel approach to delineate source–sink zones based on trip route aggregation on road networks. We first represented original trajectories using road segment sequences and applied the Latent Dirichlet Allocation (LDA) model to associate trajectories with route semantics. We then ran a hierarchical clustering operation to aggregate trajectories with similar route semantics. Finally, we adopted an adaptive multi-variable agglomeration strategy to associate the trajectory clusters with each traffic analysis zone to delineating source and sink zones, with a trajectory topic entropy defined as an indicator to analyze the dynamic impact between the road network and source–sink zones. We used taxi trajectories in Xiamen, China, to verify the effectiveness of the proposed method.

Assessing the needs of patients with breast cancer and their families across various treatment phases using a Latent Dirichlet Allocation model: a text-mining approach to online health communities.

This study aimed to assess the different needs of patients with breast cancer and their families in online health communities at different treatment phases using a Latent Dirichlet Allocation (LDA) model. Using Python, breast cancer-related posts were collected from two online health communities: patient-to-patient and patient-to-doctor. After data cleaning, eligible posts were categorized based on the treatment phase. Subsequently, an LDA model identifying the distinct need-related topics for each phase of treatment, including data preprocessing and LDA topic modeling, was established. Additionally, the demographic and interactive features of the posts were manually analyzed. We collected 84,043 posts, of which 9504 posts were included after data cleaning. Early diagnosis and rehabilitation treatment phases had the highest and lowest number of posts, respectively. LDA identified 11 topics: three in the initial diagnosis phase and two in each of the remaining treatment phases. The topics included disease outcomes, diagnosis analysis, treatment information, and emotional support in the initial diagnosis phase; surgical options and outcomes, postoperative care, and treatment planning in the perioperative treatment phase; treatment options and costs, side effects management, and disease prognosis assessment in the non-operative treatment phase; diagnosis and treatment options, disease prognosis, and emotional support in the relapse and metastasis treatment phase; and follow-up and recurrence concerns, physical symptoms, and lifestyle adjustments in the rehabilitation treatment phase. The needs of patients with breast cancer and their families differ across various phases of cancer therapy. Therefore, specific information or emotional assistance should be tailored to each phase of treatment based on the unique needs of patients and their families.

Diversified Filtering Mechanism for Evaluation Indicators of Urban Road Renewal Schemes

As global urban infrastructure renewal progresses, the urgent need for sustainability-driven urban renewal intensifies amidst resource scarcity and environmental concerns. Effective evaluation and decision making regarding urban road renewal schemes are prerequisites for their successful implementation. However, variation in the prioritization of indicators in project evaluations and the poor adaptability of existing frameworks hinder the quick assessment of diverse projects. To address this issue, this paper proposes a scheme evaluation framework with embedded renewal project features comprising four modules. Following the initial construction of a sustainability-driven evaluation system, an indicator-filtering mechanism combining the Latent Dirichlet Allocation (LDA) model with a text similarity algorithm is developed. The Entropy Weight-–TOPSIS method is then employed to derive the final optimal decision based on selected indicators. Applying the decision framework to the G15 Jialiu Widening and Reconstruction Project in Shanghai, China, indicators are reduced by 48.3%, with the optimal scheme decision consistent with the traditional Entropy Weight–TOPSIS method. The framework is robust and enhances decision efficiency, filling theoretical gaps in existing indicator-filtering mechanisms.

Neurocomputer System of Semantic Analysis of the Text in the Kazakh Language

The purpose of the study is to solve an extreme mathematical problem—semantic analysis of natural language, which can be used in various fields, including marketing research, online translators, and search engines. When training the neural network, data training methods based on the latent Dirichlet allocation model and vector representation of words were used. This study presents the development of a neurocomputer system used for the purpose of semantic analysis of the text in the Kazakh language, based on machine learning and the use of the latent Dirichlet allocation model. In the course of the study, the stages of system development were considered, regarding the text recognition algorithm. The Python programming language was used as a tool using libraries that greatly simplify the process of creating neural networks, including the Keras library. An experiment was conducted with the involvement of experts to test the effectiveness of the system, the results of which confirmed the reliability of the data provided by the system. The papers of modern computer linguists dealing with the problems of natural language processing using various technologies and methods are considered.

Artificial intelligence and sustainable development during the pandemic: An overview of the scientific debates

The current work aims to analyze the main themes related to artificial intelligence (AI) and sustainable development during the pandemic period. This study provides an overview of the specialized literature related to AI and sustainability from the beginning of the pandemic through 2023. The present paper analyses scientific literature emphasizing both artificial intelligence's positive and negative impacts on sustainable development objectives (SDGs). To conduct the research, we employed bibliometric analysis and text-mining techniques to identify the major themes in the literature indexed in the Web of Science and Scopus databases. Firstly, we used descriptive measures to identify the authors' impact, the article production by country, the main keywords used, and other descriptive data. We further used data reduction methods based on co-word analysis (such as multiple correspondence analysis) on authors' keywords to show patterns in the themes explored in the literature. Bibliometric analysis was supplemented by text mining using Latent Dirichlet allocation (LDA) and structural topic modeling on abstracts to provide a comprehensive view of scientific debates on AI and sustainable development. Our research has identified various themes in the literature related to AI and sustainable development. These themes include social sustainability, health-related issues, AI technologies for energy efficiency, sustainability in industry and innovation, IoT technologies for smart and sustainable cities, urban planning, technologies for education and knowledge production, and the impact of technologies on SDGs. We also found that there is a significant positivity bias in the literature when discussing the impact of AI on sustainable development. Despite acknowledging certain risks, the literature tends to focus on the potential benefits of AI across various sectors. In addition, the analysis shows a growing emphasis on energy efficiency, which is facilitated by the use of AI technologies. Our study contributes to a better understanding of current scholarly discussion trends and emerging scientific avenues regarding AI and sustainable development. It also highlights the areas where research is needed and the implications for practitioners and policymakers.

Classification and Prediction of Food Safety Policy Tools in China Based on Machine Learning

Governments use policy interventions to mitigate food safety risks. Despite its crucial role, empirical studies evaluating the effectiveness of China's food safety policy tools are scarce. Drawing on a dataset encompassing 11,236 food safety policy texts from 2005 to 2021 and the incidence of problematic food products in the Eastern, Central, and Western regions of China, this study employs Latent Dirichlet Allocation (LDA) and eXtreme Gradient Boosting (XGBoost) models to facilitate the classification of policy tools and forecast the effectiveness of policy combinations. The study reveals that (1) local governments have gradually become an important supplementary maker of food safety policies, and have issued an increasing number of policy tools year by year. (2) Mandatory policy tools are predominant in number and have the highest legal hierarchy and authority levels, followed successively by guiding policy and voluntary policy tools. (3) Mandatory policy tools demonstrated the most effective intervention results, followed successively by guiding policy and voluntary policy tools. (4) The forecast analysis reveals that combinations of policies within high-growth frameworks and those driven by mandatory regulations emerge as the most effective. Therefore, the balance of policy tools in terms of type, effectiveness, and quantity, as well as their applicability in different situations, should all be taken into account.

Improving the term weighting log entropy of latent dirichlet allocation

<p class="AbstractText">The process of analyzing textual data involves the utilization of topic modeling techniques to uncover latent subjects within documents. The presence of numerous short texts in the Indonesian language poses additional challenges in the field of topic modeling. This study presents a substantial enhancement to the term weighting log entropy (TWLE) approach within the latent dirichlet allocation (LDA) framework, specifically tailored for topic modeling of Indonesian short texts. This work places significant emphasis on the utilization of LDA for word weighting. The research endeavor aimed to enhance the coherence and interpretability of an Indonesian topic model through the integration of local and global weights. Local Weight focuses on the distinct characteristics of each document, whereas global weight examines the broader perspective of the entire corpus of documents. The objective was to enhance the effectiveness of LDA themes by this amalgamation. The TWLE model of LDA was found to be more informative and effective than the TF-IDF LDA when compared with short Indonesian text. This work improves topic modeling in brief Indonesian compositions. Transfer learning for NLP and Indonesian language adaptation helps improve subject analysis knowledge and precision, this could boost NLP and topic modeling in Indonesian.</p>

Analysis of Suicide-related Tweets During the COVID-19 Pandemic

Background:: The COVID-19 virus started in 2019 and badly affected the different sectors of many countries around the world. Based on this, financial difficulties, loss of loved ones, sudden anger, relationships, family disputes, and psychological distress increased, and individuals were stalled from carrying out their lifestyle in a normal way, and some individuals were even motivated to commit suicide. Objective:: It is important to reduce the number of suicides and identify the reasons for this situation. Through this research, the focus is on identifying the main topics discussed relevant to suicides during the COVID-19 pandemic. Methods:: Individuals use Twitter, a social media platform, to share their ideas freely and publically. We collected 9750 primary data through Twitter API (Application Programming Interface). After preprocessing and feature extraction by TF-IDF (Term Frequency-Inverse Document Frequency), we applied the LDA (Latent Dirichlet Allocation) and Probabilistic Latent Semantic Analysis (PLSA) topic modeling algorithms to identify topics. Results:: Based on the LDA results, we extracted ten different topics under the three themes, such as the impact of COVID-19, human feelings, getting support, and having awareness. Intertopic Distance Map, Most Salient Terms, and Word Clouds Visualization are used to check the results. The coherence score and perplexing value are used to measure how interpretable the extracted topics are to humans. PLSA also extracted 25 topics with their probabilities, and Kullback–Leibler (KL) divergence was used to check the results. Conclusion:: We were able to gain insight into human emotions and the main motivations behind suicide attempts using the topics we extracted. Expert feedback proved that LDA results were better than PLSA. Based on that, we found the main impact of COVID-19 on human lives, how human feelings were changed positively and negatively during that period, what supporting and awareness methods people used, and what they preferred. The required measures can then be taken by those responsible authorities and individuals to prevent, reduce, and get ready for this kind of suicidal incident in the future.

Twitter users perceptions of AI-based e-learning technologies

Today, teaching and learning paths increasingly intersect with technologies powered by emerging artificial intelligence (AI).This work analyses public opinions and sentiments about AI applications that affect e-learning, such as ChatGPT, virtual and augmented reality, microlearning, mobile learning, adaptive learning, and gamification. The way people perceive technologies fuelled by artificial intelligence can be tracked in real time in microblog messages promptly shared by Twitter users, who currently constitute a large and ever-increasing number of individuals. The observation period was from November 30, 2022, the date on which ChatGPT was launched, to March 31, 2023. A two-step sentiment analysis was performed on the collected English-language tweets to determine the overall sentiments and emotions. A latent Dirichlet allocation model was built to identify commonly discussed topics in tweets. The results show that the majority of opinions are positive. Among the eight emotions of the Syuzhet package, ‘trust’ and ‘joy’ are the most common positive emotions observed in the tweets, while ‘fear’ is the most common negative emotion. Among the most discussed topics with a negative outlook, two particular aspects of fear are identified: an ‘apocalyptic-fear’ that artificial intelligence could lead the end of humankind, and a fear for the ‘future of artistic and intellectual jobs’ as AI could not only destroy human art and creativity but also make the individual contributions of students and researchers not assessable. On the other hand, among the topics with a positive outlook, trust and hope in AI tools for improving efficiency in jobs and the educational world are identified. Overall, the results suggest that AI will play a significant role in the future of the world and education, but it is important to consider the potential ethical and social implications of this technology. By leveraging the positive aspects of AI while addressing these concerns, the education system can unlock the full potential of this emerging technology and provide a better learning experience for students.

Enhancing Rubric Development in Science Education through Topic Modeling Techniques

Content experts conduct traditional approaches to developing rubrics for constructed response (CR) items, which is a labor-intensive process. We aim to illustrate the potential benefits of utilizing topic modeling techniques to improve the efficiency of the rubric workload. The results of this study reveal that over half of the keywords in the rubric corresponded with the top 20 words extracted from the supervised latent Dirichlet allocation (sLDA) model. The rubric-based scores assigned by human raters showed medium-to-high associations with the sLDA-predicted scores. The sLDA approach offers supporting evidence for refining the rubric concerning criteria for word usage and score assignments. It accomplishes this by concurrently incorporating the predetermined rubric of content experts and the actual responses provided by students.

Analysis of research topics and trends in investigator-initiated research/trials (IIRs/IITs): A topic modeling study.

With the exponential growth of publications in the field of investigator-initiated research/trials (IIRs/IITs), it has become necessary to employ text mining and bibliometric analysis as tools for gaining deeper insights into this area of study. By using these methods, researchers can effectively identify and analyze research topics within the field. This study retrieved relevant publications from the Web of Science Core Collection and conducted bioinformatics analysis. The latent Dirichlet allocation model, which is based on machine learning, was utilized to identify subfield research topics. A total of 4315 articles related to IIRs/IITs were obtained from the Web of Science Core Collection. After excluding duplicates and articles with missing abstracts, a final dataset of 3333 articles was included for bibliometric analysis. The number of publications showed a steady increase over time, particularly since 2000. The United States, Germany, the United Kingdom, the Netherlands, Canada, Denmark, Japan, Switzerland, and France emerged as the most productive countries in terms of IIRs/IITs. The citation analysis revealed intriguing trends, with certain highly cited articles showing a significant increase in citation frequency in recent years. A model with 45 topics was deemed the best fit for characterizing the extensively researched fields within IIRs/IITs. Our analysis revealed 10 top topics that have garnered significant attention, spanning domains such as community health, cancer treatment, brain development and disease mechanisms, nursing research, and stem cell therapy. These top topics offer researchers valuable directions for further investigation and innovation. Additionally, we identified 12 hot topics, which represent the most cutting-edge and highly regarded research areas within the field. This study contributes to a comprehensive understanding of the current research landscape and provides valuable insights for researchers working in this domain.

Exploring Business Environment Policy Changes in China Using Quantitative Text Analysis

A conducive business environment is crucial for establishing a sustainable market economy. This paper aims to quantitatively analyze the evolution of China’s business environment policy, offering valuable insights for future optimization. Focusing on 1335 national-level business environment policies from 2006 to 2023, this study employed a social network analysis (SNA) and the latent Dirichlet allocation (LDA) model to investigate policy changes in terms of the issuing rhythm, collaborating departments, and policy attention. The findings reveal: (1) China has established a mature policy system for its business environment, with both an increasing number and improving impact of related policies. (2) A governance network of the business environment has gradually formed, with the participation of differentiated departments and the domination of one central unit, ensuring efficient collaboration and clear instruction. (3) The attention of the business environment policy has shifted from attracting foreign investment and developing the industrial chain to simplifying bureaucratic approval procedures, smoothing trade circulation, and ensuring legal reliability. This paper’s results serve as an empirical contribution to the field of business environment policy research.

Scoping Review with Topic Modeling on the Diagnostic Criteria for Degenerative Cervical Myelopathy.

This study is a scoping review. There is a broad variability in the definition of degenerative cervical myelopathy (DCM) and no standardized set of diagnostic criteria to date. We interrogated the Myelopathy.org database, a hand-indexed database of primary clinical studies conducted exclusively on DCM in humans between 2005-2021. The DCM inclusion criteria used in these studies were inputted into 3 topic modeling algorithms: Hierarchical Dirichlet Process (HDP), Latent Dirichlet Allocation (LDA), and BERtopic. The emerging topics were subjected to manual labeling and interpretation. Of 1676 reports, 120 papers (7.16%) had well-defined inclusion criteria and were subjected to topic modeling. Four topics emerged from the HDP model: disturbance from extremity weakness and motor signs; fine-motor and sensory disturbance of upper extremity; a combination of imaging and clinical findings is required for the diagnosis; and "reinforcing" (or modifying) factors that can aid in the diagnosis in borderline cases. The LDA model showed the following topics: disturbance to the patient is required for the diagnosis; reinforcing factors can aid in the diagnosis in borderline cases; clinical findings from the extremities; and a combination of imaging and clinical findings is required for the diagnosis. BERTopic identified the following topics: imaging abnormality, typical clinical features, range of objective criteria, and presence of clinical findings. This review provides quantifiable data that only a minority of past studies in DCM provided meaningful inclusion criteria. The items and patterns found here are very useful for the development of diagnostic criteria for DCM.

Personalized anti-tumor drug efficacy prediction based on clinical data

Anti-tumor drug efficacy prediction poses an unprecedented challenge to realizing personalized medicine. This paper proposes to predict personalized anti-tumor drug efficacy based on clinical data. Specifically, we encode the clinical text as numeric vectors featured with hidden topics for patients using Latent Dirichlet Allocation model. Then, to classify patients into two classes, responsive or non-responsive to a drug, drug efficacy predictors are established by machine learning based on the Latent Dirichlet Allocation topic representation. To evaluate the proposed method, we collected and collated clinical records of lung and bowel cancer patients treated with platinum. Experimental results on the data sets show the efficacy and effectiveness of the proposed method, suggesting the potential value of clinical data in cancer precision medicine. We hope that it will promote the research of drug efficacy prediction based on clinical data.

An improved IPA approach driven by big data and its application to customer satisfaction research of energy-saving appliance

Against the backdrop of increasing global demand for reducing greenhouse gas emissions, promoting the use of energy-saving and environmentally friendly products has become a crucial aspect of low-carbon economic development. Customer satisfaction plays a vital role in the promotion of these products. To address the challenges of dealing with big data in the conventional customer satisfaction analysis tool, Importance Performance Analysis (IPA), a machine learning-based method is proposed to improve IPA. Firstly, the Latent Dirichlet Allocation (LDA) model is used to capture users’ opinions on different product topics. Then, the Support Vector Machine (SVM) and Random Forest (RF) algorithms are employed respectively to assess the satisfaction and importance of product attributes, enabling an objective measurement of customer satisfaction and adapting to the current trend of big data. The proposed method is applied to the analysis of water heater satisfaction on the JD platform, obtaining satisfaction levels for 10 topics. The research findings demonstrate that the improved IPA method based on SVM-RF effectively explores customer satisfaction and can provide some improvement strategies for platform managers and manufacturers.

신문기사 빅데이터를 활용한 친환경 섬유의 추이에 관한 연구

The development of environmentally friendly products and services has become a trend, and the development and utilization of eco-friendly textiles with economic value is gaining attention as a new business model. Analyzing and identifying trends and developments in eco-friendly textiles can provide important information and insights for various stakeholders such as companies, governments, and consumers to help them achieve sustainable growth. For this study, we collected and analyzed data from newspaper articles mainly covering the textile and fashion sector from 2000 to June 2023. A total of 12,331 articles containing the keyword 'eco-friendly textiles' were collected, and after performing morphological analysis on the extracted data, Latent Dirichlet Allocation and Dynamic Topic Modeling analysis were performed to identify topics by year. The results of the study are expected to provide strategic guidance and insights for the sustainable development of the textile industry, thereby helping to promote the research, development, and commercialization of eco-friendly textiles.

Two-stage attention network for fault diagnosis and retrieval of fault logs

In industrial systems, textual failure records note the failure mechanisms, the parts involved, and the failure symptoms; these records guide fault analysis and repair. However, case retrieval and feature extraction require extensive prior knowledge and diagnostic expertise; this method is time-consuming and labor-intensive. In this article, we present a novel two-stage framework that automatically extracts and generates features from very large textual records. We use an improved weighted latent Dirichlet allocation model and the Word2vec method to extract topic category and semantic features from fault texts; this approach accelerates training convergence. Next, we build a topic-context attention model in which word-embedding semantic features interact with topic features. Finally, we use classification and similarity calculation models to diagnose faults and retrieve similar cases; this approach ensures feature generation. Our method is very granular in terms of case representation which significantly improves diagnosis. The method robustly identifies similar cases by interrogating vehicle maintenance records.

Topic modeling analysis of Community Savings Groups: evidence from the combined literature

Objective: To identify topics of study related to Community Savings Groups (CSGs) from the literature available. Design/Methodology/Approach: Some phases of natural language processing were implemented. The data were obtained from scientific databases and gray literature. The analysis included 228 abstracts of papers, theses, working papers, and reports. The Latent Dirichlet Allocation model was used to identify the topics. Results: Six topics have been the focus of the discussion about the existence and impact of CSGs in the last two decades. Study Limitations/Implications: Texts without abstracts in English were excluded. Findings/Conclusions: The topics found deal with various aspects on which CSGs have had an impact, such as health, empowerment, primary sector, violence, and other aspects related to existence. Additional evidence is required to consider CSGs as an effective and sustainable mechanism that facilitates well-being.

Application of text mining and coupling theory to depth cognition of aviation safety risk

Aviation accidents have attracted a lot of attention due to the fatalities and considerable property loss. The complexity underlying these accidents is often the result of multiple risk factors coupling together, thereby increasing the difficulty of risks identification and comprehensive controlling. It is necessary to enhance proactive safety management capabilities and aircraft operational reliability through deeply cognitive risk information. This paper explores the application of Latent Dirichlet Allocation (LDA) model of text mining and coupling theory in two aviation safety datasets. The results of applying LDA topic modeling categorize risks across different datasets. Subsequently, the N-K model is employed to measure various coupling modes of risk factors, and the coupling effects between different risk factors were further analyzed. The results indicate that the two datasets identify different risk categories, and the coupling values of the risk factors usually increase with the number of factors. The results also reveal a higher degree of coupling among three risk factors: pilot manipulation, aircraft systems, and aircraft engines in the NTSB dataset. The proposed methodology shows significance in enhancing the accuracy of aviation risk analysis and the efficiency of accident prevention.