Word Clusters Research Articles

Assessing Carbon Dioxide Emissions in Manufacturing Industries: A Systematic Review

Emissions of pollutants and their consequences for the atmosphere have received special attention from international organizations in recent years due to the climate crisis predicted in the next decades. In this regard, the Carbon Dioxide (CO2) produced in industrial sectors is one of the most concerning compounds because of its impact on global warming and climate change. This study developed a systematic review of Carbon Dioxide Emissions from manufacturing industries considering one decade of research documents focused on addressing this problem. For this, different assessments such as the trend of published articles, top-cited studies, the network evaluation of journals, and keywords network evaluation were conducted. After a careful data-driven analysis, research trends were identified. Findings revealed the increased urgency of finding and assessing information regarding the climate crisis due to CO2 emissions as well as revealing which main sectors and research areas have been involved in its investigation. Furthermore, the most influential contributions and clusters of words obtained demonstrate interrelationships among research trends that are focused on finding new paths to generate more sustainable processes in every manufacturing industry. This study aims to generate valuable insights into the role played by manufacturing industries in the context of the environmental situation, revealing trends and key points among the scientific community.

A Review of CiteSpace Visualisation and Analysis of High-Temperature Corrosion Inhibitors for Oil and Gas Fields

With the increasing global energy demand, the exploitation depth of oil and gas fields is gradually increasing. At the same time, importing many high-acid crude oil makes it increasingly heavy and inferior, and its acid value is constantly improving. This change has led to the increasingly severe corrosion problem of oil and gas field equipment, which has become an essential factor affecting the national economy and society's sustainable development. As an economical and practical anticorrosion measure, corrosion inhibitors play a crucial role in the anticorrosion of oil and gas field equipment. Through the research method of biorientation, retrieve the Web of Science database in 2008-2024 about oil and gas field high-temperature corrosion inhibitor research literature information, using CiteSpace measurement analysis software visual analysis in the literature keywords, publications, high citation frequency, cooperation and word clustering information change trend, analyze the research situation of oil and gas field in recent years, summarizes the research hotspot of oil field high-temperature corrosion inhibitor, prominent authors and institutions, reference relationship and development trend. The number of documents on high-temperature corrosion inhibitors in oil and gas fields is smaller, and the authors, institutions, and countries are not closely related. There is less research cooperation on high-temperature corrosion inhibitors in oil and gas fields, and more independent studies exist. China University of Petroleum has the first number of publications, and China is the country with the first number of publications. The study of mass spectrometry for corrosion inhibitors in oil and gas fields is prominent, while the literature on high-temperature corrosion inhibitors is rare.

Perceived Impact of COVID-19 in an Underserved Community: A Natural Language Processing Approach.

To utilise natural language processing (NLP) to analyse interviews about the impact of COVID-19 in underserved communities and to compare it to traditional thematic analysis in a small subset of interviews. NLP and thematic analysis were used together to comprehensively examine the interview data. Fifty transcribed interviews with purposively sampled adults living in underserved communities in the United States, conducted from June 2021 to May 2022, were analysed to explore the impact of the COVID-19 pandemic on social activities, mental and emotional stress and physical and spiritual well-being. NLP includes several stages: data extraction, preprocessing, processing using word embeddings and topic modelling and visualisation. This was compared to thematic analysis in a random sample of 10 interviews. Six themes emerged from thematic analysis: The New Normal, Juxtaposition of Emotions, Ripple Effects on Health, Brutal yet Elusive Reality, Evolving Connections and Journey of Spirituality and Self-Realisation. With NLP, four clusters of similar context words for each approach were analysed visually and numerically. The frequency-based word embedding approach was most interpretable and well aligned with the thematic analysis. The NLP results complemented the thematic analysis and offered new insights regarding the passage of time, the interconnectedness of impacts and the semantic connections among words. This research highlights the interdependence of pandemic impacts, simultaneously positive and negative effects and deeply individual COVID-19 experiences in underserved communities. The iterative integration of NLP and thematic analysis was efficient and effective, facilitating the analysis of many transcripts and expanding nursing research methodology. While thematic analysis provided richer, more detailed themes, NLP captured new elements and combinations of words, making it a promising tool in qualitative analysis. Not applicable. No patient or public contribution.

National interest Through News Lens: A Computer-Based Textual Analysis of COVID-19 Vaccine Coverage in China, United Kingdom, and the USA

This research is a comparative text analysis on the news of Covid-19 pandemic vaccine invention updates in China Daily, The Guardian, and USA Today. The relevant countries of the origin of these media outlets (China, UK and the USA) were in the race of vaccine solutions for the Covid-19. To find out how they represented their country’s updates in comparison to other countries, the study was initiated. Only the text-based news from 1st May to 31st May 2020 was collected from the respective newspapers. The computer-based text analysis using MAXQDA software was used to perform the study based on the theoretical framework of framing. The study found how the news is presented by such globally known national dailies. By analysing their news texts; using word frequencies, word cluster combinations, and semantic associations between the news published during the selected time. A total 105 text-based news from the print edition of the newspapers were listed and 84,295 words were analysed to determine how the Covid-19 vaccine updates were presented by the highest circulated national daily newspapers in China, the UK, and the USA. After the textual analysis, six individual frames were found, and the result indicated three similar frames and three different frames. The similarities and differences such as framing each other’s vaccine outcomes, public health issues and the positive updates of their respective country’s vaccines were addressed from the base of different framing frameworks. Additionally, the coverage of local and foreign news from the individual newspapers was also taken. It has also addressed the geopolitical and socio-economic factors behind the frames. Keywords: Communication studies, mass communication, journalism, media framing, computer-mediated data analysis.

An Evaluation of the Maternal Patient Experience through Natural Language Processing Techniques: The Case of Twitter Data in the United States during COVID-19

The healthcare sector constantly investigates ways to improve patient outcomes and provide more patient-centered care. Delivering quality medical care involves ensuring that patients have a positive experience. Most healthcare organizations use patient survey feedback to measure patients’ experiences. However, the power of social media can be harnessed using artificial intelligence and machine learning techniques to provide researchers with valuable insights into understanding patient experience and care. Our primary research objective is to develop a social media analytics model to evaluate the maternal patient experience during the COVID-19 pandemic. We used the “COVID-19 Tweets” Dataset, which has over 28 million tweets, and extracted tweets from the US with words relevant to maternal patients. The maternal patient cohort was selected because the United States has the highest percentage of maternal mortality and morbidity rate among the developed countries in the world. We evaluated patient experience using natural language processing (NLP) techniques such as word clouds, word clustering, frequency analysis, and network analysis of words that relate to “pains” and “gains” regarding the maternal patient experience, which are expressed through social media. The pandemic showcased the worries of mothers and providers on the risks of COVID-19. However, many people also shared how they survived the pandemic. Both providers and maternal patients had concerns regarding the pregnancy risks due to COVID-19. This model will help process improvement experts without domain expertise to understand the various domain challenges efficiently. Such insights can help decision-makers improve the patient care system.

VERBAL LEXEMES IN THE DERIVATIONAL CLUSTER WITH THE INITIAL WORD SALT IN THE NATIONAL RUSSIAN LANGUAGE

The article deals with semantic characteristics of verbal lexemes that are a part of the derivational cluster – a structural component of lexical and phraseological complex with the initial word salt. The paper analyses the role of the initial word in forming the complex, reveals the causes of semantic and amount differences of particular word clusters that are formed by different lexical and semantic variants of the polysemantic word salt. The article reveals the factors that influence the development of lexical item creative potential: extra linguistic, language system and intra-word ones. The article demonstrates the causes of the disproportion of analysed particular word clusters – factors that have positive and negative impact on word-formation activity of lexical and semantic variants of the word salt. Lexical items of different derivational stages ascending to two lexical and semantic variants of the initial word and items with erased inner form, that are on the periphery of the general word cluster, are analysed. The author develops a hypothesis about semantic connection of these items and lexical and semantic variants of the word salt. The possible reasons of metaphoric meanings appearing are shown. The article gives analysis of semantic shifts revealed in some derived words. The author comes to the conclusion about topicality of the denoted object for the native speakers and peculiarities of development and meaning extension of the word salt in verbal lexemes.

“Track every move”: Analyzing developers’ privacy discourse in GitHub README files

We adopt a socio-material perspective to examine how developers translate privacy, as a social value, into user applications. Our comprehensive survey of the research on developers’ privacy highlights their key position as privacy mediators and their forums as productive settings for unobtrusive studies of their discourse. The open-source code-sharing platform GitHub contains both discourse and code; by focusing on GitHub, we analyzed nearly 60,000 README files created between 2008 and 2020 that include the term “privacy,” studying quantitatively and qualitatively how discourse is translated into code. Using VOSviewer.com, we identified two main word clusters: “security” and “privacy policy.” Voyant-tools.org confirmed these findings, suggesting that some references elaborate on practices that safeguard privacy, while others discuss policy as a means of complying with both public and, ironically, commercial regulations. A closer reading of the files reveals that even privacy enthusiasts may inadvertently promote code that poses threats to privacy.

Integrating word embedding and topic modeling for sentiment analysis: A case study on the social mood on economy

In recent years, textual analysis and embedding spaces have become essential and complementary tools for sentiment analysis in National Statistics Institutes’ research, owing to their ability to summarize discussed topics effectively. Istat has developed an innovative tool, wordembox, which allows external users to explore the outputs of popular word embedding algorithms, such as Word2Vec and FastText. This tool enriches the analysis with a novel graph functionality, enabling users to discover clusters of words and facilitating implicit topic modeling. This article focuses on Social Mood on Economy (SME) posts over a period in which the index recorded a strong downward trend: the first month of the Russia-Ukraine conflict at the beginning of 2022. We compare findings from wordembox with standard topic modeling techniques, including Bayesian Latent Dirichlet Allocation (LDA), Top2Vec, and BERTopic, recent methods that extract clusters from word embedding spaces. These techniques show coherent results, and their combined use in textual analysis may create a synergy that enhances the informative content of synthetic indexes such as ‘Social Mood on Economy Index (SMEI)’.

INOVAÇÃO E TEORIA ATOR-REDE

Sociology of innovation is a transdisciplinary approach to research and development whose theoretical-methodological framework is based on the Actor-Network Theory. The article aims to map scientific communications produced in the literature about innovation and Actor-Network Theory (ANT). As bibliographical research, a semiotic-material approach is used to map these research interests on the Dimensions scientific data platform, seeking to explore their problematization networks via word co-occurrence and clustering with the VOSviewer network analysis software, in addition to describing their translational movements based on the titles and summaries of the mapped research itself and the literature itself in some way related. Two problematization networks about innovation and ANT are explored, one being multidisciplinary (see relationships between different fields of research such as health, management and technologies) and the other interthematic (through actor-words such as “implementation”, “framework” and “knowledge”. Such research interests are crossed by the very semiotic-material complexity of scientific production and communication related to ANT and innovation, performing socio-technical and political-economic processes of invention, negotiation and commercialization between human and non-human actors, of somehow linked to different knowledge and domains of scientific and technological knowledge.

Analyzing the impact of Social Interaction on Stock Market Participation: A Qualitative Study Using NVivo

Background: Stock market participation plays a crucial role in wealth creation and economic welfare. Prior studies show social interaction factors like parental guidance, partner opinions and online networks can influence such financial decisions. However, little is known about their combined impact in developing markets. Methods: This study analyzed the influence of social interaction on stock market participation in Kathmandu Valley, Nepal. Qualitative data was collected through interviews of 10 investors and analyzed using NVivo software. Tools included word clouds, cluster analysis, sentiment analysis and thematic coding. Results: Results indicated that while parents generally lacked knowledge, some were influenced by participating relatives. Partners motivated research through information sharing and encouragement. Community reputation had a positive effect. Internet emerged as the dominant information source compared to offline relationships. Moderately positive sentiments were observed for community, partner and internet influences. Conclusion: Social interactions, particularly through the internet, collectively contributed to stock market participation. However, parental influence was less direct. Partners influenced primary market involvement through discussions. This provides novel insights into socio-cultural determinants of equity investing in an emerging South Asian context. Novelty: The study makes an original qualitative assessment of multiple social drivers on capital market engagement in Kathmandu Valley, adding new dimensions for understanding household finance decisions and developing inclusive capital markets.

Neurodivergent patient experience in a tertiary children's hospital-a qualitative analysis.

Sensory processing challenges are commonly encountered in pediatric patients, particularly in those who are neurodivergent. We previously developed a novel clinical pathway (named "Sensory Pathway") which aimed at improving patient care for those with sensory barriers via staff training, provision of sensory toolkits and early integration of families throughout the hospital stay. We hypothesized that utilization of this pathway will result in improved patient experience and provide valuable feedback to improve care. A voluntary survey was made available to all patients who utilized this resource as part of our hospital wide patient satisfaction survey. Qualitative data was coded using open coding as part of the constant comparison method data using NVivo 12 for Windows software for analysis. Software was used to create word clouds and clusters for visualization, which confirmed the themes and patterns that were noted from initial open coding. Between 2021 and 2022, surveys were obtained from 160 patients who utilized the Sensory Pathway. More than 50% reported that the most helpful components of the pathway were the approach by the staff and sensory tools. The three major themes identified from the survey were (1) Tools and techniques that benefited their children; (2) Positive interactions and communication with the hospital staff, and (3) Suggestions for future improvement. The survey results highlight the importance of having tools readily available to aid with sensory regulation and comfort of patients during healthcare encounters, the value of a positive patient and staff encounter, as well as opportunities for improvement.

Алгоритмы поиска вербальных маркеров идентичности в современном научном дискурсе

The article is devoted to the study of identity verbalization specifics via Data Mining. The research material consists of English texts from Internet scientific repositories and e-libraries devoted to various concepts of youth identity. A methodology based on the use of modern natural language processing and machine learning tools was developed and tested as part of the research. The analysis was carried out using the Natural Language Toolkit library for tokenization and POS-tagging procedures for calculating the frequency of tokens from the «identity» environment. Word Embeddings, pre-trained Word2Vec model and K-means algorithm were used for the subsequent analysis and clustering of words based on their semantic proximity. Gensim library and Scikit-learn library were used to work with the Word2Vec model. As a result, it was proved that in English scientific discourse young person’s identity is verbalized within 9 semantic categories: behavior, communities, communication, education, identity, language, practice, complexity, science, the most common of which are education (33%), language (21%) and communities (18%). N-grams analysis made it possible to identify semantic fields, establish their attributes, and evaluate texts’ similarity, which provided the most accurate vector space search for semantically close n-grams. Optimization made it possible to establish a similarity measure to rank phrases according to the query, as well as assign each n-gram a certain ranking weight. Improvements can be achieved by adding statistical word weighting, such as TF-IDF. The proposed system is capable of searching in a large text array of related phrases with a similar meaning.

Global and Latest Hotspots of Female Genital Plastic Surgery in the Past 20 Years: A Bibliometric and Visualized Review.

An increasing number of surgical and nonsurgical interventions are available in the field of female genital plastic surgery. The rate of female genital plastic surgery has increased by nearly 220 percent over the past 5 years. Despite several studies on the topic, no relevant bibliometric analysis has been conducted. We searched the Web of Science Core Collection for articles related to female genital plastic surgery. CiteSpace 6.1.R2 (Drexel University, USA) and VOSviewer 1.6.10.0 (Leiden University, the Netherlands) were used, and national distribution, institutions, journals, authors, and key words were analyzed and calculated. From 2003 to 2022, 1299 papers in the field of female genital plastic surgery were retrieved. There were more articles produced in the United States, and there were also two institutions in the Netherlands that were highly productive. A wide and close relationship has been established between researchers and institutions conducting female genital plastic surgery. Professor Bouman MB published the most articles on female genital plastic surgery in the Journal of Sexual Medicine. Female genital plastic surgery dominated the top 10 references with the highest local citation score. There were four clusters of key words with the most citations, and the most recently trending key words were "vaginal agenesis," "transgender," and "congenital adrenal hyperplasia." The purpose of this article is to provide a summary of the current research status focusing on female genital plastic surgery. It is hoped that more efforts will be made to promote the development of female genital plastic surgery in the future.

Topic Modeling for Scientific Articles: Exploring Optimal Hyperparameter Tuning in BERT

Topic modeling has emerged as a successful approach to uncovering topics from textual data. Various topic modeling techniques have been introduced, ranging from traditional algorithms to those based on neural networks. In this research, we explore advanced topic modeling techniques, including BERT-based approaches, to enhance the analysis of scientific articles. We first investigate a widely used Latent Dirichlet Allocation (LDA) model and then explore the capabilities of BERT, to automatically uncover latent topics within scientific papers. The goal of this study is to identify the optimal hyperparameter setting for BERT-based topic modeling of scientific articles. We conduct experiments across several scenarios involving combinations of word embedding, dimension reduction, and clustering methods. The results were analyzed based on the coherence values, average execution time, number of topics generated, visualization through the inter-topic distance map, and the top-N-words of each topic. Our findings suggest that combination of RoBERTa for word embedding, PCA for dimension reduction, and K-Means for clustering yields superior results among the tested scenarios. Further evaluation of BERT-based topic modeling is necessary to validate these findings and explore its applications in various academic and industrial contexts. The implications of these advanced techniques could significantly streamline the process of staying updated with scientific literature, potentially revolutionizing research methodologies across disciplines.

Ideologies as conceptual networks: towards a data-intensive approach

ABSTRACT This article introduces a data-intensive approach to visualizing political ideologies as text networks. The methodology combines network theory with collocation analysis from corpus linguistics. Its similarities and differences to Michael Freeden’s morphological approach are highlighted. The prospects are examined by focusing on the case study of Finnish socialism in the early 20th century. Primary sources consist of printed labor newspapers, handwritten newspapers produced by ordinary working people, and parliamentary speeches. The empirical part demonstrates that the network approach is useful for (1) locating key political words based on centrality in the network, (2) identifying clusters of words related to each other more strongly than to the rest of the network, and (3) seeing the structure of an ideological network. The main contribution of the article is methodological for the approach can be applied to other machine-readable sources, both at small and large scales, to automatically extract information on the linguistic patterns characteristic of a political ideology under investigation.

Semi-supervised topic representation through sentiment analysis and semantic networks

This paper proposes a novel approach to topic detection aimed at improving the semi-supervised clustering of customer reviews in the context of customers' services. The proposed methodology, named SeMi-supervised clustering for Assessment of Reviews using Topic and Sentiment (SMARTS) for Topic-Community Representation with Semantic Networks, combines semantic and sentiment analysis of words to derive topics related to positive and negative reviews of specific services. To achieve this, a semantic network of words is constructed based on word embedding semantic similarity to identify relationships between words used in the reviews. The resulting network is then used to derive the topics present in users' reviews, which are grouped by positive and negative sentiment based on words related to specific services. Clusters of words, obtained from the network's communities, are used to extract topics related to particular services and to improve the interpretation of users' assessments of those services. The proposed methodology is applied to tourism review data from Booking.com, and the results demonstrate the efficacy of the approach in enhancing the interpretability of the topics obtained by semi-supervised clustering. The methodology has the potential to provide valuable insights into the sentiment of customers toward tourism services, which could be utilized by service providers and decision-makers to enhance the quality of their services.

Trends in environmental risk and child health research: A bibliometric study, 1990–2022

BackgroundWorldwide, climate change has significantly contributed to the global burden of disease. Children are among the most vulnerable groups of population bearing the brunt of climate change. To explore the development of research on environmental risk and child health, a bibliometric analysis was conducted encompassing literature from 1990 to 2022. MethodsThe study draws upon 6816 published articles related to environmental risk and child health, sourced from the Scopus database spanning the period from 1990 to 2022. The research encompasses several key analyses: trend analysis, country and journal contribution, author contribution using the Bibliometrix R package and co-occurrence analysis was performed using VOSviewer. ResultsThe study highlights the major contributions of the USA and China. The USA leads in both Single Country Publications and Multiple Country Publications. The International Journal of Environmental Research and Public Health stands out as the primary source, with the highest number of documents in this field. Co-occurrence analysis revealed common clusters of words like children, child health, mental health, adolescence, and physical activity. The keyword network map highlighted climate change, social determinants of health, and resilience as the most emerging research topics. ConclusionsThe study highlights the crucial role of environmental factors in influencing child health. The geographical disparities in research output suggest a need for broader research engagement globally, particularly from developing countries, to better address and mitigate the adverse effects of environmental exposures on children's health worldwide.

Physiology education and research in the European Higher Education System — a case study from Portugal

The “Future of Physiology” has become a recurring theme worldwide in discussions amongst Physiology organizations. The Bologna Process fostered a proper higher education environment within Europe, comparable with the USA and UK. This paper presents a current view of Physiology teaching within Portugal, an EU member state and part of the European High Education Area (EHEA). Data was sourced from the governmental agency DGES (from September to November 2022) to identify institutions and curricula featuring disciplines (CU/D) aligned with human Physiology. The teaching modalities, hours, and credits for Human Physiology disciplines were obtained from the institutions’ websites, yielding a database with 365 courses/degrees and 764 distinct Physiology CU/D. In the second stage, a bibliometric analysis of the lecturers’ scientific production from 2017-2022 was conducted using the VOSviewer v 1.6.19 to construct and visualize the key word co-occurrence networks and clusters. A thematic analysis of words in each cluster was then performed to identify common themes. Important divergences appeared, particularly between universities and technical colleges. In technical colleges, Physiology is prevalent in the first year, while in universities, Physiology-related CU/Ds are sequentially present from the first year until late in the course, indicating a progression in advanced knowledge and its application. These differences might be related to the different structural organization of these institutions and likely reflect the differences between facilities, available teaching-learning instruments, and staff preparation. The bibliometric analysis revealed considerable asymmetries in the scientific profile of the teaching staff. revealed Significant differences between university and technical colleges’ scientific production are clear: staff with relevant production were affliated with reference university centers or research units. A pronounced concentration of research interests in two primary domains, classified in the thematic analysis as Medical Physiology and Lifestyle Physiology, was found, with researchers' preferences focusing on biomedical research and innovation, cardiovascular function, sport performance, and well-being. These findings might be common within the EHEA, and do not raise any immediate concerns regarding Physiology as a discipline at present. On the contrary, they suggest that Physiology is clearly recognized as important in health education. Physiology teaching and learning must not lose sight of its primary role as an an integrated science of life required to shape the approach and rationale applied to problems requiring our understanding of health and disease, Physiology teaching and learning continue to be critical in human health education and research. This work is financed by national funds through FCT - Foundation for Science and Technology, I.P., under the UIDB/04567/2020 and UIDP/ 04567/2020 projects. João Gregório is funded by Foundation for Science and Technology (FCT) Scientific Employment Stimulus contract with the reference number CEEC/CBIOS/EPH/2018. This is the full abstract presented at the American Physiology Summit 2024 meeting and is only available in HTML format. There are no additional versions or additional content available for this abstract. Physiology was not involved in the peer review process.

Analysis of Knowledge and Satisfaction in Virtual Clinical Simulation among Nursing Students: A Mixed Study.

Virtual simulation offers a powerful educational tool with considerable, albeit underexplored potential. This technology immerses students in lifelike digital scenarios, fostering the acquisition of knowledge and skills necessary for their future careers. This study aimed to assess knowledge acquisition and satisfaction outcomes among students using a virtual simulation teaching approach. The specific objectives were (1) to compare pre-and posttest knowledge acquisition, (2) to investigate the influence of prior professional experience on knowledge, and (3) to explore satisfaction levels with virtual simulation. One hundred and fifty-nine nursing students participated in a virtual simulation-based clinical intervention, entailing the resolution of a virtual adult patient hospitalized with respiratory pathology. Sociodemographic data and prior professional experience were collected, and knowledge was evaluated through pre-to-post tests. Satisfaction levels were assessed using open-ended questions. Quantitative data were analyzed using descriptive statistics, Wilcoxon, Mann-Whitney U, and Cohen's tests, while qualitative data underwent keyword-in-context analysis. Significant differences were noted between pre- and posttest knowledge levels, with prior experience showing no significant impact on knowledge acquisition. Participants reported high levels of satisfaction. Lexicometric analysis identified four clusters of words related to the key terms "simulation", "learn", "activity", and "knowledge". Virtual clinical simulation effectively enhances knowledge acquisition and fosters satisfaction, with students recognizing the positive impact of this approach on their learning. Consequently, virtual simulation contributes to the training of competent health professionals.

Text Mining and Multi-Attribute Decision-Making-Based Course Improvement in Massive Open Online Courses

As the leading platform of online education, MOOCs provide learners with rich course resources, but course designers are still faced with the challenge of how to accurately improve the quality of courses. Current research mainly focuses on learners’ emotional feedback on different course attributes, neglecting non-emotional content as well as the costs required to improve these attributes. This limitation makes it difficult for course designers to fully grasp the real needs of learners and to accurately locate the key issues in the course. To overcome the above challenges, this study proposes an MOOC improvement method based on text mining and multi-attribute decision-making. Firstly, we utilize word vectors and clustering techniques to extract course attributes that learners focus on from their comments. Secondly, with the help of some deep learning methods based on BERT, we conduct a sentiment analysis on these comments to reveal learners’ emotional tendencies and non-emotional content towards course attributes. Finally, we adopt the multi-attribute decision-making method TOPSIS to comprehensively consider the emotional score, attention, non-emotional content, and improvement costs of the attributes, providing course designers with a priority ranking for attribute improvement. We applied this method to two typical MOOC programming courses—C language and Java language. The experimental findings demonstrate that our approach effectively identifies course attributes from reviews, assesses learners’ satisfaction, attention, and cost of improvement, and ultimately generates a prioritized list of course attributes for improvement. This study provides a new approach for improving the quality of online courses and contributes to the sustainable development of online course quality.