Text Mining Approach Research Articles

Enhancing digital currency adoption: examining user experiences

PurposeThis study aimed to analyse user experiences and perceptions of eRupee banking applications in India, focussing on understanding the key factors driving user satisfaction and dissatisfaction.Design/methodology/approachA comprehensive text-mining approach was employed to analyse 5,176 user reviews collected from the Google Play Store. Sentiment analysis and latent Dirichlet allocation (LDA) were used to classify reviews and uncover prevailing themes.FindingsThe analysis revealed that positive reviews highlighted the themes of usefulness, convenience, satisfaction, app attributes, and ease of use. Negative reviews emphasise issues related to lack of trust, faulty updates, unreliability, security concerns, and inadequate customer support. The Logistic Regression model demonstrated superior performance in predicting user sentiments, achieving an AUC of 0.7926 and an accuracy rate of 77.90%.Research limitations/implicationsThis study was limited to reviews from a single-platform source. Future research could incorporate data from multiple online sources and employ qualitative methods to gain deeper insight. Additionally, longitudinal studies and cross-cultural analyses are recommended to capture evolving user sentiments and global perspectives.Practical implicationsThe findings provide actionable insights for bank managers, app developers and policymakers to enhance eRupee applications by addressing identified issues and leveraging positive aspects to improve overall user experience and satisfaction.Originality/valueThis study makes a novel contribution to the literature on digital currency and advanced text-mining techniques using machine-learning models to analyse user feedback in the context of an emerging economy. The proposed conceptual model and practical recommendations serve as the foundation for future research and practical development in digital financial services.

Reverse Osmosis Membrane Engineering: Multidirectional Analysis Using Bibliometric, Machine Learning, Data, and Text Mining Approaches

Membrane engineering is a complex field involving the development of the most suitable membrane process for specific purposes and dealing with the design and operation of membrane technologies. This study analyzed 1424 articles on reverse osmosis (RO) membrane engineering from the Scopus database to provide guidance for future studies. The results show that since the first article was published in 1964, the domain has gained popularity, especially since 2009. Thin-film composite (TFC) polymeric material has been the primary focus of RO membrane experts, with 550 articles published on this topic. The use of nanomaterials and polymers in membrane engineering is also high, with 821 articles. Common problems such as fouling, biofouling, and scaling have been the center of work dedication, with 324 articles published on these issues. Wang J. is the leader in the number of published articles (73), while Gao C. is the leader in other metrics. Journal of Membrane Science is the most preferred source for the publication of RO membrane engineering and related technologies. Author social networks analysis shows that there are five core clusters, and the dominant cluster have 4 researchers. The analysis of sentiment, subjectivity, and emotion indicates that abstracts are positively perceived, objectively written, and emotionally neutral.

Metastatic Versus Localized Disease as Inclusion Criteria That Can Be Automatically Extracted From Randomized Controlled Trials Using Natural Language Processing.

Extracting inclusion and exclusion criteria in a structured, automated fashion remains a challenge to developing better search functionalities or automating systematic reviews of randomized controlled trials in oncology. The question "Did this trial enroll patients with localized disease, metastatic disease, or both?" could be used to narrow down the number of potentially relevant trials when conducting a search. Six hundred trials from high-impact medical journals were classified depending on whether they allowed for the inclusion of patients with localized and/or metastatic disease. Five hundred trials were used to develop and validate three different models, with 100 trials being stored away for testing. The test set was also used to evaluate the performance of GPT-4o in the same task. In the test set, a rule-based system using regular expressions achieved F1 scores of 0.72 for the prediction of whether the trial allowed for the inclusion of patients with localized disease and 0.77 for metastatic disease. A transformer-based machine learning (ML) model achieved F1 scores of 0.97 and 0.88, respectively. A combined approach where the rule-based system was allowed to over-rule the ML model achieved F1 scores of 0.97 and 0.89, respectively. GPT-4o achieved F1 scores of 0.87 and 0.92, respectively. Automatic classification of cancer trials with regard to the inclusion of patients with localized and/or metastatic disease is feasible. Turning the extraction of trial criteria into classification problems could, in selected cases, improve text-mining approaches in evidence-based medicine. Increasingly large language models can reduce or eliminate the need for previous training on the task at the expense of increased computational power and, in turn, cost.

Exploring the Features and Trends of Industrial Product E-Commerce in China Using Text-Mining Approaches

Industrial product e-commerce refers to the specific application of the e-commerce concept in industrial product transactions. It enables industrial enterprises to conduct transactions via Internet platforms and reduce circulation and operating costs. Industrial literature, such as policies, reports, and standards related to industrial product e-commerce, contains much crucial information. Through a systematical analysis of this information, we can explore and comprehend the development characteristics and trends of industrial product e-commerce. To this end, 18 policy documents, 10 industrial reports, and five standards are analyzed by employing text-mining methods. Firstly, natural language processing (NLP) technology is utilized to pre-process the text data related to industrial product commerce. Then, word frequency statistics and TF-IDF keyword extraction are performed, and the word frequency statistics are visually represented. Subsequently, the feature set is obtained by combining these processes with the manual screening method. The original text corpus is used as the training set by employing the skip-gram model in Word2Vec, and the feature words are transformed into word vectors in the multi-dimensional space. The K-means algorithm is used to cluster the feature words into groups. The latent Dirichlet allocation (LDA) method is then utilized to further group and discover the features. The text-mining results provide evidence for the development characteristics and trends of industrial product e-commerce in China.

Sentiment Analysis of Hotel Reviews in Anyer Beach Tourism Area: A Lexicon-Based Text Mining Approach

This study aims to analyze tourist sentiment towards hotels in the Anyer beach tourism area through online reviews. Sentiments and emotions expressed in these reviews were analyzed using a lexicon-based approach from the National Research Council (NRC) lexicon, which includes emotion categories such as anger, fear, sadness, joy, and disgust. Hotel review data were collected from TripAdvisor, and the analysis involved text preprocessing steps such as cleaning, case folding, stemming, and stopword removal. The sentiment analysis results reveal that most tourists provided positive reviews, with only 14.06% of the reviews displaying negative sentiment. Word cloud visualization identified the words "bad" and "dirty" as frequently appearing in negative reviews, likely pointing to cleanliness and service quality issues as the primary reasons for dissatisfaction. Emotional analysis showed dominant feelings of sadness, anger, disgust, and fear, likely triggered by unmet expectations regarding cleanliness and comfort during their stay. Based on these findings, it is recommended that hotel management in the Anyer beach tourism area address these concerns by implementing regular cleaning routines and staff training to enhance hotel service quality.

Enteric Methane Emission in Livestock Sector: Bibliometric Research from 1986 to 2024 with Text Mining and Topic Analysis Approach by Machine Learning Algorithms.

Methane (CH4) from livestock, particularly enteric CH4 emission (EME), is one contributor to greenhouse gas emissions and climate change. This review analyzed 1294 scientific abstracts on EME in ruminants from 1986 to May 2024, using Scopus® data. Descriptive statistics, text mining, and topic analysis were performed. Publications on EME have risen significantly since 2005, with the Journal of Dairy Science being the most frequent publisher. Most studies (82.1%) were original research, with Northern Hemisphere countries leading in publication numbers. The most frequent terms were "milk", "cow", and "diet", while key research topics included greenhouse gas emissions from livestock, diet composition, and prediction models. Despite progress, some areas like CH4 emission from animals need further investigation.

Analysis of Korean Mothers' Adolescent Issues in Prior- and Post- COVID-19 Period: A Text Mining Approach

Analysis of Korean Mothers' Adolescent Issues in Prior- and Post- COVID-19 Period: A Text Mining Approach

The Effect of Perceived Risk Type on Negative Emotions and Coping Behaviors in Personal Information Leakage: Text Mining Approach

The Effect of Perceived Risk Type on Negative Emotions and Coping Behaviors in Personal Information Leakage: Text Mining Approach

Thoughts and emotions evoked by thinking about own death: American versus Japanese undergraduates.

The prompts "What emotions does the thought of your own death arouse in you?" and "What will happen to you when your body dies?" have been used to induce anxiety in Terror Management Theory. The current study investigated how the responses to these prompts may reveal cross-national differences by using a text-mining approach. Undergraduates in the US (n = 298) and Japan (n = 212) participated in the study. Across both groups, anxiety was the most common emotion. Cross-national differences also emerged, such that students in the US were more likely to mention sadness, funeral, and religiosity for the first prompt, and acceptance, spiritual change, and religiosity for the second prompt. Students in Japan were more likely to mention regret for the first, and sadness, emptiness, and funeral for the second prompt. Results revealed differences and similarities in thoughts and emotions people associate with when thinking about own death.

Attitudes and preferences of the Chinese public towards products made from recycled materials: A text mining approach

Products made from recycled materials, as an environmentally friendly option, have attracted public attention. Understanding public attitudes and preferences towards such products is crucial for their market development. In order to explore the Chinese residents’ attitude and emotional tendency, we analyzed public discussions and topics on products made from recycled materials from Sina Weibo. Meanwhile, LDA and BERT deep learning models were employed to assess the level of public attention, hot topics, and sentiment tendencies in China. Results show a significant upward trend in public interest in products made from recycled materials. Although the fact that most people have a positive attitude towards the environmental concept of products made from recycled materials and support such products, there is not a significant demand for products made from recycled materials, i.e., there is a green attitude-behaviour gap. Results further reveal that factors such as the price of products made from recycled materials, branding, and public skepticism about the sustainability of the products are the main reasons for the gap between environmental awareness and consumer behaviour. By analyzing the public's cognitive structure and psychological characteristics regarding products made from recycled materials through social media data, this paper can help recycling manufacturers understand consumers' needs and expectations, as well as assist policymakers in formulating better circular economy policies.

The incidence and prevalence of Dupuytren’s disease in primary care: results from a text mining approach on registration data

Background The focus of research and management of Dupuytren’s disease (DD) is shifting from relieving symptoms in the later stages of disease towards the prevention of contractures. Treatment services might likewise shift towards primary care. Studying characteristics of DD patients who seek medical care for the first time, may identify a symptomatic target group for early DD treatments. We present the first study that estimates the incidence and prevalence of DD in primary care by applying a text-mining algorithm to registration data. Methods This is a population-based cohort study using electronic health records from Dutch general practices involved in a regional research network. Descriptive statistics were used to describe sex, age, comorbidities and lifestyle factors, the latter two were identified via International Classification of Primary Care (ICPC) codes. Incidence rate was calculated as number of patients with a first contact for DD/1000 person years for the years 2017–2021, point prevalence as the percentage of patients with a contact for DD in 2021. DD contacts were identified using a text-mining algorithm. Results The incidence ranged between 1.41 and 1.72/1000 person years and the overall prevalence was 1.99%. Incidence and prevalence are higher among males and increase with age, peaking between 61 and 80 years. Conclusions Our results of prevalence and incidence of DD in primary care give an insight into the relevant population of patients with symptomatic DD that might be the future target group for potential disease controlling treatments.

Trends and Gaps in the Scientific Literature about the Effects of Nutritional Supplements on Canine Leishmaniosis.

In canine leishmaniosis (CanL), complex interactions between the parasites and the immunological background of the host influence the clinical presentation and evolution of infection and disease. Therefore, the potential use of nutraceuticals as immunomodulatory agents becomes of considerable interest. Some biological principles, mainly derived from plants and referred to as plant-derived nutraceuticals, are considered as supplementation for Leishmania spp. infection. This study provides a systematic review regarding the use of nutraceuticals as a treatment using a text mining (TM) and topic analysis (TA) approach to identify dominant topics of nutritional supplements in leishmaniosis-based research, summarize the temporal trend in topics, interpret the evolution within the last century and highlight any possible research gaps. Scopus® database was screened to select 18 records. Findings revealed an increasing trend in research records since 1994. TM identified terms with the highest weighted frequency and TA highlighted the main research areas, namely "Nutraceutical supports and their anti-inflammatory/antioxidant properties", "AHCC and nucleotides in CanL", "Vit. D3 and Leishmaniosis", "Functional food effects and Leishmaniosis" and "Extract effects and Leishmaniosis". Despite the existing academic interest, there are only a few studies on this issue so far, which reveals a gap in the literature that should be filled.

Customers' sentiment on food delivery services: An Arabic text mining approach

The Covid-19 pandemic has accelerated the shift in organizations' strategies toward innovative online services. Customer reviews on platforms for online ordering and delivery are a vital source of information about how well a business is performing. Businesses that provide food delivery services (FDS) seek to leverage consumer input to locate areas where customer satisfaction could be raised. Sentiment analysis (SA) has been the subject of an enormous amount of English-language research. Despite Arabic's increasing popularity as a writing language on the Internet, not much study has been conducted on sentiment analysis of Arabic up to this point, with a limited number of publicly available resources for Arabic SA such as datasets and lexicons. The present study collects FDS-related reviews in Arabic to conduct extensive emotion mining, taking advantage of Natural Language Processing, feature selection, and Machine Learning techniques to elicit personal judgments, identify polarity, and recognize customers’ feelings in the FDS domain. To demonstrate that the proposed approach is suitable for analyzing human perceptions of FDS, we designed and carried out excessive experiments that assess the utility of each phase. Our highest categorization accuracy was 90 % using Mutual Information with the SVM classifier. The study's findings provide various managerial insights for improving their plans and service delivery, as well as revealing the main reasons for consumer complaints. It also demonstrates how future academics might harness the power of online business reviews in Arabic using a variety of text-mining approaches.

Understanding critical service factors in neobanks: crafting strategies through text mining

Purpose This study aims to analyse and understand customer sentiments and perceptions from neobanking mobile applications by using advanced machine learning and text mining techniques. Design/methodology/approach This study explores a substantial large data set of 330,399 user reviews available in the form of unstructured textual data from neobanking mobile applications. This study is aimed to extract meaningful patterns, topics, sentiments and themes from the data. Findings The results show that the success of neobanking mobile applications depends on user experience, security features, personalised services and technological innovation. Research limitations/implications This study is limited to textual resources available in the public domain, and hence may not present the entire range of user experiences. Further studies should incorporate a wider range of data sources and investigate the impact of regional disparities on user preferences. Practical implications This study provides actionable ideas for neobanking service providers, enabling them to improve service quality and mobile application user experience by integrating customer input and the latest trends. These results can offer important inputs to the process of user interaction design, implementation of new features and customer support services. Originality/value This study uses text mining approaches to analyse neobanking mobile applications, which further contribute to the growing literature on digital banking and FinTech. This study offers a unique view of consumer behaviour and preferences in the realm of digital banking, which will add to the literature on the quality of service concerning mobile applications.

Text mining approach for feature extraction and cartilage disease grade classification using knee MRI radiology reports

MRI radiology reporting processes can be improved by exploiting structured and semantically labelled data that can be fed to artificial intelligence (AI) tools. AI-based tools assisting radiology reporting can help to automatically individuate cartilage grading in textual magnetic resonance imaging (MRI) reports, thus supporting clinicians' decisions regarding medical imaging utilisation, diagnosis and treatment. In this study, we extracted information (clinical findings, observations, anatomical regions, etc.) and classified knee cartilage degradation from medical reports utilising transfer-learning techniques applied to the Bidirectional Encoder Representations from Transformers (BERT) model and its variants, pre-trained on an Italian-language corpus. To realise this objective, we used a dataset of 750 MRI knee reports written by three radiologists who contributed to a manual annotation process to perform text classification (TC) and named entity recognition (NER) tasks. The dataset was obtained from an internal database of the IRCCS SYNLAB SDN. Seventy percent of the dataset was used for training, 10% was used for validation and 20% was used for testing. The best-performing configurations for NER and TC tasks were based on the pre-trained BERT model. The macro F1-scores obtained with the NER and TC models are 0.89 and 0.81, respectively. The accuracies calculated on the test set for both tasks are 0.96 and 0.99, respectively.

Online education – bane or boon? A quantitative plus text mining approach

PurposeThe COVID-19 pandemic and its aftermath sent the entire educational system across the globe topsy-turvy. Virtual classrooms, online lectures and online evaluations became the order of the day, replacing traditional face to face classroom interactions and examinations conducted physically. While it may be possible to reach out to a larger audience in remote places via online platforms, the new medium lacks personal touch of the past, and is known to cause physical and psychological problems for participants. This study collects primary data from a representative sample of students from emerging economies to study the factors that influence intention to pursue online education.Design/methodology/approachANOVA, Kruskal–Wallis test, exploratory factor analysis (EFA) and multiple linear regression (MLR) have been used to test our hypothesis. We have also used text mining to corroborate statistical test results and ascertain the sentiment of students towards online learning.FindingsThis study not only confirms findings in extant literature that “benefits” is an important factor. It also identifies new factors such as “health”, “evaluation”, “class duration” and “student qualification”, that influence student intention to pursue online education. Sentiment analysis shows that students have positive sentiment coupled with trust towards online education. Text mining shows that “mode of class”, “time or duration of class” and “quality of learning” are important features that students consider.Originality/valueThis is one of the few studies to use quantitative plus text mining method of research to understand intention to pursue online education.

Research Synthesizes in Pro-environmental Behavior in Education: A Text Mining Approach

Research Synthesizes in Pro-environmental Behavior in Education: A Text Mining Approach

Uncovering airline service quality dimensions from passengers' online reviews: A text mining approach to validate and extend Servqual

This study investigates airline service quality dimensions by employing text-mining techniques to analyse passengers' emotional responses and experiences with airlines as reflected in their online reviews. The study aims to identify the relationship between these and SERVQUAL dimensions to confirm its reliability in the airline industry and reveal new and promising dimensions of airline service quality. The study contributes to academia by enriching literature on airline service quality and text mining applications, identifying areas for enhancement, and suggesting strategic directions for continuous improvement to practitioners based on passengers' quality perceptions of airline service experiences. With a large dataset from 100 airlines obtained from Skytrax, the study offers a deeper understanding of airline service quality. It encourages using big data and text-mining techniques to explore consumer preferences. The study's findings challenge traditional models and bring out new, context-specific service quality characteristics to provide a greater understanding of passenger experiences. These give the airlines insightful guidance on improving service offerings and fulfilling customer expectations, eventually improving customer satisfaction, loyalty, and competitive positioning.

Text mining approach in chicken meat welfare

The aim of the study was to analyze the aspects affecting broiler welfare with the use of Text Mining technique. This approach converts text into numerical data and analyzes word frequency distributions, enabling the extraction of useful information and the identification of relationships between elements. Text mining has limitations, i.e. ambiguity and context sensitivity, making it difficult to capture nuanced meanings. The search was carried out with Scopus using the term "Welfare" with the keywords "Chicken", "Broiler", "Broiler chicken", and "Chicken meat", to create a database of abstracts. Text Mining and Topic Analysis were performed on the abstracts (1228 documents) using the Software R 4.3.1., analyzing also the weight of bigram and trigram. Publications on broiler welfare are present in the bibliography since 1990's, but in the last 10 years, for the interest of public opinion, the numbers of publications significantly increased (76.5% of all documents published). USA, Brazil, and Europe-27 published 60% of the documents found. The works were published in a high number of journals, but 37% of them are published in only 4 journals (Poultry Science, Animals, Applied Animal Behavior Science and Animal Welfare). Text Mining analysis identified key terms related to the slaughter phase, housing management, and environmental conditions such as light quality and quantity. Moreover, a high correlation was found between some terms, underlying the importance of the effects of rearing, slaughter phases and litter management on broiler welfare. Most of the countries focused their research on some specific topics identified by Topic Analysis, mainly genetic selection, feeding, stocking density, slaughter, and consumer perceptions. Poultry Science published the highest number of papers (18%) and the topics more investigated were growing performance, transport and slaughter, and litter management. In conclusion, the high number of publications on chicken welfare underlines the importance of broiler welfare both in Europe and in other countries, even if it is difficult to identify common research topics among the geographic areas and the evolution over the time.

Text mining of verbal autopsy narratives to extract mortality causes and most prevalent diseases using natural language processing

Verbal autopsy (VA) narratives play a crucial role in understanding and documenting the causes of mortality, especially in regions lacking robust medical infrastructure. In this study, we propose a comprehensive approach to extract mortality causes and identify prevalent diseases from VA narratives utilizing advanced text mining techniques, so as to better understand the underlying health issues leading to mortality. Our methodology integrates n-gram-based language processing, Latent Dirichlet Allocation (LDA), and BERTopic, offering a multi-faceted analysis to enhance the accuracy and depth of information extraction. This is a retrospective study that uses secondary data analysis. We used data from the Agincourt Health and Demographic Surveillance Site (HDSS), which had 16338 observations collected between 1993 and 2015. Our text mining steps entailed data acquisition, pre-processing, feature extraction, topic segmentation, and discovered knowledge. The results suggest that the HDSS population may have died from mortality causes such as vomiting, chest/stomach pain, fever, coughing, loss of weight, low energy, headache. Additionally, we discovered that the most prevalent diseases entailed human immunodeficiency virus (HIV), tuberculosis (TB), diarrhoea, cancer, neurological disorders, malaria, diabetes, high blood pressure, chronic ailments (kidney, heart, lung, liver), maternal and accident related deaths. This study is relevant in that it avails valuable insights regarding mortality causes and most prevalent diseases using novel text mining approaches. These results can be integrated in the diagnosis pipeline for ease of human annotation and interpretation. As such, this will help with effective informed intervention programmes that can improve primary health care systems and chronic based delivery, thus increasing life expectancy.