Text Mining Applications Research Articles

Patent Technology Trends of Oral Health: Application of Text Mining

Patent Technology Trends of Oral Health: Application of Text Mining

MeSH-Based Semantic Weighting Scheme to Enhance Document Indexing: Application on Biomedical Document Classification

Document indexing phase plays a significant role in text mining applications such as text document classification. The common indexing paradigm is based on terms frequency in documents known as Bag Of Words (BOW)-based representation approach. However, such classical approach suffers from ambiguity and disparity of words. In addition, traditional term weighting schemes, such as TF-IDF, exploit only the statistical information of terms in documents. To overcome these problems, we have been interested in biomedical semantic document indexing using concepts extracted from the knowledge resource MeSH. Thus, we have focused first on a disambiguation method to identify the adequate senses of ambiguous MeSH concepts and we have considered four representation enrichment strategies to identify the best appropriate representatives of the adequate sense in the textual entities representation. Second, we propose to introduce a semantic weighting scheme that quantifies MeSH concept’s importance in documents through their occurrence frequency and semantic similarities with unambiguous MeSH concepts. Our contribution lies particularly in the in-depth experimental study of the performance of these methods and precisely the impact of the semantic weighting scheme on the performance. To do that, three benchmark datasets TREC 2004 genomics, BioCreative II and OHSUMED were used.

Prediction of Certain examinations on AI procedures for Text rundown

Making text synopses from huge volume of unstructured text like client surveys, web log posts and online entertainment posts is a significant assignment in text mining applications. These synopses uncover the valuable data which depicts the whole report or surveys. Rundown errand could be performed utilizing two significant methodologies: Extractive and abstractive methodology. Extractive methodology distinguishes the huge piece of the report that uncovered the whole happy and removes it to shape synopsis. Abstractive approach makes synopsis in light of catchphrases and semantics from the archive, which makes it troublesome when contrasted with the other methodology. The extractive synopsis task is perplexing because of overt repetitiveness, enormous volume of text, changeability and semantics of regular language in the text. The wide pertinence as well as trying nature of the errand has enlivened dynamic research in the space by both scholar and industry specialists. This exploration centers around the plan of AI based frameworks for two center regions connected with text mining, specifically, Component based text synopsis and text comparability location. Existing element positioning and outline frameworks utilize an assortment of strategies including inactive semantic ordering; Innocent Bayes' and other semantics based approaches. Because of the intricacy of the undertaking there is a requirement for creating proficient frameworks. In this proposal, an element positioning framework in light of client inclinations have been created. Three different AI approaches have been embraced for highlight based miniature level extractive text synopsis development.

Kansei engineering for the intelligent connected vehicle functions: An online and offline data mining approach

The big data era enables automakers to mine users’ affective (Kansei) requirements for the car design. However, existing literature mostly applies text mining with users’ online comments, possibly leading to biased results since users without online comments were not considered. To fill in this gap, this paper proposes to jointly analyse users’ online commenting and offline usage big data, and develops a novel framework to efficiently fuse these two datasets for the Kansei engineering of the intelligent connected vehicle (ICV) functions. A behaviour-enhanced large language model is proposed to process users’ online comments; then, users’ Kansei requirements are further jointly analysed with their offline in-cabin behaviour data, by the proposed NLP-MDCEV (natural language process — multiple discrete-continuous extreme value) model, to understand user’s complex discrete and continuous choice decisions in the smart cockpit. In addition, the proposed framework aims to solve the problem of design tasks prioritization, where not all the Kansei requirements can be met if design resources are limited. The proposed framework is applied in the studied new energy vehicle company, with more than nine-months’ online comments and six-months’ offline usage data, where results suggest its merits of economic, efficient, and effective.

Impacts of User Personality Traits on Their Contributions in Idea Implementation: A Moderated Mediation Model.

In the realm of open innovation, users have emerged as a significant external source of innovation that enterprises cannot afford to overlook. Implemented ideas play a pivotal role in driving the iterative innovation of products within enterprises. However, the existing literature still lacks an exploration of specific impact mechanisms on contributions in idea implementation. This study presents a model that delineates the impact of user personality traits on idea implementation contributions, drawing upon theories such as personality trait theory, user engagement perspective, and trait activation theory. Empirical research was carried out by utilizing user data obtained from the Chinese high-tech company Xiaomi's MIUI community. Personality trait indicators were developed through the application of text mining and machine learning techniques. To evaluate the models, a negative binomial regression model, which is well-suited for handling discrete data, was employed. The findings of this study indicate that user openness and conscientiousness positively influence their idea implementation contribution, whereas neuroticism has a negative impact on implementation contribution. Additionally, it is observed that user engagement plays a partial mediating role in the relationship between openness, conscientiousness, neuroticism, and idea implementation contribution. Community incentives can positively moderate the impact of user engagement on the relationship between conscientious personality and idea implementation contribution. This study expands the analysis of the impact mechanism of user idea implementation contributions, which has important theoretical guidance and practical implications for accurately identifying leading users in open innovation communities and enhancing user innovation contributions.

Testing high-dimensional multinomials with applications to text analysis.

Motivated by applications in text mining and discrete distribution inference, we test for equality of probability mass functions of K groups of high-dimensional multinomial distributions. Special cases of this problem include global testing for topic models, two-sample testing in authorship attribution, and closeness testing for discrete distributions. A test statistic, which is shown to have an asymptotic standard normal distribution under the null hypothesis, is proposed. This parameter-free limiting null distribution holds true without requiring identical multinomial parameters within each group or equal group sizes. The optimal detection boundary for this testing problem is established, and the proposed test is shown to achieve this optimal detection boundary across the entire parameter space of interest. The proposed method is demonstrated in simulation studies and applied to analyse two real-world datasets to examine, respectively, variation among customer reviews of Amazon movies and the diversity of statistical paper abstracts.

Optimized Support Vector Machine with Particle Swarm Optimization to Improve the Accuracy Amazon Sentiment Analysis Classification

Text mining is a valuable technique that empowers users to gain a deeper understanding of existing textual data, ultimately allowing them to make more informed decisions. One important application of text mining is in the field of sentiment analysis, which has gained significant traction among companies aiming to understand how customers perceive their products and services. In response to this growing need, various research efforts have been made to improve the accuracy of sentiment analysis classification models. The purpose of this article is to discuss a specific approach using the Support Vector Machine (SVM) algorithm, which is often used in machine learning for text classification tasks and then combined with the application of Particle Swarm Optimization (PSO), which optimizes the SVM model parameters to achieve the best classification results. This dynamic combination not only improves accuracy but also enhances the model's ability to efficiently handle large amounts of text data to achieve better results. The research findings highlight the effectiveness of this approach. The application of the SVM algorithm with PSO resulted in an outstanding accuracy performance of 94.92%. The substantial increase in accuracy compared to previous studies shows the promising potential of this methodology. This proves that the SVM algorithm model approach with Particle Swarm Optimization provides good performance.

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.

Understanding social and clinical associations with unemployment for people with schizophrenia and bipolar disorders: large-scale health records study

PurposePeople with severe mental illness (SMI) experience high levels of unemployment. We aimed to better understand the associations between clinical, social, and demographic inequality indicators and unemployment.MethodsData were extracted from de-identified health records of people with SMI in contact with secondary mental health services in south London, UK. A Natural Language Processing text-mining application was applied to extract information on unemployment in the health records. Multivariable logistic regression was used to assess associations with unemployment, in people with SMI.ResultsRecords from 19,768 service users were used for analysis, 84.9% (n = 16,778) had experienced unemployment. In fully adjusted models, Black Caribbean and Black African service users were more likely to experience unemployment compared with White British service users (Black Caribbean: aOR 1.62, 95% CI 1.45–1.80; Black African: 1.32, 1.15–1.51). Although men were more likely to have experienced unemployment relative to women in unadjusted models (OR 1.36, 95% CI 1.26–1.47), differences were no longer apparent in the fully adjusted models (aOR 1.05, 95% CI 0.97–1.15). The presence of a non-affective (compared to affective) diagnosis (1.24, 1.13–1.35), comorbid substance use (2.02, 1.76–2.33), previous inpatient admissions (4.18, 3.71–4.70), longer inpatient stays (78 + days: 7.78, 6.34–9.54), and compulsory admissions (3.45, 3.04–3.92) were associated with unemployment, in fully adjusted models.ConclusionPeople with SMI experience high levels of unemployment, and we found that unemployment was associated with several clinical and social factors. Interventions to address low employment may need to also address these broader inequalities.

Exploring the determinants of the user experience in P2P payment systems in Spain: a text mining approach

PurposeThis study aims to identify which determinants are responsible for impacting the user experience of three peer-to-peer (P2P) payment services in the Spanish market.Design/methodology/approachA sample of all online reviews (n = 16,048) published in Google Play of three paytech apps—Bizum, Twyp, and Verse—was analyzed using text mining and sentiment analysis.FindingsA holistic interpretation of the seed terms included in each aspect allowed to label them based on the preferences expressed by paytech app users in their reviews. Six latent aspects were identified: ease of use, usefulness, perceived value, performance expectancy, perceived quality, and user experience. In addition, the results of the analysis suggest a positivity bias in the online reviews of fintech P2P app users. Our results also show that online reviews of apps associated with banks or financial institutions, such as Bizum (to a greater extent) or Twyp, show more negative emotions, whereas independent apps (Verse) show more positive emotions. Moreover, the most critical users are those of unidentified gender, while women remain in a more neutral position, and men tend to express their opinions more positively regarding P2P payment apps.Practical implicationsPaytech providers should analyze the problems faced by users immediately after an encounter. By applying text mining analysis, service providers can gain efficiency in understanding user sentiments and emotions without tedious and time-consuming reviews.Originality/valueThis is a pioneering study on peer-to-peer (P2P) mobile payment systems from the user’s perspective because it investigates the emotions and sentiments that users convey through bank reviews.

Optimization of Practical Path of Teaching Reform in Higher Education - Based on Distributed Logistic Model Application

Abstract This study presents a novel approach to the application of distributed logistic modeling for the enhancement of education and teaching in colleges and universities, particularly focusing on the pedagogical goals and curriculum content. Utilizing the abundance and accessibility of educational resources, this research harnesses data from diverse sources such as books, textbooks, catechisms, and blogs. Through the application of text mining and text recognition technologies, preliminary data are extracted for analysis. Subsequent data preprocessing steps involve the removal of extraneous information, null values, and outliers to refine the dataset. The research identifies key determinants influencing educational outcomes, establishing independent and dependent variables for these factors. The logistic and sigmoid functions are employed to compute the loss function, thereby addressing issues related to overfitting. Regularization transformations further optimize the results, culminating in the development of a robust distributed logistic model for education. An illustrative analysis demonstrates the model’s applicability and effectiveness in understanding and improving educational practices. Data presentation: P=0.026<0.05, the independent variable of knowledge base level (x7 ) has a significant effect on the effect of education and teaching and OR-Value=3.11, that is to say, if the knowledge base level rises by one unit, the dependent variable of the impact of education and teaching will be increased by 3.11 magnitude of change.

Research Trends in Sustainable E-Payment Systems: A Study Using Topic Modeling Approach

This article analyses research trends in the domain of sustainable e-payment and finds the research gaps therein by applying text mining technique. Abstracts and indexed keywords of 703 research articles on sustainable e-payment have been analyzed by applying the topic modeling approach and the latent Dirichlet allocation technique to narrow down to ten topics. Corresponding number of articles that fall under those topics are determined to address the research gap. Findings reveal disparity in research trends in different aspects of electronic payment. Research and publication in some areas have witnessed appreciable increase in recent years while other topics have remained relatively less explored. Overall, research and publication in the sphere of e-payment show upward trend, especially in recent years. Topics, such as “problems and solutions in e-payments,” “modern statistical analysis tools,” “digitalization of healthcare,” and “secured e-payment technology,” have attracted rigour and interest of the researchers in the domain. In comparison, publications pertaining to topics, such as “cloud-based e-payment system,” “security in electronic payment,” “future of online payment technique,” and “adoptability of digital payment method,” are lesser in numbers. This disparity in research trends in different aspects of electronic payment opens up avenues for a more holistic intellectual exploration of the knowledge domain. Furthermore, the study also finds that the keywords searched in Scopus, number of citations, and name of the publisher act as key factors that impact the popularity of the articles published in this area.

Text Value and Linguistic Characterization in Chinese Language Literature Based on Text Mining Techniques

Abstract This study applies text mining techniques to deeply analyze Chinese language and literature’s text value and linguistic features. The study adopts the methods of textual disambiguation, vector space modeling, semantic network and Labeled-LDA model. Taking the novels of Yu Hua and Ge Fei as an example, it reveals the differences between the two writers in linguistic features such as using punctuation, average word length, and sentence discrete degree. The study provides a comprehensive heat score for the novels based on three dimensions: reading base group, reading gain, and reading discussion. The results show that the frequency of period use in Yu Hua’s works is decentralized, while Ge Fei’s works are more concentrated. Ge Fei’s average word length is slightly higher, showing a tendency to use multi-syllabic words. The novel popularity and heat scores conform to a power law distribution, reflecting the Pareto rule that 80% of the popularity is concentrated on 20% of the hot novels. This study provides a new perspective on Chinese language and literature through the application of text mining technology, and its methods and tools can effectively enhance the effectiveness and efficiency of teaching.

Deriving Marketing Intelligence Using Online User Generated Textual Content: a Review of Text Mining Applications

Deriving Marketing Intelligence Using Online User Generated Textual Content: a Review of Text Mining Applications

Which skills are the most prized? Analysing monetary value of geographers’ skills on the labour market in six European countries

The objective of the study is to identify those skills that are actually needed by the labour market and allow university graduates to achieve the highest remuneration. To achieve this objective, the authors monitored, for 18 months, online job postings from six countries addressed to geography graduates. Online job postings are the most up-to-date and reliable source of data about the salaries that employers are willing to offer for specific skills or skillsets. A total of 17,397 advertisements were collected, out of which 7,407 included information about the offered salary. Applying text mining and regression tree (classification and regression tree [CART]) analyses, the authors identified skills that significantly differentiate annual salaries. The group of competences associated with higher earnings includes highly specialised geographic information system (GIS), statistical and geological skills. Lower salaries were linked to some general skills such as communicating in a native language as well as some specialised skills, but only to those related to teaching and conducting scientific research.

Ecosystem service evaluation based on local knowledge of residents using spatial text-mining

This study aims to evaluate the ecosystem services of Upo wetland, one of the best-known Ramsar sites in Korea, reflecting the characteristics of the ecological assets and local knowledges in the area. Application of spatial text-mining begins with collecting local perceptions and knowledge of residents on the 17 ecological assets of Upo site and surrounding area. Our results identified five important ecosystem services: flood control during heavy rainfall, water purification by aquatic plants, cultural and natural heritages, agricultural products and water provision for crop cultivation. GIS created a map where these ecosystem services were linked to the locations of 17 ecological assets. This map showed which ecosystem service is associated with particular ecological assets and their characteristics from residents’ perspectives. Mapping local knowledge using the spatial text-mining is able to identify multi-functional bases which provide various ecosystem services in the same location simultaneously. Identification of multi-functional bases can provide information for local government to design an effective and comprehensive management plan considering physical-cultural geography of ecosystem services.

Organizational Traits and Social Badging: Text Mining Application

ABSTRACT This paper, employing a deductive research methodology approach, explores the concept of social badging for organizations from employees’ rating perspective in social media job portals (SMJP). This research attempts to identify the impact of monetary and non-monetary benefits as the antecedents and to explore the moderating effect of management support, organizational culture, and employee-perceived firm image on social badging in SMJPs. Relying on the signaling and person-environment fit theories, this study analyses more than 100,000 employee reviews from social media using text analytics techniques. The findings highlight the essential organizational traits to enhance favorable social badging for organizations. This study also has practical implications by underlying the critical drivers for reputational branding in social media.

Local food experiences before and after COVID-19: a sentiment analysis of EWOM

Purpose – To use Natural Language Processing (NLP) to explore how people feel and what they share online about their experiences with food. In addition, to learn how these experiences have evolved recently, differences before and during the crisis COVID -19 will be explored. Methodology/Design/Approach – A total of 35,001 reviews of restaurants and local cuisine establishments near tourist attractions in the city of Ayutthaya, Thailand, were extracted from the Google Local Guide platform. Several NLP techniques were used to analyse the text data, including sentiment analysis, word cloud analysis, and the N-gramme model. Findings – The results reveal travellers’ hidden sentiments toward dining experiences. Key attributes of experience sharing related to food activities in online reviews were identified both before and after COVID -19. From a theoretical perspective, the findings are relevant for researchers to recognise tourists’ behaviour in sharing local food experiences. From a practical perspective, decision makers will have a better understanding of tourist behaviour to develop and implement appropriate strategies. Originality of the research – This study is the first to analyse and interpret online reviews on Google Maps platform by applying text mining and sentiment analysis in gastronomic tourism research, especially in the context of COVID -19.

Text Mining Application With K-Means Clustering to Identify Sentiments and Popular Topics: A Case Study of The Three Largest Online Marketplaces in Indonesia

Text Mining Application With K-Means Clustering to Identify Sentiments and Popular Topics: A Case Study of The Three Largest Online Marketplaces in Indonesia

Applying Text Mining and Semantic Network Analysis of Tweets to Investigate Social Perceptions on No Kids Zones in Korea

Objectives: This study aims to examine the social perceptions on the ‘No Kids Zones’ considering the continuous spread and the concern of the possibility of increased discrimination against children in our society.Methods: The study used a substantial number of tweets (<i>n</i> = 51,600) with the ‘No Kids Zones’ keyword. First, we probed tweets using Jupyter Notebook to create documents that contain texts between January 2019 and October 2022. Second, we examined TF-IDF, degree centrality, and frequency of words to extract the main keywords and reflect how relevant and connected those words are to a collection of tweet information. Third, based on the 60 keywords we extracted, CONCOR analysis and network visualization were performed using UCINET to examine the co-occurred perceptions on 'No Kids Zones'.Results: The findings demonstrate that the main keywords related to No Kids Zones include kid, parents, adult, children, baby, child and owner in the context of the social target, and ‘cafe’ as social place, and ‘discrimination’, ‘hate’ as social discourse. Second, the analysis showed that there are broad perspectives on children in the context of the No Kids Zones in Korean Society as being either difficult to handle (and, thus, causing inconvenience), or as deserving social understanding and consideration as growing beings.Conclusion: This study suggests a need for improvement both in social understanding and awareness of children and their rights, leading to the prevention of the spread of No Kids Zones. Moreover, parent-focused educational strategies to discipline their children are emphasized for the healthy development of children.