Text Mining Approach Research Articles

Service quality dimensions in Austrian food retailing – a text mining approach for physical retail stores

ABSTRACT Investigating Service Quality (SQ) and its implications for customer satisfaction has become an increasingly popular research area. Especially in the context of physical grocery retailing, ensuring customer satisfaction has become a key success factor. Most previous research studies apply traditional methods (e.g. surveys) for physical shops and utilize text mining-based approaches mainly for e-commerce. In our paper, we propose a novel approach based on LDA. By combining expert-based word counting analysis with the LDA approach, we confirm that unsupervised text mining based on LDA can be used as a reliable approach to cluster textual comments to SQ dimensions in physical retail settings. We have analyzed over 163,000 publicly available textual customer reviews related to the Austrian market, which is special in terms of its extremely high density of retail outlets, high price levels and a tendency towards traditional form of shopping. Our results show that personal interaction, policies, and product-related aspects seem to be positive drivers of customer satisfaction, while reliability is a clear driver of customer dissatisfaction. Results also show a significantly higher relevance of personal interaction in smaller stores and cities with fewer than 5,000 inhabitants than in other store types and bigger cities. Regarding practical implications, hypermarkets should focus on physical aspects to reduce negative reviews and increase efforts in personal interaction to increase positive reviews. On the other hand, smaller stores should continue to rely on personal interaction to avoid negative reviews and might focus on higher reliability to generate more positive reviews. The applied text-mining approach enables future research with a starting base to analyze SQ dimensions and their relevance in additional countries or area, as e.g. fashion or hardware retail.

Sustainable Green Educational Paths in the Italian Higher Education Institutions: A Text Mining Approach

In response to the global imperative of environmental sustainability, higher education institutions play a pivotal role in shaping a green-conscious society. This study delves into the landscape of Italian university education, analyzing the green educational offer and examining the degree programs with a dedicated focus on environmental sustainability promoted during the academic year 2021–2022. For this purpose, we employed statistical-textual analyses techniques to examine the texts describing the educational objectives and the expected professional outcomes after the completion of the study paths for 179 Italian green degree courses (BA and MS), analyzing a corpus resulting in 144,709 occurrences. In particular, the multifaceted nature of the green educational approach, including its multidisciplinary and interdisciplinary orientation, attention to territorial dynamics, intersectoral collaboration, and the balance between theoretical and applied training, are studied. The results reveal an integration of these crucial elements within the Italian university educational offer. This research addresses the growing importance of environmental sustainability in higher education and provides insights into how Italian universities contribute to this global discourse. The findings contribute to ongoing discussions on refining educational strategies, aligning with global sustainability goals, and fostering a generation of environmentally conscious and skilled professionals.

Understanding the challenges affecting food-sharing apps’ usage: insights using a text-mining and interpretable machine learning approach

Understanding the challenges affecting food-sharing apps’ usage: insights using a text-mining and interpretable machine learning approach

A text mining approach to explore factors influencing consumer intention to use metaverse platform services: Insights from online customer reviews

Metaverse technology has recreated real-world surroundings into a virtual setting that has caught the attention of many consumers and brands. Metaverse platforms are facilitating brands to sell physical and digital versions of their products, and consumers are eagerly purchasing these products. Owing to this dramatic shift, it is crucial to understand the factors impacting user adoption of metaverse platform services. The present study leverages an LDA-based topic modeling approach to analyze 17136 online user reviews of the Highrise Virtual Metaverse mobile platform. The study revealed ten factors impacting consumer intention to use the metaverse platform services that are asset buy-sell experience, availability of virtual assets, visually appealing virtual environment, enjoyment from virtual events, social interaction, social activity, positive experience with the metaverse ecosystem, mobile app-related issues, user account-related issues, and the feature of watch ad-to earn. Building upon the uses and gratification theory and flow theory, the study explained that consumers gain three major gratifications and experience a flow state while using metaverse platform services. Furthermore, it explores the emotions expressed by users within the metaverse platform. Correspondence analysis is performed to understand the factors leading to positive and negative user experiences with the platform services. The study presents crucial practical implications for brand marketers and metaverse platform developers.

A Brief Survey of Text Mining: Domains, Implemented Algorithms and Evaluation Metrics

Among text-oriented applications, Natural Language Processing (NLP) plays a significant role in managing and identifying a particular text data. NLP is broadly used in text mining domains as well. In general, text mining is the process of combining diverse techniques to characterise and transform the text. Hence, the syntactic information and semantic information are utilised together in the NLP model to assist the process of analysing, or extracting the text. On the other hand, the text mining model is examined by different standard measurements, which also vary concerning text objectives or applications. Due to the advent of machine and deep learning models, text mining has become the hot research area used in various domains like classification, recognition, sentiment analysis, and speech-related topics. Though the models are not time-consuming and effective, certain factors are considered for further enhancement of these models. Thus, this survey paper elucidates the evaluation metrics used in text mining approaches by deploying standard algorithms. It explores the literature work on the formerly implemented text mining approaches for analysing the evaluation metrics in text mining. In addition to this, the proposed model to perform text mining in every survey paper is analysed. Further, it provides the algorithmic categorisation of existing research works, discussion on different datasets used with the consideration of various evaluation metrics, and finally categorises the metrics used for analysing the performance of such text mining approaches. This survey work also illustrates the merits and demerits of the existing text-mining approaches. Finally, the research gaps and challenging issues are given to direct future work.

A podcast to teach medical humanities at medical school: a text-mining study of students’ lived experience

ABSTRACT The teaching of medical humanities is increasingly being integrated into medical school curricula. We developed a podcast called Le Serment d’Augusta (Augusta’s Oath), consisting of six episodes tackling hot topics in the modern world of healthcare related to the patient-doctor relationship, professionalism, and ethics. This podcast aimed to provide scientific content in an entertaining way, while promoting debate among medical students. The Le Serment d’Augusta podcast was proposed as one of the various optional modules included in the second- to fifth-year curriculum at the School of Medicine of Sorbonne University (Paris). We asked students to report their lived experience of listening to the podcast. We then used a text-mining approach focusing on two main aspects: i) students’ perspective of the use of this educational podcast to learn about medical humanities; ii) self-reported change in their perception of and knowledge about core elements of healthcare after listening to the podcast. 478 students were included. Students were grateful for the opportunity to participate in this teaching module. They greatly enjoyed this kind of learning tool and reported that it gave them autonomy in learning. They appreciated the content as well as the format, highlighting that the topics were related to the very essence of medical practice and that the numerous testimonies were of great added value. Listening to the podcast resulted in knowledge acquisition and significant change of perspective. These findings further support the use of podcasts in medical education, especially to teach medical humanities, and their implementation in the curriculum.

Identifying missing data handling methods with text mining

AbstractMissing data is an inevitable aspect of every empirical research. Researchers developed several techniques to handle missing data to avoid information loss and biases. Over the past 50 years, these methods have become more and more efficient and also more complex. Building on previous review studies, this paper aims to analyze what kind of missing data handling methods are used among various scientific disciplines. For the analysis, we used nearly 50.000 scientific articles published between 1999 and 2016. JSTOR provided the data in text format. We utilized a text-mining approach to extract the necessary information from our corpus. Our results show that the usage of advanced missing data handling methods, such as Multiple Imputation or Full Information Maximum Likelihood estimation, is steadily growing in the examination period. Additionally, simpler methods, like listwise and pairwise deletion, are still in widespread use.

The Relationship Between Gender Inequality and Female-Victim Intimate Partner Homicide in China: Amelioration, Backlash or Both?

A debate existing in feminist and criminological literature is the plausible macro-level relationship between gender inequality and female-victim intimate partner homicide (FV-IPH). The amelioration hypothesis assumes the reduction of gender-based violence in more gender-egalitarian societies, while the backlash hypothesis anticipates that reducing gender inequality may actually increase males’ violence perpetration against women to maintain their dominance. A third theoretical account hypothesizes a curvilinear relationship that integrates the traditional theses and provides a possible explanation for some inconsistent findings. This study revisited and tested these three macro-level theoretical propositions using detailed incident information on 11,310 Chinese judgment documents of intentional homicides (2017-2019) and multidimensional gender inequality indices across provinces. By disentangling the incident-level effects from the aggregate-level forces, our models enable a more explicit estimation of the relationship between provincial gender inequality and FV-IPH. The results indicated that: 1) backlash processes are more likely to occur with increases in women’s empowerment; 2) the relationship between the degree of egalitarian gender ideology and men’s likelihood of committing FV-IPH conforms to an inverted U. Using an innovative Chinese big-data source and text-mining approach, this study represents a pioneering endeavor, as it furnishes robust empirical evidence to corroborate the curvilinear relationship between cultural gender inequality and FV-IPH in a non-Western context. The implications of our findings underscore the need for tailored policy interventions that take into account the nuanced dimensions of gender inequality, particularly those that are culture-related.

Social Media as Tools for Agricultural Extension in Uganda: A Text Mining Approach

The article discusses the potential of social media as a tool for agricultural extension in Uganda. The authors argue that social media platforms, such as Facebook, X formerly Twitter, WhatsApp, and YouTube, offer a range of opportunities for communication, information sharing, and collaboration among farmers. The study is guided by the Media Richness Theory, which asserts that channels of information based on technology are more effective for transmitting text than other media. The article highlights the challenges faced by traditional extension approaches in reaching remote areas and delivering timely and personalized advice, and suggests that social media can help overcome these challenges. Despite the potential benefits, the authors note that there is limited research on how social media can be effectively utilized for agricultural extension purposes in Uganda. The article concludes by emphasizing the need for agricultural extension workers to utilize social media to engage farmers and improve the effectiveness of agricultural extension services.

Evaluating the Impact of Digital Transformation and Sustainability Strategies on Earnings Management: A Text Mining Approach

Digital transformation has the potential to fundamentally change companies and create value. This study examines the impact of digital transformation and sustainability strategies on the earnings quality of Indonesian listed companies on three sectors: infrastructures, transportation and logistics, and consumer non-cyclicals. Using text mining techniques to measure intensity of digital transformation and sustainability strategies, we found that sustainability strategy shown in the company’s annual report reflects lower level of earnings management especially in accrual earnings management, while companies with digital transformation strategy, particularly in artificial intelligence technology, are less likely to engage real earnings management. Findings of this study provide insights into the effect of digital transformation and sustainability on the quality of accounting information and corporate governance, and offer implications for corporate digital transformation and government regulation.

Let’s talk aliens - Stakeholder perceptions of an alien species differ in time and space

Humans play an integral role in biological invasions, from aiding introductions of alien species to experiencing their impacts and holding the ability to manage them. The importance of understanding the dynamics of stakeholders’ perceptions on alien species is therefore increasingly recognized. In this study, we used anonymous online surveys to contrast recreational anglers’ perceptions towards European flounder (Platichthys flesus, Linnaeus, 1758) in Iceland, where it is classified as a potentially invasive species, to the perceptions prevailing amongst recreational anglers in the species’ native range. We furthermore explored potential temporal changes in the perception of Icelandic recreational anglers. Our results indicate that Icelandic recreational anglers have a highly negative perception towards the European flounder, while in its native range, recreational anglers have positive perceptions towards this species. In Iceland, we have furthermore detected a significant change towards less negative perceptions between the surveys administered in October 2019 and March 2023. Finally, we compared the results of the online surveys and novel, conservation culturomics tools to further explore stakeholder perceptions and public interest in Iceland. The comparison highlighted some limitations that should be considered when using culturomics in very small societies or for small languages. For example, the text mining approaches on newspaper articles and social media conservations detected neutral perceptions in the communication to the public and within the targeted stakeholder group via social media in contrary to the perceptions detected in the online surveys. Moreover, we detected short-term peaks in the public’s interest in European flounder and potential drivers of those peaks using Wikipedia pageviews but Google Trends provided mixed and unreproducible results. Overall, our study highlights that stakeholders’ perceptions towards an alien species as well as the public’s interest in it vary over time and space, though the drivers of these changes are often difficult to identify.

Assessing changes in reliability methods over time: An unsupervised text mining approach

Assessing changes in reliability methods over time: An unsupervised text mining approach

Identifying Sustainability Efforts in Company’s Reports Using Text Mining and Machine Learning

This study delves into the utilization of text mining to scrutinize social and environmental reports of companies, showcasing its effectiveness in evaluation. It explores various text mining techniques and practically applies decision tree, k-nearest neighbors, and naïve Bayes methods. The paper offers guidance on extracting pertinent terms related to four CSR dimensions: Environment, Employee, Social responsibility, and Human rights. Results demonstrate the successful differentiation of text based on these dimensions, leveraging a CSR-relevant dictionary by Pencel and Malascue. Employing document classification techniques, the study constructs four models using distinct text mining approaches for comparative analysis. Through this research, the valuable role of text mining in assessing social and environmental disclosures is underscored, providing insights into optimizing these techniques for evaluations and emphasizing their potential to enhance understanding and decision-making in corporate social responsibility assessments. Keywords: sustainability, text mining, machine learning, Corporate Social Responsibility - CSR, environmental reports

Exploring the evolution trends of port integration policy in China by a text mining approach

Ports are essential and strategic nodes of international trade and economic activities. The integration of port resources helps enhance the optimal division of port functions to further promote economic development. This paper explores the evolutionary trends of port integration policy from 2011 to 2021 in China through a text-mining approach. We first used the Latent Dirichlet Allocation (LDA) topic analysis method to analyze the port integration policies and summarize the evolutionary trends of port policies. In addition, an association analysis was conducted to explore port integration policies' impacts by examining their relationships among the environmental protection, digitalization level, and port development scale. Our findings suggested that China's port integration policy has evolved from specific and simple to abstract and complicated at the managerial level. Port development has enriched from infrastructure construction to the ideology of economic development. Our findings show that China's port integration is gradually improving the port operation. The findings of the study contribute to the extant literature by analyzing the port integration policy evolution in China and can be referred to by other countries.

Traditional Chinese Medicine in Colorectal Cancer Therapy: A Focus on <i>Panax quinquefolium L.</i> through Text Mining and Network Medicine Approaches

Background: This study aimed to identify traditional Chinese medicines (TCMs) with potential anti-colorectal cancer (CRC) properties and their core active constituents. Methods: A comprehensive review of the literature regarding CRC treatment using TCM was conducted using the PubMed database. A text mining approach was employed to ascertain the correlation between TCM and CRC, highlighting the top ten TCMs. The most significantly correlated TCM underwent network medical analysis. Component data were sourced from the TCMSP and HERB databases, while their targets were identified through public databases. Concurrently, various databases were utilized to pinpoint CRC-associated target genes. Network medicine was then employed to ascertain the network proximity between component targets and CRC genes. Potential targets for both TCMs and CRC were mapped and were subsequently input into the String database to craft a protein-protein interaction (PPI) diagram. Visualization and analysis of the TCM-ingredients-targets and PPI diagrams were performed using Gephi 0.9.2. Lastly, DAVID database was used for GO and KEGG pathway enrichment analyses of the intersecting targets. Results: Text mining revealed Panax quinquefolium L. displays the most pronounced anti-CRC properties. Notably, key ingredients of Panax quinquefolium L., including Ginsenoside Rb3, Papaverine, Ginsenoside Rg3, and Ginsenoside Rb1, were found to have substantial impacts on cancer and microRNA-cancer signaling pathways. Conclusions: The TCM Panax quinquefolium L. showcases a strong potential in CRC treatment, particularly due to the efficacy of Ginsenoside Rb3 and Ginsenoside Rg3. This study provides a foundational analysis for further exploration into the therapeutic effects and underlying mechanisms of Panax quinquefolium L. in combating CRC.

Software Requirements Engineering and User Experience Design Modeling of Big Data Analysis using Convolution-Bidirectional Temporal Convolutional Network

The study of user perception and interaction with applications is referred to as user experience, or UX. The intricacy and versatility of software products, from requirements engineering to product functionality are well recognized. UX evaluations are often depends on prototypes, but it's important to consider the semantics embedded in software requirements to ensure project success. In this manuscript, Software Requirements Engineering and User Experience Design Modeling of Big Data Analysis using Convolution-Bidirectional Temporal Convolutional Network (SRE-UEDM-BDA-CBTCN) is proposed. The input data are collected from Requirements dataset. The collected data are given to the Convolution-Bidirectional Temporal Convolutional Network (CBTCN) to Design Modeling of Big Data Analysis user experience based on the dataset. In general, CBTCN does not express any adaption of optimization techniques for determining the ideal parameters to accurate Design user experience. Hence, African Vultures Optimization Algorithm (AVOA) is proposed in this work to improve the weight parameter of CBTCN. The proposed model is implemented and the efficiency is evaluated utilizing some performance metrics like accuracy, precision, specificity, sensitivity and F1-Score. The proposed SRE-UEDM-BDA-CBTCN method provides 28.46%, 21.34 and 33.81% higher accuracy, 22.88%, 26.52% and 34.63% higher Precision and 28.46%, 21.34 and 33.81% higher specificity compared with the existing techniques like Holistic big data integrated artificial intelligent modeling to improve privacy and safety in data management of smart cities (AIM-BDI-SDM), Exploring the factors that affect user experience in mobile-health applications: A text-mining and machine-learning approach (MHA-UED-MLA) and Towards Measuring User Experience based on Software Requirements (TM-UEB-SR).

Quantitative evaluation of the medicine innovation policy in China: based on the PMC-Index model.

Medicine innovation is crucial in promoting the sustainable development of medicine undertakings, which has significant economic and social benefits. China is the main force in global medicine consumption, with a huge demand for innovative medicines. Thus, the Chinese government releases a series of policies aimed at providing scientific and reasonable guidance for medicine innovation. However, there is inadequate quantitative evaluation and comparison of various medicine innovation policies in the existing studies. This paper adopts the approach of text mining and the Policy Modeling Consistency Index (PMC-Index) model to construct an evaluation system and then quantitatively evaluates and compares the traditional Chinese medicine innovation policies (TCMIPs), the biological medicine innovation policies (BMIPs), and the multiple medicine innovation policies (MMIPs) in China. The results indicate that: (1) The three types of drug innovation policies have similarities in content and goal through comparative analysis of high-frequency words, while they also have their own characteristics. (2) The average PMC-Index of 29 TCMIPs is 5.77, which has the highest policy bad rate (21%); the average PMC-Index of 12 BMIPs is 6.21, which has the highest policy good rate (92%); moreover, the average PMC-Index of 35 MMIPs is 6.06, which has the highest policy excellence rate (26%). (3) The BMIPs, MMIPs, and TCMIPs have similar scores on policy object, policy orientation, policy timeliness, policy evaluation, and policy accessibility, while they differ significantly mainly on policy nature, incentive method, policy function, policy issuing agency, and policy instrument. This study contributes to a comprehensive understanding of medicine innovation policies in China, in order to provide theoretical support for future policy formulation and optimization in the medicine industry. Moreover, we expand the application scenarios of policy diffusion theory.

Cause-effect relationships among factors impacting customers’ satisfaction with zero-waste products: a text mining and multi-criteria decision-making approach

Cause-effect relationships among factors impacting customers’ satisfaction with zero-waste products: a text mining and multi-criteria decision-making approach

TREADS: Target Research for Anti-epileptic Drugs Using Data Science

Context: Epilepsy is a common neurological disease and is classified into different types based on features such as the kind of seizure, age of onset, part of brain effected, etc. There are nearly 30 approved anti-epileptic drugs (AEDs) for treating different epilepsies and each drug targets proteins exhibiting a specific molecular mechanism of action. There are many genes, proteins, and microRNAs known to be associated with different epileptic disorders. This rich information on epilepsy-associated data is not available at one single location and is scattered across multiple publicly available repositories. There is a need to have a single platform integrated with the data, as well as tools required for epilepsy research. Methods and Material: Text mining approaches are used to extract data from multiple biological sources. The data is curated and populated within an in-house developed epilepsy database. Machine-learning based models are built in-house to know the probability of a protein being druggable based on the significant protein features. A web interface is provided for the access of the epilepsy database as well as the ML-based tool developed in-house. Results: The epilepsy-associated data is made accessible through a web browser. For a protein of interest, the platform provides all the feature values, and the results generated using different machine learning models are displayed as visualization plots. Conclusions: To meet these objectives, we present TREADS, a platform for epilepsy research community, having both database and an ML-based tool for the study of AED targets. To access TREADS: https://treads-aer.cdacb.in

Analysis of Trends in Yoga Research in Korea Using the Text Mining Approach (2013~2022)

Analysis of Trends in Yoga Research in Korea Using the Text Mining Approach (2013~2022)