Search

To achieve high-quality development, a critical question needs to be addressed: can enterprise digital transformation effectively alleviate enterprise financing problems by reducing the cost of equity capital? This study uses the text mining to analyze the financial statement from Chinese companies listed on Shanghai and Shenzhen A-share markets between 2011 and 2021, in order to define the digital transformation. Further, this study empirically tests the influencing mechanisms of digital transformation on the cost of equity capital, considering the perspectives of information disclosure quality and stock liquidity. The conclusions are as follows: (i) enterprise digital transformation can significantly reduce the cost of equity capital, and under the control of other variables, the cost of equity financing will be reduced by 8.8% for every 1% increase in digital transformation; (ii) digital transformation not only leads to a decrease in the cost of equity capital through the two independent mediation channels, improving information disclosure and accelerating stock liquidity, but also reduces the cost of equity capital through the chain mediation channel from information disclosure quality to stock liquidity; (iii) heterogeneity analysis finds that the effect of digital information on the cost of equity capital is more pronounced in larger, non-state-owned, non-high-tech and eastern enterprises. This study enriches the research of the influence of digital transformation on external financing, and plays an important role in the promotion of enterprise digital transformation and the formulation of targeted policies. [ABSTRACT FROM AUTHOR]

This study investigates how Quality Management (QM) programmes, particularly the Baldrige excellence framework, provide an approach to enhance healthcare organisational performance. Two independent methods were used to examine the short-term and long-term effects of winning the Baldrige award and the specific influence of common QM practices on results. The first method assesses the Baldrige Award's impact on hospital performance by examining patient survey data and shows that initial quality improvements are not sustained in the long term. The second method uses confirmatory semantic analysis (CSA), a text-mining method, to analyse 22 Baldrige award-winning applications to determine the relationship between QM practices and organisational results in healthcare settings. The results show that only three QM practices – measurement, analysis, and knowledge management (MAKM), leadership, and operations focus – significantly contribute to organisational performance. Furthermore, CSA findings highlight the dominant role of leadership in driving performance outcomes, with other factors in the framework showing nonsignificant mediation effects. By exploring both the overarching effectiveness of QM programmes across different time lengths and specific practices that contribute to performance, this research provides academic insights with practical application in the healthcare industry. Importantly, the findings highlight the nuanced relationship between QM initiatives and organisational excellence. [ABSTRACT FROM AUTHOR]

Artificial intelligence (AI) is increasingly embedded into service firms' operations. However, production systems and operations management scholars have not yet examined if AI-empowered service operations are positively judged by service customers. To bridge this gap, this study draws on the three-factor theory of customer satisfaction applied to online review data, to capture the effect of AI-empowered service operations on overall customer satisfaction, operationalised by means of online review ratings. Based on text analytics techniques applied to a sample of more than 50,000 TripAdvisor ORs covering 35 international hotels in Asia and America, we develop a penalty–reward contrast analysis. The findings reveal that the effects of customer interaction with mechanical AI on customer satisfaction with service operations are asymmetric: positive customer interaction with mechanical AI positively and significantly influences overall customer satisfaction with AI-empowered service operations, whereas negative customer interaction with mechanical AI does not significantly alter customer satisfaction. Taken together, these findings suggest that mechanical AI constitutes a key element of resilient AI-empowered service operations. [ABSTRACT FROM AUTHOR]

This article presents an approach for predicting Lockout/Tagout (LOTO) procedure sheets, which are commonly used in the manufacturing industry to prevent premature equipment restart during maintenance. The prediction problem of energetic devices to lock from machine names is regarded as a multi-task classification problem. The dataset was obtained by processing LOTO sheets in Portable Document Format (PDF). The K-Nearest Neighbours (KNN), Random Forest (RF), and Deep Neural Network (DNN) algorithms were compared for this problem. The best prediction performance was achieved with the DNN method, with top-1 accuracies exceeding 63% and top-2 accuracies exceeding 90% for all devices. The sensitivity analysis conducted on the results indicates that the approach is robust and reliable, regardless of the industrial sector considered. In other words, the approach is not significantly affected by variations in the industry or its specific characteristics. These results suggest that the proposed approach can be used to assist workers in drafting LOTO sheets, and offers strong potential for concrete applications in safety management in the era of smart manufacturing. [ABSTRACT FROM AUTHOR]

Textual data require an analytical trade-off between breadth and depth. Automated approaches locate patterns across large swaths of data points but sacrifice qualitative insight because they are not well equipped to deal with context-determined ways to express meaning, like figurative language. To strengthen the power of automated text analysis, researchers seek hybrid methodologies that combine computer-augmented analysis with sociocultural researcher insights based on qualitative textual interpretation. This article demonstrates a new method, which the authors term metaphor-enabled marketplace sentiment analysis (MEMSA). Building on existing automated text analysis methodologies linking word lists to sentiments, MEMSA adds metaphors that associate topics with sentiments across domains. Using MEMSA, researchers can leverage the sentiment potential of these located metaphors and scale insights to the level of big textual data by employing a dictionary approach enhanced by a specific and useful linguistic property of metaphors: their predictable structure in text (something is something else). This article shows that metaphors add associative detail to sentiments, revealing the targets and sources of sentiments that underlie the associations. Understanding nuanced market sentiments enables marketers to identify sentiment-based trends embedded in market discourse, so they can better formulate, target, position, and communicate value propositions for products and services. [ABSTRACT FROM AUTHOR]

Despite tremendous recent progress, extant artificial intelligence (AI) still falls short of matching human learning in effectiveness and efficiency. One fundamental disparity is that humans possess a wealth of prior knowledge, while AI lacks the essential commonsense knowledge required for learning tasks. Guided by schema theory, we employ the design science research methodology to introduce a novel knowledge-aware learning framework to harness the knowledge-based processes in human learning. Unlike existing pre-trained large language models (LLMs) and knowledge-aware approaches that treat knowledge in considerably different ways from humans, our theoretically grounded framework closely mimics how humans acquire, represent, activate, and utilize knowledge. The extensive evaluations in the context of text analytics tasks demonstrate that our design achieves comparable performance to the state-of-the-art LLMs and enhances model generalizability and learning efficiency. This study takes a step forward by bringing cognitive science into building cognitively plausible AI and human-AI collaboration research. [ABSTRACT FROM AUTHOR]

Order picking in warehouses is a labour- and time-intensive logistical process that significantly impacts the efficiency of supply chains. Although technical progress facilitates the automation of specific order picking tasks, human workers remain the primary actors of order picking. Owing to high operating costs associated with manual order picking, its design and management have been increasingly researched for decades. Because manual order picking systems are socio-technical systems, human factors and workers' interaction with technology are essential for operational success. As innovative technologies become increasingly utilised, such as augmented reality or exoskeletons, warehouse managers need to consider the effects of supportive and substitutive technologies on operational outcomes. However, the potentials and obstacles of using technologies in manual order picking require further investigations. Therefore, this study analyses literature content on supportive and substitutive technologies in manual warehouse order picking and investigates the existing state of research in this field. Text mining is employed to enhance the insights regarding the content analysis. Additionally, future research opportunities on the integration of supportive and substitutive technologies are proposed for manual order picking improvement and development of sustainable and human-centered logistics systems, according to the Industry 5.0 vision. [ABSTRACT FROM AUTHOR]

Cyberattacks have been increasing in volume and intensity, necessitating proactive measures. Cybersecurity risk management frameworks are deployed to provide actionable intelligence to mitigate potential threats by analyzing the available cybersecurity data. Existing frameworks, such as MITRE ATT&CK, provide timely mitigation strategies against attacker capabilities yet do not account for hacker data when developing cyber threat intelligence. Therefore, we developed a novel information technology artifact, ATT&CK-Link, which incorporates a novel transformer and multi-teacher knowledge distillation design, to link hacker threats to this broadly used framework. Here, we illustrated how hospital systems can use this framework to proactively protect their cyberinfrastructure against hacker threats. Our ATT&CK-Link framework has practical implications for cybersecurity professionals, who can implement our framework to generate strategic, operational, and tactical cyber threat intelligence. ATT&CK-Link also contributes to the information systems knowledge base by providing design principles to pursue targeted cybersecurity analytics, risk management, and broader text analytics research through simultaneous multi-modal (e.g., text and code) distillation and classification. [ABSTRACT FROM AUTHOR]

Blockchain (BC) applications in supply chain management (SCM) have recently received extensive attention. It is important to synthesise the extant literature on the field to identify key research themes and navigate potential future directions. This study thus develops an efficient, scalable data-driven review approach that uses text mining and Latent Dirichlet Allocation (LDA)-based topic modelling for automatic content analysis of full-text documents. Our method overcomes the drawbacks of traditional systematic literature reviews using either manual coding or bibliographic analysis for article classifications, which are highly time-consuming and biased when dealing with large amounts of text. 108 papers published between 2017 and 2022 were analysed which identified 10 key research themes, including revenue management, sustainability, traceability, manufacturing system, scheduling in cloud manufacturing, healthcare SCM, anti-counterfeit system, logistics and transportation, system architecture development, and food & agriculture SC. Five future directions are then suggested, including (1) integration of BC and other emerging technologies for global and scalable SCM, (2) crypto-X applications in SCM, (3) BC-enabled closed-loop SCM, (4) the environmental and social impacts of BC-based SCM and (5) decentralised autonomous organisations in SCM. [ABSTRACT FROM AUTHOR]

The Alliance of Genome Resources (Alliance) is an extensible coalition of knowledge bases focused on the genetics and genomics of intensively studied model organisms. The Alliance is organized as individual knowledge centers with strong connections to their research communities and a centralized software infrastructure, discussed here. Model organisms currently represented in the Alliance are budding yeast, Caenorhabditis elegans, Drosophila, zebrafish, frog, laboratory mouse, laboratory rat, and the Gene Ontology Consortium. The project is in a rapid development phase to harmonize knowledge, store it, analyze it, and present it to the community through a web portal, direct downloads, and application programming interfaces (APIs). Here, we focus on developments over the last 2 years. Specifically, we added and enhanced tools for browsing the genome (JBrowse), downloading sequences, mining complex data (AllianceMine), visualizing pathways, full-text searching of the literature (Textpresso), and sequence similarity searching (SequenceServer). We enhanced existing interactive data tables and added an interactive table of paralogs to complement our representation of orthology. To support individual model organism communities, we implemented species-specific landing pages and will add disease-specific portals soon; in addition, we support a common community forum implemented in Discourse software. We describe our progress toward a central persistent database to support curation, the data modeling that underpins harmonization, and progress toward a state-of-the-art literature curation system with integrated artificial intelligence and machine learning (AI/ML).

Contemporary organisations recognise the need for Anthropocene disruptions and transform their business models, restructure their operations, and re-engineer their supply chains to attain greater sustainable objectives and a strong ESG (environmental-social-governance) proposition. Indeed, physical asset management shifted from the negative image associated with asset failure, expensive maintenance, and decommissioning to an enabler of sustainability that allows us to create and capture value from extended lifetime, renewed functions, and increased awareness. In this direction, this study follows a systematic reviewing process enabled by text analytics methods to identify the means and approaches to build a sustainable perspective for physical asset management. Our key contributions and insights are supported by statistics and key features extracted from over 2800 journal articles. We particularly emphasise the research footprint, the evolution, and research trends of the two most asset-intensive sectors (i.e. construction and energy) represented as barriers and enablers of sustainable development. Lacking a unified perspective of the field, this study proposes a conceptual framework that adopts an asset-within-a-system perspective, recognises the links between the stakeholders and holistically integrates the extracted research trends. The knowledge provided here positions physical asset management as a key resource in achieving competitive advantage in the framework of sustainable development. [ABSTRACT FROM AUTHOR]

Research on Blockchain implementation in the Pharmaceutical Supply Chains (PSC) is lacking despite its strong potential to overcome conventional supply chain challenges. Thus, this study aims to provide critical insight into the nexus between Blockchain and PSC and further build a conceptual framework for implementation within the pharmaceutical industry. Following a systematic literature review and text mining approach, 65 interdisciplinary articles published between 2010 and 2021 were studied to capture the decade long developments. Descriptive and thematic analysis showcases nascent developments of Blockchain in PSC. The drivers and barriers to adoption, implementation stages, and applications identified through the thematic analysis guide in setting the agenda for future research, primarily focussing on the use of Blockchain for drug counterfeiting, recall issues, along with other sector-specific challenges such as patient privacy, regulations and clinical trials. Research on Blockchain for PSC has been slow compared to other sectors, but has accelerated since the Covid-19 pandemic. Identified influential factors, implementation process and apparent applications are expected to influence researchers and practitioners in developing a roadmap for adopting Blockchain in the pharmaceutical industry. The proposed conceptual framework is novel and provides valuable directions to producers, regulators and governments to implement Blockchain in the pharmaceutical industry. [ABSTRACT FROM AUTHOR]

The COVID-19 pandemic created the opportunity for various educational resources to be more widely used by learners studying remotely, including in India. This study examines the availability and type of content offered by two of the most prominent Indian educational sites on YouTube. This study included content analysis, sentiment analysis, and text mining to determine the sentiment of viewers, the trend of videos, the growth of videos, and the regions where the majority of videos were generated and uploaded, among other things. This study made use of two well-known general domain educational resources, namely eGyanKosh and E-PGpathshala. Using the channel ID of each channel, Webometric Analyst software was used to collect raw data, and R-Studio was used to analyse audience sentiments on the accessible videos. Compared to subject-specific videos, the channel e-GyanKosh uploads more generic videos, such as memorials, lectures, and professors’ talks. On the other hand, more subject-specific videos are being added to e-PGpathshala. The majority of user responses were positive, indicating that viewers are satisfied with the YouTube videos made available by these two educational resources. [ABSTRACT FROM AUTHOR]

Using methods such as Latent Dirichlet Allocation (LDA) and content analysis, this paper does a comprehensive analysis of Anatolia‘s contributions to tourism and hospitality research over the last 27 years, analyzing publishing trends, regional distribution, and topic evolution. The results show a significant increase in worldwide contributions, covering 92 nations, and an interdisciplinary strategy in line with the UN Sustainable Development Goal (UNSDG) 11. Important subject clusters are identified by the study, underscoring the journal’s growing influence and its part in determining the course of future research. Through the identification of emergent topics, the study highlights Anatolia‘s engagement in varied topics and offers a strategic framework for future research. [ABSTRACT FROM AUTHOR]

This study explores the relationship between AI applications and supply chain concentration. We measure the AI applications of Chinese listed firms based on text analytics on annual reports from 2007 to 2021. Our results show that AI applications reduce supply chain concentration, and these results are robust to endogeneity examination. In addition, AI reduces companies' supply chain concentration by enhancing their bargaining power and, in turn, improving their operational performance. [ABSTRACT FROM AUTHOR]

An in silico target discovery pipeline was developed by including a directional and weighted molecular disease network for metabolic dysfunction-associated steatohepatitis (MASH)-induced liver fibrosis. This approach integrates text mining, network biology, and artificial intelligence/machine learning with clinical transcriptome data for optimal translational power. At the mechanistic level, the critical components influencing disease progression were identified from the disease network using in silico knockouts. The top-ranked genes were then subjected to a target efficacy analysis, following which the top-5 candidate targets were validated in vitro. Three targets, including EP300, were confirmed for their roles in liver fibrosis. EP300 gene-silencing was found to significantly reduce collagen by 37%; compound intervention studies performed in human primary hepatic stellate cells and the hepatic stellate cell line LX-2 showed significant inhibition of collagen to the extent of 81% compared to the TGFβ-stimulated control (1 μM inobrodib in LX-2 cells). The validated in silico pipeline presents a unique approach for the identification of human-disease-mechanism-relevant drug targets. The directionality of the network ensures adherence to physiologically relevant signaling cascades, while the inclusion of clinical data boosts its translational power and ensures identification of the most relevant disease pathways. In silico knockouts thus provide crucial molecular insights for successful target identification. [ABSTRACT FROM AUTHOR]

In this paper, we posit that the ‘global’ status of the pandemic is not an essentialized feature of the crisis, but a product of social construction by political leaders. More specifically, we examine how political leaders of a superpower and a peripheral nation produce the pandemic's globality through crisis geographies from above and below. Utilizing a mixed methods framework, we analyse public speeches by Donald Trump of the United States and Rodrigo Duterte of the Philippines through a critical approach to text analytics. Quantitatively, we found that besides mentioning their own homelands, Western countries featured more prominently in Trump's speeches while Asian neighbours were more salient in Duterte's speeches during the pandemic. However, the United States and China were consistently the most central in the crisis geographies of the pandemic of both speakers. Qualitatively, we further characterized the discourses surrounding these global pronouncements as: (a) collective reflexive positioning on the world stage, (b) charting zones of hope and (c) scapegoating zones of blame. Taken together, implications of this work are discussed in terms of understanding pandemic leadership in national and international contexts, recognizing its negotiated embeddedness in global structural hierarchies and enhancing critical approaches to geopolitical psychology. [ABSTRACT FROM AUTHOR]

With the increase in infertility cases recorded over the last 20 years, there is a considerable demand for assisted reproductive treatments (ART). However, there is significant variation in the availability of such treatments across different countries. Legislation on assisted reproduction is influenced by various cultural expressions, making it seemingly impossible to create a single representation adaptable to different contexts. This work investigates the cultural representations of ART in Italy and Spain. We collected 1,735 articles from two Italian and Spanish newspapers, with all the articles containing the respective translation of ART from 2013 to 2022. The two corpora were analyzed using the Emotional Text Mining (ETM) methodology. The analysis produced 3 clusters in the Italian corpus and 5 clusters in the Spanish corpus. From the Italian results, a view of ART emerged that is linked to ethical limitations and the ideal of the traditional family. In contrast, the Spanish results depict ART in terms of community, rights, public health, and birth seen in itself. In conclusion, this study highlights the strong differences between Italian and Spanish cultures regarding ART. The results could be used to improve clinical practices and legislation surrounding ART. [ABSTRACT FROM AUTHOR]

In the last decade, the fast technological and social transformations have been placing new demands on Higher Education (HE) systems to update their educational offers. Grounded in the broader discourse on the impact of such transformation on HE, this article relies on Text Mining (TM). We consider as a case study the Italian HE system, providing an overview of the university education in the last 10 Academic Years. We automatically analyse 54,535 learning outcomes of degree programmes to identify the relevant topics with Named Entity Recognition, a technique of TM. For each topic, we measured its trend in time and coverage on a geographical basis and in the disciplinary fields. We detected 6062 different topics, among these the most growing are artificial intelligence, sustainability, rare diseases, and ethics. The findings reveal that topics related to hard sciences register higher occurrence than the ones concerning humanities and social sciences. Furthermore, we observed that universities are overcoming the boundaries of disciplinary fields, promoting knowledge contamination and vertical specialisation. The proposed approach can advance studies in HE literature for effective and efficient analysis. The findings can inform policies and practices in HE on evolving learning outcomes and educational offerings, even across different countries and disciplines. [ABSTRACT FROM AUTHOR]

The interaction between a mother and child stands as one of the most profound and intricate human connections, weaving a rich tapestry of behavioral and emotional bonds during the formative years. Although mother–child interactions have received substantial attention in the developmental science literature, few studies have tapped into the extensive corpus of speech data available to uncover the nuances of these interactions across developmental stages. This study applied text mining and sentiment analysis on narratives extracted from mother–child conversations to identify the developmental trend of mother–child interactions from early to middle childhood. The results, based on three key areas of dyadic interactions, demonstrated a shift toward more balanced turn-taking dynamics and linguistic congruence as children age. Also, there was a significant interdependence of mother and child expressed emotions across time. Further investigation of the dyadic emotionality revealed a nonlinear effect of mother-expressed emotion on child-expressed emotion: mother-expressed negative emotions followed a cubic-like pattern, while positive emotions followed a mild quadratic trend. Taken together, the findings of this study present a picture of progressive augmentation of mother–child synchrony over time. [ABSTRACT FROM AUTHOR]

The Systems Engineering Research Center (SERC) is a University Affiliated Research Center (UARC) of the US Department of Defense (DoD) formed in 2008 with more than 20 collaborator universities in the United States. Over the last decade, SERC has conducted research with Principal Investigators from universities within the SERC network, as reflected in technical reports (TR). These reports describe detailed information and analysis of the conducted research for every project under SERC support, such as written records of experiments or results of a scientific project. We analyzed the TRs from 2009 to early 2023 to identify research streams, topics, and evolution in systems engineering (SE) research using text mining and network analysis techniques, such as Louvain Community Detection and word similarity. As a result, we identified four major research streams over a decade of research projects, along with insights about topics and the evolution of SE within this time frame. Finally, we distinguished most profile authors and their most significant collaborations and networks. [ABSTRACT FROM AUTHOR]

Despite the plethora of research on computer-supported collaborative writing, previous studies have failed to provide an adequate analysis of the quality and quantity of multi-authored texts due to the vast amount of unstructured data. This study aims to expand the current research by contributing new perspectives to the understanding of students' collaborative writing interactions and strategies. Nineteen EFL learners, divided into five groups, were asked to collaboratively write a literature review on a selected research topic using Google Docs. The qualitative and quantitative analysis of the data, supported by text mining using DocuViz, revealed that the groups demonstrated patterns of interactions along the continuum of equality and mutuality. However, due to the nature of the required task, groups with the same collaborative interaction patterns exhibited some writing strategy variations. Text visualization analysis further revealed that the groups adopted more than one writing strategy to complete the task. They tended to start with an outline in which the task was divided, and students worked either in parallel or sequentially. This was followed by cooperative revisions or a synchronous hands-on style before the task's due date. By using multiple data analyses, this study distinguishes between interaction patterns and writing strategies, two concepts previously used interchangeably. Methodological and pedagogical implications are also presented. [ABSTRACT FROM AUTHOR]

Are social media posts with emoji more engaging? Guided by the media richness theory, this study explores the relationship between visual (i.e., emoji) and textual content, and how they collectively impact user engagement with peer-to-peer accommodation brands. A three-stage sequential design using naturalist data, including text mining, frequent/rare itemset mining, and one-way ANOVA, was used. This study revealed that the combination of { Travel Tips and Inspiration, } and { Interaction and Motivation, } tended to result in an increased amount of likes and shares in social media posts. By theoretically revealing and empirically examining the complex relationship between verbal and visual content, this study enriches the theoretical understanding of media richness in tourism brands. Practically, this study provides actionable guidelines for tourism brands to increase user engagement by effectively using visual-verbal content. [ABSTRACT FROM AUTHOR]

Preparing the Manual on Uniform Traffic Control Devices (MUTCD) involves gathering inputs from various public and the National Committee on Uniform Traffic Control Devices (NCUTCD) sponsoring agencies. The NCUTCD assists in developing standards, guidelines, and warrants for traffic control devices and practices employed to regulate, warn, and guide traffic flow on roadways. This organization advises the Federal Highway Administration (FHWA) and other relevant agencies on suggested updates and interpretations to the MUTCD and other nationally recognized standards. Examples of such sponsoring agencies include AASHTO, ASCE, Institute of Transportation Engineers (ITE), American Highway Users Alliance (AHUA), National Association of City Transportation Officials (NACTO), National Association of County Engineers (NACE), International Bridge, Tunnel and Turnpike Association (IBTTA), and American Traffic Safety Services Association (ATSSA). Other national and regional agencies have also been invited to provide feedback on the draft manual. Although all comments are considered valuable, those from federal agencies may hold more weight due to their expertise in specific subject matters. This study utilized text-mining techniques to analyze the comments from the sponsoring agencies, aiming to identify commonalities and distinct features in their feedback. The main question addressed was whether each agency effectively represented its interests and if there were shared interests among them. The study also explored the suggestions, questions, and recommendations raised by each agency. The findings revealed that some concerns were shared among agencies, although in most cases, they represented individual interests. Specifically, some agencies shared a common interest in speed limits, whereas others had similar topics concerning signs and markings. Other shared interests are bike lanes, 85th percentile speed, and pedestrian- and bus lane–related topics. This study's insights into the interests and concerns of various MUTCD sponsoring agencies can aid in creating more effective, engaging, collaborative, and well-rounded technical documents. As a limitation, this study only used the current MUTCD revision comments, and hence the results reflect only recent concerns from the agencies. Practical Applications: The Federal Highway Administration collects comments from both the general public and NCUTCD sponsoring agencies for modifying the MUTCD. This study used the comments from the NCUTCD sponsoring agencies submitted by May 2021 and conducted supervised and unsupervised text mining analysis to understand any available patterns, differences, or commonalities in the agencies' concerns in shaping the MUTCD. The findings indicate the presence of various shared interests among the agencies and some specific features that were specific to the agencies. In addition, it was observed that the majority of the agencies have a great concern for the safety and well-being of society by showing a common interest in safety influencing factors such as speed, road signs, and the definition and use of the 85th percentile speed. This understanding can foster greater collaboration among the agencies, leading to more well-rounded and comprehensive guidelines. [ABSTRACT FROM AUTHOR]

In the text mining area, prevalent deep learning models primarily focus on mapping input features to result of predicted outputs, which exhibit a deficiency in self-dialectical thinking process. Inspired by self-reflective mechanisms in human cognition, we propose a hypothesis that existing models emulate decision-making processes and automatically rectify erroneous predictions. The Self-adaptive Reflection Enhanced pre-trained deep learning Model (S-REM) is introduced to validate our hypotheses and to determine the types of knowledge that warrant reproduction. Based on the pretrained-model, S-REM introduces the local explanation for pseudo-label and the global explanation for all labels as the explanation knowledge. The keyword knowledge from TF-IDF model is also integrated to form a reflection knowledge. Based on the key explanation features, the pretrained-model reflects on the initial decision by two reflection methods and optimizes the prediction of deep learning models. Experiments with local and global reflection variants of S-REM on two text mining tasks across four datasets, encompassing three public and one private dataset were conducted. The outcomes demonstrate the efficacy of our method in improving the accuracy of state-of-the-art deep learning models. Furthermore, the method can serve as a foundational step towards developing explainable through integration with various deep learning models. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Small Business & Entrepreneurship is the property of Routledge and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

This article aims to critically understand the current state of the art of Public-Private Partnerships (PPPs) in the health sector and to highlight implications useful for implementing sustainability-oriented PPPs. By employing text mining to analyze the sampled articles, we identify the main themes distinguishing healthcare PPPs and sustainability. We critically discuss the narrative underlying the results achieved in terms of emerging topics: governance, managerial tools, barriers, advantages/disadvantages, and big data. Finally, we propose a literature-driven framework on PPP management that identifies implications – systemic approach, technical managerial skills, governance balance, operational instruments – that can facilitate the development of sustainability-oriented PPPs in the healthcare sector. [ABSTRACT FROM AUTHOR]

In an era characterized by constant advancements in computer science, web novels represent an extensive and intricate form of text that presents unique challenges for automated processing. This investigation aims to address the issues associated with the time-intensive, laborious, and error-prone nature of text processing within web novels. It presents a novel joint entity-relationship extraction model that is enhanced by various features. By leveraging a combination of computer vision and natural language processing techniques, the extraction of named entities and relationships is modeled in a unified framework to optimize text feature mining. The employment of bidirectional long-short term memory networks and multi-layer perceptron equips the model with the capability to effectively extract entity relationships from web novels comprehensively. Experimental outcomes indicate that the model achieves an F1 score of 72.4%, marking a notable enhancement over traditional pipelined models. This study offers robust tools and methodologies for computers to process extensive and complex textual data, further integrates computer vision with natural language processing, and broadens the potential applications within the domain of information processing. [ABSTRACT FROM AUTHOR]

Not all relevant data come in structured formats. We created this teaching case to introduce students to an important data analysis technique that can be used on unstructured data: text analytics. This case focuses on why MD&A disclosures may provide auditors, regulators, and investors with decision-relevant information during the global pandemic. There are a wide variety of tools that can be used to introduce accounting students to text analytics. In the Teaching Notes, we provide instructions for Alteryx, a technology that offers a low-code solution to text analytics. Low-code solutions allow faculty and students to focus on critical thinking and applying text analytics to accounting. The learning objectives are (1) expand students' understanding of text analytics in an accounting setting, (2) develop students' skills necessary for performing text analytics, and (3) expand students' critical thinking skills as they apply text analytics in accounting or business contexts. Data Availability: Data are available from public sources cited in the text and materials that are available for download. [ABSTRACT FROM AUTHOR]

Background: Rockfalls pose a serious threat along the main road network, representing a major hazard in mountainous territory and causing damage and victims. Currently, susceptibility mapping represents a starting point to identify areas more susceptible to rockfall occurrence, a key approach in land use planning and risk management. Despite the extensive use of these maps by decision makers and administrators, the usability of such maps over time and their reliability represent a poorly discussed and examined feature. Methods: Here, we proposed a-posteriori analysis of a three-year-old rockfall susceptibility map, generated along the main road network of the Aosta Valley, an alpine region of north-western Italy. To verify map consistency over time, we implemented a dual-analysis in GIS-environment and by text mining, to respectively analyse the geocoded data and textual information derivable from the regional landslide inventory. The first one allowed us to extract rockfall events occurred after the susceptibility map generation. By this way, we operated to spatially and temporally verify the map consistency. Jointly, the textual information reported in the Event Description Form, linked to each geocoded event, are being exploited. This allowed us to derive relevant information about occurred damage and their degree, presence of protective measures or secondary roads, i.e. involvement of, farm or forestry, road. Results: The implemented approach allowed us to prove the quality of the previous map in terms of reliability, robustness and degree of fitting respect to the succession of rockfall occurrence over time. After only three years as many as 198 rockfall events have been occurred and collected since the map was generated. Particularly, 80% of rockfall fit with "high" and "very high" susceptibility classes, and pointed out large involvement of main roads in rockfall occurrence, representing the most affected target with damage to road pavement and vehicles, as well as a relevant involvement of existing rockfall barriers and of the dense network of forestry roads and footpaths that characterize this alpine region. Results: The proposed approach representing a starting point in landslide susceptibility map verification and usability as valid instrument for a reliable land planning. [ABSTRACT FROM AUTHOR]

The purpose of this study is to identify how sustainable fashion brands communicate with consumers on social media, specifically, Instagram. By applying a data mining technique to analyze brand posts and consumer comments, we thoroughly examine how consumers engage with sustainable messages from each brand and how those engagements are associated with brand posts. A sample of six sustainable fashion brands was selected, including Eileen Fisher, Everlane, Girlfriend Collective, Patagonia, Reformation, and Stella McCartney. Public posts of the six brands and corresponding consumer comments on Instagram between November 1, 2019 and November 1, 2022 were collected. LDA (Latent Dirichlet Allocation) text mining technique was applied to extract topics from each brand’s posts and follower comments. A fixed effects linear panel model was then employed to examine if consumer comments are significantly associated with sustainable messages from each brand. Ten major sustainability-related themes were identified from brand posts, and four major sustainability-related themes were discovered from consumer comments. The linear panel results provide preliminary evidence that the sustainability-related themes from consumer comments are positively influenced by the sustainability-related themes from brand posts, indicating that brand posts indeed affect consumers’ opinions about sustainability. [ABSTRACT FROM AUTHOR]

AbstractWho influenced whom during the 2008 crisis? Did academic economists shape central bankers’ attitudes towards fiscal policy, or did central bankers impose their agenda? In an attempt to answer these questions, we analyse established attitudes and yearly topics found in speeches by bankers from six central banks and in working papers published by academic economists. Methodologically, both attitudes and topics are reconstructed through textual analysis. The results show that context matters. [ABSTRACT FROM AUTHOR]

The employment policies targeted at university graduates, which are exceedingly valuable to the national human resource, are closely related to the national economy and people's livelihood. The employment policies for college students are essential pathways for promoting high-quality job placement for graduates, making the review and evaluation of relevant policies exceedingly significant. This study analyzes the university-student employment policies issued between 1997 and 2023; the researchers utilize text mining and content analysis and refer to the policy indicators designed by existing scholars to develop an evaluation index for college student employment. A PMC index model was constructed to quantitatively evaluate 9 selected policy samples. The results indicate that P5, P6, and P7 have good consistency ratings; P8, P4, and P9 have acceptable consistency ratings; and P2, P3, and P1 have low consistency ratings. The average score for the 9 policy samples is 5.03, reflecting an overall satisfactory quality of China's college student employment policies. By constructing a PMC surface, the model visually reveals certain deficiencies in China's college-student employment policies in regard to policy design, policy tools, and policy content. This study provides countermeasures and proposals from aspects such as policy nature and policy measures. [ABSTRACT FROM AUTHOR]

Background: Violence against Emergency Medical Services (EMS) personnel vary between studies. Current studies are mainly based on self-reporting, thus other designs are needed to provide more perspective. The purpose of this study was to explore the rate and predictors of violent behavior targeted at EMS personnel by exploring the Electronic patient care records (ePCR) documentation by EMS personnel. Methods: This was a retrospective cohort study of EMS patients in Finland. The data were collected from three regions between 1st June and 30th November 2018. Text mining and manual evaluation were used to identify and explore predictors of violence targeted at EMS personnel from the ePCR narratives. Multivariable logistic regressions were used to determine factors that were independently associated with violent behavior. The results are presented with odds ratios (ORs) with 95% confidence intervals (CIs). Results: The EMS personnel reported experiences of violence in a total of 297 identified missions (0.7%) of all EMS missions (n = 40,263). The violence was mostly verbal (62.3%) and the most common violence perpetrator was the patient (98.0%). The police were alarmed to many missions where violence was reported (40.7%). Sometimes violence occurred suddenly although the police were present. The multivariable logistic regression model indicates that violence occurred typically in urban areas (OR 1.699; 95% CI 1.283 to 2.248), at weekend nights (OR 1.357; 95% CI 1.043 to 1.765), by male (OR 1.501; 95% CI 1.160 to 1.942), and patients influenced by alcohol (OR 3.464; 95% CI 2.644 to 4.538). A NEWS2 score of 3 in any parameter (vs. score 0–4, OR 2.386; 95% CI: 1.788 to 3.185) and ALS unit type (vs. BLS, OR 1.373; 95% CI: 1.009 to 1.866) increased the likelihood as well. Conclusions: The documentation in ePCRs show low rates of violence targeted at EMS personnel. However, violence is a multidimensional phenomenon connected to unfamiliar patients, rushed situations, and an uncontrolled environment. This means that the EMS personnels' safety cannot be ensured in all situations. Therefore, a balance between safety margins and treating patients needs to be considered. [ABSTRACT FROM AUTHOR]

Social networks are the most important stage in achieving big data in the discipline of health, with tweets from anywhere in the world currently enabling. It's also a great source of information for researching health issues and forecasting healthcare decisions. In terms of revenue and service, health care has become one of the world's leading industries. Every day, billions of customers use Twitter to share health-related topics, their views, and opinions on various healthcare topics. By aggregating millions of users' self-reported health conditions, we hope to distinguish the variety of health information discussed on Twitter. A topic modelling framework for discovering health topics on Twitter, a social networking website, is described. This is an exploratory approach to learning about the health topics that are frequently discussed on social media. In this sense, the required visualisations are a necessary measure to trim the information in order to identify the cluster's direction. The proposed topic model, i.e., Distributed Semantic Assisted Non-Negative matrix factorization, contributes to the pool of health statistics by balancing and pruning towards the direction of health topics from various perspective data sources. This assistance briefly describes the country's good public health structure and tracks the evolution of the main health-related tweets for early public advice. [ABSTRACT FROM AUTHOR]

Text classification, as an important research area of text mining, can quickly and effectively extract valuable information to address the challenges of organizing and managing large-scale text data in the era of big data. Currently, the related research on text classification tends to focus on the application in fields such as information filtering, information retrieval, public opinion monitoring, and library and information, with few studies applying text classification methods to the field of tourist attractions. In light of this, a corpus of tourist attraction description texts is constructed using web crawler technology in this paper. We propose a novel text representation method that combines Word2Vec word embeddings with TF-IDF-CRF-POS weighting, optimizing traditional TF-IDF by incorporating total relative term frequency, category discriminability, and part-of-speech information. Subsequently, the proposed algorithm respectively combines seven commonly used classifiers (DT, SVM, LR, NB, MLP, RF, and KNN), known for their good performance, to achieve multi-class text classification for six subcategories of national A-level tourist attractions. The effectiveness and superiority of this algorithm are validated by comparing the overall performance, specific category performance, and model stability against several commonly used text representation methods. The results demonstrate that the newly proposed algorithm achieves higher accuracy and F1-measure on this type of professional dataset, and even outperforms the high-performance BERT classification model currently favored by the industry. Acc, marco-F1, and mirco-F1 values are respectively 2.29%, 5.55%, and 2.90% higher. Moreover, the algorithm can identify rare categories in the imbalanced dataset and exhibit better stability across datasets of different sizes. Overall, the algorithm presented in this paper exhibits superior classification performance and robustness. In addition, the conclusions obtained by the predicted value and the true value are consistent, indicating that this algorithm is practical. The professional domain text dataset used in this paper poses higher challenges due to its complexity (uneven text length, relatively imbalanced categories), and a high degree of similarity between categories. However, this proposed algorithm can efficiently implement the classification of multiple subcategories of this type of text set, which is a beneficial exploration of the application research of complex Chinese text datasets in specific fields, and provides a useful reference for the vector expression and classification of text datasets with similar content. [ABSTRACT FROM AUTHOR]