Text Mining Processing Research Articles

COVID-19 effects on the going concern audit opinion in MENA region: Text mining approach

The COVID-19 pandemic has affected the economic sector, especially the audit task that requires the physical intervention of the auditor. The aim of this paper is to study the effect of COVID-19 on audit opinion in the MENA region through a novel text mining approach. The collected data included 83 bank reports from 377 branches in 14 MENA countries. The text mining approach was employed using Python software via corpus creation, tokenization, stop words removal, stemming, and feature selection. Afterwards, a univariate analysis was performed to delineate the variables that are significantly associated with COVID-19, followed by a linear regression model quantifying the relationship of the variables. The results of the text mining process led to the creation of a dictionary composed of 8000 words. After the text mining steps, 10 variables were obtained. The univariate analysis showed that 3 out of 10 extracted variables were associated with COVID-19 and a linear regression equation was accordingly generated. Our research revealed that, in the MENA region, the COVID-19 pandemic led to an increase in the audit workload and risk assessment, yielding an overall unfavorable audit opinion. Finally, the authors used similar techniques to the research of Wei, Li, Zhu, and Li (2019) and Boskou, Kirkos, and Spathis (2018).

The Weight of Surgical Knowledge: Navigating Information Overload.

The Weight of Surgical Knowledge: Navigating Information Overload.

Automated Classification of Unstructured Bilingual Software Bug Reports: An Industrial Case Study Research

Software bug report classification is a critical process to understand the nature, implications, and causes of software failures. Furthermore, classification enables a fast and appropriate reaction to software bugs. However, for large-scale projects, one must deal with a broad set of bugs from multiple types. In this context, manually classifying bugs becomes cumbersome and time-consuming. Although several studies have addressed automated bug classification using machine learning techniques, they have mainly focused on academic case studies, open-source software, and unilingual text input. This paper presents our automated bug classification approach applied and validated in an industrial case study. In contrast to earlier studies, our study is applied to a commercial software system based on unstructured bilingual bug reports written in English and Turkish. The presented approach adopts and integrates machine learning (ML), text mining, and natural language processing (NLP) techniques to support the classification of software bugs. The approach has been applied within an industrial case study. Compared to manual classification, our results show that bug classification can be automated and even performs better than manual bug classification. Our study shows that the presented approach and the corresponding tools effectively reduce the manual classification time and effort.

Text Complexity Classification Data Mining Model Based on Dynamic Quantitative Relationship between Modality and English Context

With the rapid development of mobile internet technology, there are a large number of unstructured data in dynamic data, such as text data, multimedia data, etc., so it is essential to analyze and process these unstructured data to obtain potentially valuable information. This article first starts with the theoretical research of text complexity analysis and analyzes the source of text complexity and its five characteristics of dynamic, complexity, concealment, sentiment, and ambiguity, combined with the expression of user needs in the network environment. Secondly, based on the specific process of text mining, namely, data collection, data processing, and data visualization, it is proposed to subdivide the user demand analysis into three stages of text complexity acquisition, recognition, and expression, to obtain a text complexity analysis based on text mining technology. After that, based on computational linguistics and mathematical-statistical analysis, combined with machine learning and information retrieval technology, the text in any format is converted into a content format that can be used for machine learning, and patterns or knowledge are derived from this content format. Then, through the comparison and research of text mining technology, combined with the text complexity analysis hierarchical structure model, a quantitative relationship complexity analysis framework based on text mining technology is proposed, which is embodied in the use of web crawler technology. Experimental results show that the collected quantitative relationship information is identified and expressed in order to realize the conversion of quantitative relationship information into product features. The market data and text data can be integrated to help improve the model performance and the use of text data can further improve predictions for accuracy.

Smarter people analytics with organizational text data: Demonstrations using classic and advanced NLP models

AbstractRecent developments in text mining and natural language processing (NLP) have paved a new way for analysing text data. These techniques are particularly useful for human resource management (HRM) due to the large amount of text information in the field. This paper adds to the literature by introducing and demonstrating steps of using NLP. Two demonstrations are presented: Demonstration One illustrates how simple and straightforward Bag‐of‐Word models applied on textual comments can be used to predict numerical ratings of companies; Demonstration Two shows how personality (self‐reported scores on the Big Five) can be predicted from situational interview questions through more complex Doc2Vec algorithms. Together, these demonstrations show that both simple and complex techniques are effective tools in predicting organizational outcomes. Accessible syntax and guides for beginners are also provided.

Screening and in Silico Validation of Anti-Microbial Peptides Derived from Lysostaphin, Entero and Endolysin

Introduction: Antimicrobial peptides (AMPs) are small molecules which are known to exert destructive effects upon pathogenic microorganisms. AMPs are designed from proteins obtained from various sources and tested under in vitro conditions to deduce their antimicrobial activity.
 Materials and Methods: A few of the peptidoglycan hydrolases such as lysostaphin (AAB53783.1), enterolysin (AGG79281.1), and endolysin (YP_009901016.1) were selected for the study based on an extensive text mining process. The protein sequences of the proteins were retrieved from the NCBI (National Centre for Biotechnology Information) database in the FASTA format (https://www.ncbi.nlm.nih.gov/protein/).
 Results and Discussion :In the antimicrobial protein lysostaphin, three antimicrobial peptide are been found, in which two is active and other is inactive, and one has antifungal property with a score of -0.15, and one having cell penetrating property, in which all are non toxic.
 Conclusion: The present study predicts AMPs from lysostaphin, entero and endolysins. These peptides were found to possess antifungal, anti-biofilm properties. Most of the peptides predicted were found to be non-cell penetrating and non-toxic.

Penerapan Algoritma Support Vector Machine (SVM) dengan TF-IDF N-Gram untuk Text Classification

Syntax Journal of Informatics is an information system that contains a collection of scientific articles managed by the Informatics Study Program of Singaperbangsa Karawang University. Currently, Syntax Journal of Informatics does not have a feature for categorizing scientific articles based on their focus and scope. The research is conducted to classify scientific articles into categories according to focus and scope contained on Syntax Journal of Informatics’ page automatically by utilizing the text mining process. Text mining is a process that aims to get important information from the text. The method used in the research is Knowledge Discovery in Database (KDD) with stages of data selection, preprocessing, transformation, modeling and evaluation. This study will compare the classifications based on the title of the article. The algorithm used is the Support Vector Machine (SVM) using four SVM kernels, including the linear kernel, polynomial kernel, sigmoid kernel and RBF kernel. Data are divided into four scenarios by using traintestsplit, namely 60:40, 70:30, 80:30 and 90:10. The results of the study after testing the model are measured by of Accuracy, Precision, Recall and F-measure. The best results are accuracy of 70%, precision of 75%, recall of 69% and f-measure of 71% in the 90:10 comparison scenario and linear kernel.

Realizing the Power of Text Mining and Natural Language Processing for Analyzing Patient Safety Event Narratives: The Challenges and Path Forward.

Patient safety event (PSE) reports are a useful lens to understand hazards and patient safety risks in healthcare systems. However, patient safety officers and analysts in healthcare systems and safety organizations are challenged to make sense of the ever-increasing volume of PSE reports, including the free-text narratives. As a result, there is a growing emphasis on applying text mining and natural language processing (NLP) approaches to assist in the processing and understanding of these narratives. Although text mining and NLP in healthcare have advanced significantly over the past decades, the utility of the resulting models, ontologies, and algorithms to analyze PSE narratives are limited given the unique difference and challenges in content and language between PSE narratives and clinical documentation. To promote the application of text mining and NLP for PSE narratives, these unique challenges must be addressed. Improving data access, developing NLP resources to practically use contributing factor taxonomies, and developing and adopting shared specifications for interoperability will help create an infrastructure and environment that unlocks the collaborative potential between patient safety, research, and machine learning communities, in the development of reproducible and generalizable methods and models to better understand and improve patient safety and patient care.

Machine Learning Techniques in the Energy Consumption of Buildings: A Systematic Literature Review Using Text Mining and Bibliometric Analysis

The high level of energy consumption of buildings is significantly influencing occupant behavior changes towards improved energy efficiency. This paper introduces a systematic literature review with two objectives: to understand the more relevant factors affecting energy consumption of buildings and to find the best intelligent computing (IC) methods capable of classifying and predicting energy consumption of different types of buildings. Adopting the PRISMA method, the paper analyzed 822 manuscripts from 2013 to 2020 and focused on 106, based on title and abstract screening and on manuscripts with experiments. A text mining process and a bibliometric map tool (VOS viewer) were adopted to find the most used terms and their relationships, in the energy and IC domains. Our approach shows that the terms “consumption,” “residential,” and “electricity” are the more relevant terms in the energy domain, in terms of the ratio of important terms (TITs), whereas “cluster” is the more commonly used term in the IC domain. The paper also shows that there are strong relations between “Residential Energy Consumption” and “Electricity Consumption,” “Heating” and “Climate. Finally, we checked and analyzed 41 manuscripts in detail, summarized their major contributions, and identified several research gaps that provide hints for further research.

Boosting biomedical document classification through the use of domain entity recognizers and semantic ontologies for document representation: The case of gluten bibliome

The increasing number of scientific research documents published keeps growing at an unprecedented rate, making it increasingly difficult to access practical information within a target domain. This situation is motivating a growing interest in applying text mining techniques for the automatic processing of text resources to structure the information that helps researchers to find information of interest and infer knowledge of practical use. However, the automatic processing of research documents requires the previous existence of large, manually annotated text corpora to develop robust and accurate text mining processing methods and machine learning models. In this context, semi-automatic extraction techniques based on structured data and state-of-the-art biomedical tools appear to have significant potential to enhance curator productivity and reduce the costs of document curation. In this line, this work proposes a semi-automatic machine learning workflow and a NER + Ontology boosting technique for the automatic classification of biomedical literature. The practical relevance of the proposed approach has been proven in the curation of 4,115 gluten-related documents extracted from PubMed and contrasted against the word embedding alternative. Comparing the results of the experiments, the proposed NER + Ontology technique is an effective alternative to other state-of-the-art document representation techniques to process the existing biomedical literature.

EWOM for public institutions: application to the case of the Portuguese Army

Social media platforms provide easy access to the public opinion (called electronic word-of-mouth), which can be collected and analyzed to extract knowledge about the reputation of an organization. Monitoring this reputation in the public sector may bring several benefits for its institutions, especially in supporting decision-making and developing marketing campaigns. Thus, to offer a solution aimed at the needs of this sector, the goal of this research was to develop a methodology capable of extracting relevant information about eWOM in social media, using text mining and natural language processing techniques. Our goal was achieved through a methodology capable of handling the small amount of information regarding public state organizations in social media. Additionally, our work was validated using the context of the Portuguese Army and revealed the potential to provide indicators of institutional reputation. Our results present one of the first cases of the application of this type of techniques to an Army organization and to understand its negative reputation among the population.

Identifying research themes and trends in the top 20 cancer journals through textual analysis

BackgroundThe rapid growth in cancer research continues expanding the literature. Text mining approaches help make sense of large bodies of scientific literature and integrate the mounting data into the health care delivery system. Our objective is to generate a comprehensive understanding of the themes and trends in cancer research. MethodsWe employed a three-step text mining process of corpus generation and term-list creation and analysis, including latent semantic analysis for dimension reduction and factor analysis for topic identification to analyze 93,423 abstracts from the top 20 cancer/oncology journals for the period between 1999 and 2020. ResultsWe identified 14 distinct topics in cancer literature. The results revealed the uptrend topics - including cell signaling (T-2), immunotherapy (T-3), clinical trials (T-5), disparities and epidemiology (T-7), cancer practice and policy (T-8), outcome research (T-9), and molecular therapeutics (T-10). - and downtrend topics such as cell death (T-1), early phase clinical trials (T-4), angiogenesis (T-6), cancer screening (T-12), and transplant (T-13). The topics of biomarkers(T-11) and cancer genetics(T-16) remained relatively stable. While the topics of angiogenesis (n = 10,490) and cell death (n = 10,258) included the highest number of abstracts, biomarkers (n = 3203), and cancer genetic (n = 4322) themes included the least number of articles. These findings suggest that despite having the lowest numbers of publications, certain topics such as cancer genetic (T-16) and biomarkers (T-11) have been exhibiting a stable trend and drawing a steady amount of attention from cancer researchers over the past 20 years. ConclusionFindings of this study contribute explanatory insight about themes and trends in cancer research, which can help researchers and stakeholders to identify areas for future studies. Policy Summary StatementThe findings indicate the increasing efforts to improve cancer practice and cancer care through policy efforts. Therefore, policymakers and other stakeholders may use the findings in prioritization and funding of specific topics.

Bibliometric and Text Mining Analysis on COVID-19 Research Projects in Iran

Bibliometric and Text Mining Analysis on COVID-19 Research Projects in Iran

Формализация базовых процессов и математическая модель системы мониторинга и анализа публикаций электронных СМИ

The article describes an approach to formalizing basic processes and building a mathematical model for a system for collecting and analyzing data from electronic media. The authors, as part of a scientific study, are creating a system, including the development of new algorithms, methods and approaches for collecting and analyzing textual information from Internet news sources. The main direction of the study is the application of methods for the mining of text data based on the technology of artificial neural networks, methods of natural language processing, text mining, machine learning and big data processing. Purpose of the study. To develop a formalized description of the model of the system for monitoring and analyzing the text information of electronic news media using the methods of mathematical modeling. Research methods and tools. The use of the toolkit of the methodology of mathematical modeling, with the methods of system analysis is proposed. To study the system, such methods of system analysis as abstraction, formalization, composition and decomposition, structuring and restructuring, modeling, recognition and identification were used. The system is considered as a formalized model of an automatic classifier and clusterizer for a set of text documents in a natural language in the form of an algebraic system. To solve the problems of classification and clustering of texts, it is proposed to apply machine learning methods based on neural network approaches. The structure of the system and its constituent processes, as well as processes interacting with the system from outside, are presented in the form of a formalized mathematical description. Results. The developed formalized mathematical description of the system model clearly shows the interconnection of the system components with each other, as well as internal processes. The applied approach makes it possible to detail the representation of the system based on its decomposition into subsystems and modules. All this makes it possible to streamline the sequence of stages of creating a system and decompose them into separate stages of work. Conclusion. The results obtained in the course of the study allow us to move on to the next stage of the life cycle of the information system being developed - its software development.

PERBANDINGAN KERNEL SUPPORT VECTOR MACHINE (SVM) DALAM PENERAPAN ANALISIS SENTIMEN VAKSINISASI COVID-19

In early 2020, the first recorded death from the COVID-19 virus in China [3]. Followed by WHO which later stated that the COVID-19 virus caused a pandemic. Various efforts were made to minimize the transmission of COVID-19, such as physical distancing and large-scale social circulation. However, this resulted in a paralyzed economy, many factories or business shops closed, eliminating the livelihoods of many people. Vaccines may be a solution, various International Research Communities have conducted research on the COVID-19 vaccine. In early 2021 the Sinovac vaccine from China arrived in Indonesia and was declared a BPOM clinical trial, but the existence of the vaccine still raises pros and cons, some have responded well and others have not. For this reason, a sentiment analysis of the COVID-19 vaccine will be carried out by taking data from Twitter, then classified using the Support Vector Machine algorithm. The research data is nonlinear data so it requires a kernel space for the text mining process, while there has been no specific research regarding which kernel is good for sentiment analysis, so a test will be carried out to find the best kernel among linear, sigmoid, polynomial, and RBF kernels. The result is that sigmoid and linear kernels have a better value, namely 0.87 compared to RBF and polynomial, namely 0.86

UNDERSTANDING CONSTRUCTION SITE SAFETY HAZARDS THROUGH OPEN DATA: TEXT MINING APPROACH

Construction is an industry well known for its very high rate of injuries and accidents around the world. Even though many researchers are engaged in analysing the risks of this industry using various techniques, construction accidents still require much attention in safety science. According to existing literature, it has been found that hazards related to workers, technology, natural factors, surrounding activities and organisational factors are primary causes of accidents. Yet, there has been limited research aimed to ascertain the extent of these hazards based on the actual reported accidents. Therefore, the study presented in this paper was conducted with the purpose of devising an approach to extract sources of hazards from publicly available injury reports by using Text Mining (TM) and Natural Language Processing (NLP) techniques. This paper presents a methodology to develop a rule-based extraction tool by providing full details of lexicon building, devising extraction rules and the iterative process of testing and validation. In addition, the developed rule-based classifier was compared with, and found to outperform, the existing statistical classifiers such as Support Vector Machine (SVM), Kernel SVM, K-nearest neighbours, Naïve Bayesian classifier and Random Forest classifier. The finding using the developed tool identified the worker factor as the highest contributor to construction site accidents followed by technological factor, surrounding activities, organisational factor, and natural factor (1%). The developed tool could be used to quickly extract the sources of hazards by converting largely available unstructured digital accident data to structured attributes allowing better data-driven safety management.

Performance Analysis of Hybrid Deep Learning Models with Attention Mechanism Positioning and Focal Loss for Text Classification

Over the past few decades, text classification problems have been widely utilized in many real time applications. Leveraging the text classification methods by means of developing new applications in the field of text mining and Natural Language Processing (NLP) is very important. In order to accurately classify tasks in many applications, a deeper insight into deep learning methods is required as there is an exponential growth in the number of complex documents. The success of any deep learning algorithm depends on its capacity to understand the nonlinear relationships of the complex models within data. Thus, a huge challenge for researchers lies in the development of suitable techniques, architectures, and models for text classification. In this paper, hybrid deep learning models, with an emphasis on positioning of attention mechanism analysis, are considered and analyzed well for text classification. The first hybrid model proposed is called convolutional Bidirectional Long Short-Term Memory (Bi-LSTM) with attention mechanism and output (CBAO) model, and the second hybrid model is called convolutional attention mechanism with Bi-LSTM and output (CABO) model. In the first hybrid model, the attention mechanism is placed after the Bi-LSTM, and then the output Softmax layer is constructed. In the second hybrid model, the attention mechanism is placed after convolutional layer and followed by Bi-LSTM and the output Softmax layer. The proposed hybrid models are tested on three datasets, and the results show that when the proposed CBAO model is implemented for IMDB dataset, a high classification accuracy of 92.72% is obtained and when the proposed CABO model is implemented on the same dataset, a high classification accuracy of 90.51% is obtained.

Exploring Text Mining for Recent Consumer and Sensory Studies about Alternative Proteins.

Increased meat consumption has been associated with the overuse of fresh water, underground water contamination, land degradation, and negative animal welfare. To mitigate these problems, replacing animal meat products with alternatives such as plant-, insect-, algae-, or yeast-fermented-based proteins, and/or cultured meat, is a viable strategy. Nowadays, there is a vast amount of information regarding consumers’ perceptions of alternative proteins in scientific outlets. Sorting and arranging this information can be time-consuming. To overcome this drawback, text mining and Natural Language Processing (NLP) are introduced as novel approaches to obtain sensory data and rapidly identify current consumer trends. In this study, the application of text mining and NLP in gathering information about alternative proteins was explored by analyzing key descriptive words and sentiments from n = 20 academic papers. From 2018 to 2021, insect- and plant-based proteins were the centers of alternative proteins research as these were the most popular topics in current studies. Pea has become the most common source for plant-based protein applications, while spirulina is the most popular algae-based protein. The emotional profile analysis showed that there was no significant association between emotions and protein categories. Our work showed that applying text mining and NLP could be useful to identify research trends in recent sensory studies. This technique can rapidly obtain and analyze a large amount of data, thus overcoming the time-consuming drawback of traditional sensory techniques.

Analyzing TripAdvisor reviews of wine tours: an approach based on text mining and sentiment analysis

PurposeWine packaged tours as a specific aspect of wine tourism have so far been neglected in research, for this reason, the purpose of this study is to study the key elements for the success of the wine tour in Tuscany (Italy), evaluating the points of strength and weakness.Design/methodology/approachThe study combines approaches of text mining, sentiment analysis and natural language processing, drawing on data from the TripAdvisor platform, obtaining through an automatic procedure 9,616 reviews from 600 tours in the years 2010–2020.FindingsThe authors identified six elements of successful wine tours expressed by research subjects: tour guide; logistical aspects; the quality of the wine; the quality of the food; complementary tourist and recreational activities; the landscape and historic villages. The key strength associated with success was the integration of the leading wine product with food, landscape and historic villages, while the main criticisms were concerned with the organization and planning of the tour. Furthermore, the tour guide also plays a fundamental role in consumer satisfaction.Research limitations/implicationsThe limitations of the method were linked to the origin of the data used. The main one is that TripAdvisor does not allow you to have social and personal information about the tourist who wrote the review; therefore, the methods are substantially complementary to the traditional survey through questionnaires.Practical implicationsThe proposed model can be used both by professionals to improve the quality of their products and by policymakers to promote the territorial development of quality wine-growing areas.Social implicationsThe proposed model can be useful for policymakers to promote the territorial development of quality wine-growing areas.Originality/valueThe methodology we tested is easily transferable to many countries and to the authors’ knowledge, for the first time attempts to combine multidimensional scaling, sentiment analysis and natural language processing approaches.

Mapping the genealogy of medical device predicates in the United States.

In the United States, medical devices are regulated and subject to review by the Food and Drug Administration (FDA) before they can be marketed. Low-to-medium risk novel medical devices can be reviewed under the De Novo umbrella before they can proceed to market, and this process can be fairly cumbersome, expensive, and time-consuming. An alternate faster and less-expensive pathway to going to market is the 510(k) pathway. In this approach, if the device can be shown to be substantially equivalent in safety and effectiveness to a pre-existing FDA-approved marketed device (or "predicates"), it can be cleared to market. Due to the possibility of daisy-chaining predicate devices, it can very quickly be difficult to unravel the logic and justification of how a particular medical device's equivalence was established. From patients' perspective, this minimizes transparency in the process. From a vendor perspective, it can be difficult to determine the right predicate that applies to their device. We map the connectivity of various predicates in the medical device field by applying text mining and natural language processing (NLP) techniques on data publicly made available by the FDA 78000 device summaries were scraped from the US FDA 510(k) database, and a total of 2,721 devices cleared by the 510(k) regulatory pathway in 2020 were used as a specific case study to map the genealogy of medical devices cleared by the FDA. Cosine similarity was used to gauge the degree of substantial equivalence between two medical devices by evaluating their device descriptions and indications for use. Recalls and complaints for predicate devices were extracted from the FDA's Total Product Life Cycle database using html scraping and web page optical character recognition to determine the similarity between class 1 recalled devices (the most severe form of device recall) and other substantially equivalent devices. A specific product code was used to illustrate the mapping of the genealogy from a De Novo device. The ancestral tree for the medical devices cleared in 2020 is vast and sparse, with a large number of devices having only 1-2 predicates. Evaluation of substantial equivalence data from 2003-2020 shows that the standard for substantial equivalence has not changed significantly. Studying the recalls and complaints, shows that the insulin infusion pump had the highest number of complaints, yet none of the recalled devices bore significant degree of text similarity to currently marketed devices. The mapping from the De Novo device case study was used to develop an ancestry map from the recalled predicate (recalled due to design flaws) to current substantially equivalent products in the market. Besides enabling a better understanding of the risks and benefits of the 510(k) process, mapping of connectivity of various predicates could help increase consumer confidence in the medical devices that are currently in the marketplace.