Text Databases Research Articles

Artificial intelligence in scientific writing: a friend or a foe?

The generative pre-trained transformer, ChatGPT, is a chatbot that could serve as a powerful tool in scientific writing. ChatGPT is a so-called large language model (LLM) that is trained to mimic the statistical patterns of language in an enormous database of human-generated text combined from text in books, articles and websites across a wide range of domains. ChatGPT can assist scientists with material organization, draft creation and proofreading, making it a valuable tool in research and publishing. This paper discusses the use of this artificial intelligence (AI) chatbot in academic writing by presenting one simplified example. Specifically, it reflects our experience of using ChatGPT to draft a scientific article for Reproductive BioMedicine Online and highlights the pros, cons and concerns associated with using LLM-based AI for generating a manuscript.

Real time sentiment analysis of natural language using multimedia input.

Semantics and Sentiments are parts of our daily speech and expressions that helps to convey the message in the tone intended. The accurate interpretation of emotions and actions is prudent as it expresses the true meaning of the message. This interpretation has been studied extensively in the past two decades, where professionals from various disciplines have pondered this question. Every action and expression-whether it's in a speech, in a video or through some written material-helps the recipient understand the intent behind the message. The primary motive in these studies has been to automate the analysis of these sentiments by teaching the computers to do so, using the audio, video and text-based data that has been collected so far. Machine Learning (ML) and Deep Learning (DL) is the discipline that can help us tackle such a problem which requires analysis and recognition of copious amounts of data. Classification based on these multi-media inputs has seen the application of several common and uncommon ML techniques such as Support Vector Machines (SVMs), Bayesian Networks (BNs), Decision Trees (DTs), Convolutional Neural Networks (CNNs) and K-Means Clustering. These techniques, to a certain level of accuracy, can classify a certain part of a message into a different emotion. Through this research, firstly, a comparison is represented between the previously conducted studies and secondly, a system is developed of our own that enables Real Time Sentiment Analysis and helps a user assess his/her day-to-day attitude and get appropriate recommendations for the same.

Human Resource Management and Organizational Innovation: Assessing the Moderating Role of Organization Culture

Purpose: The paper aims to contribute to the literature on organizational effectiveness by highlighting the role of human resource management (HRM) in influencing business organizational performance through its intermediate effect on innovation.
 Design/Methodology/Approach: Finally, qualitative content analysis is a research method used to analyze text-based data such as interview transcripts, survey responses, or other types of written or verbal communication. It's likely that the researchers used this method to analyze the data they collected through their questionnaire and possibly other sources, such as interviews or company reports. The goal of the analysis would have been to identify themes or patterns related to innovation and performance in the organization.
 Findings: In summary, the integration of HRM practices with innovation and culture can have a significant impact on the performance and sustainability of higher education institutions. By promoting an innovative and sustainable culture, higher education institutions can attract and retain top talent, improve organizational performance, and make a positive impact on society and the environment
 Implications/Originality/Value: The Creativity Post is an online publication that focuses on creativity and innovation. They publish articles, interviews, and research on a variety of topics related to creativity, including HR management. The Human Resource Planning Society (HRPS): HRPS is a global community of HR professionals. They offer a variety of resources to their members, including research, webinars, and events on topics related to creativity and innovation.

Utilizing Machine Learning for Detecting Harmful Situations by Audio and Text

Children with special needs may struggle to identify uncomfortable and unsafe situations. In this study, we aimed at developing an automated system that can detect such situations based on audio and text cues to encourage children’s safety and prevent situations of violence toward them. We composed a text and audio database with over 1891 sentences extracted from videos presenting real-world situations, and categorized them into three classes: neutral sentences, insulting sentences, and sentences indicating unsafe conditions. We compared insulting and unsafe sentence-detection abilities of various machine-learning methods. In particular, we found that a deep neural network that accepts the text embedding vectors of bidirectional encoder representations from transformers (BERT) and audio embedding vectors of Wav2Vec as input attains the highest accuracy in detecting unsafe and insulting situations. Our results indicate that it may be applicable to build an automated agent that can detect unsafe and unpleasant situations that children with special needs may encounter, given the dialogue contexts conducted with these children.

Data Mining Tools for Generate Item Set : Critical Review

Most algorithms used to identify large itemsets can be classified as either sequential or parallel. In most cases, it is assumed that the itemsets are identified and stored in lexicographic order (based on item name). This ordering provides a logical manner in which itemsets can be generated and counted. This is the normal approach with sequential algorithms. On the other hand, parallel algorithms focus on how to parallelize the task of finding large itemsets. Mining Associations is one of the techniques involved in the process mentioned in chapter 1 and among the data mining problems it might be the most studied ones. Discovering association rules is at the heart of data mining. Mining for association rules between items in large database of sales transactions has been recognized as an important area of database research. These rules can be effectively used to uncover unknown relationships, producing results that can provide a basis for forecasting and decision making. Today, research work on association rules is motivated by an extensive range of application areas, such as banking, manufacturing, health care, and telecommunications. It is also used for building statistical thesaurus from the text databases, finding web access patterns from web log files, and also discovering associated images from huge sized image databases.

Teaching methods: Pedagogical challenges in moving beyond traditionally separate quantitative and qualitative classrooms

In the social sciences, research methods courses may be the most important and yet the most undervalued. Quality Assurance Agency (QAA) benchmark statements that deliver UK national standards all signify that methods teaching is essential. In terms of applicability, learning how to evaluate and produce knowledge has high relevance for employability. In the UK, despite being ‘core’, methods courses, compared with disciplinary courses, tend to have lower institutional investment utilising relatively small and early-career teaching teams and are taught to large groups of students (Ferrie et al., 2022). This paper draws together literature on the pedagogy of methods with reflexive practice to critically consider the barriers to learning methods and considers what methods educators and learners can do to engage optimally with the learner experience. This paper begins by considering how teaching of numeric- and text-based data produces a different learning environment to disciplinary learning. It then considers how quantitative pedagogy is distinct from qualitative pedagogy and in turn perpetuates the idea that they are distinct forms of knowledge production. The ‘pine tree’ and the ‘oak tree’ are two pedagogic devices that help students transform their learning practices. Growing calls to mix methods in course presentations and transcend the qualitative/quantitative divide present new challenges for pedagogy. The paper will outline a third pedagogic device that has helped students grasp something of a holistic understanding of how research methods operate. The ‘dirty greenhouse’ analogy, used with undergraduates and postgraduates (in large joint social sciences course at a large UK university), helps students scaffold their learning and get a quick grasp on what the value of methods courses are and avoids pitching qualitative and quantitative paradigms ‘against’ each other. The paper will argue that students are aided by having visual frameworks that help them, enhancing their critical approach to knowledge production and understanding better what a ‘defence’ in our research writing aims to do.

Professional burnout of medical workers in the era of the COVID-19 pandemic as a risk factor for mental health

The paper presents an analysis of the literature on the problem of professional burnout syndrome in medical workers, presented in the Scientific Electronic Library (eLibrary), as well as in the English-language text database of medical and biological publications PubMed.
 The novel coronavirus infection pandemic is associated with many factors contributing to formation and development of professional burnout in medical workers. The risk factors are: high workload, lack of PPE, threat and risk of contracting a new coronavirus infection, social isolation, insufficiency (at the first stage) of accumulated knowledge about the new little-studied disease.

A Thematic Travel Recommendation System Using an Augmented Big Data Analytical Model

Tour planning has become both challenging and time-consuming due to the huge amount of information available online and the variety of options to choose from. This is more so as each traveler has unique set of interests and location preferences in addition to other tour-based constraints such as vaccination status and pandemic travel restrictions. Several travel planning companies and agencies have emerged with more sophisticated online services to capitalize on global tourism effectively by using technology for making suitable recommendations to travel seekers. However, such systems predominantly adopt a destination-based recommendation approach and often come as bundled packages with limited customization options for incorporating each traveler’s preferences. To address these limitations, “thematic travel planning” has emerged as a recent alternative with researchers adopting text-based data mining for achieving value-added online tourism services. Understanding the need for a more holistic theme approach in this domain, our aim is to propose an augmented model to integrate analytics of a variety of big data (both static and dynamic). Our unique inclusive model covers text mining and data mining of destination images, reviews on tourist activities, weather forecasts, and recent events via social media for generating more user-centric and location-based thematic recommendations efficiently. In this paper, we describe an implementation of our proposed inclusive hybrid recommendation model that uses data of multimodal ranking of user preferences. Furthermore, in this study, we present an experimental evaluation of our model’s effectiveness. We present the details of our improvised model that employs various statistical and machine learning techniques on existing data available online, such as travel forums and social media reviews in order to arrive at the most relevant and suitable travel recommendations. Our hybrid recommender built using various Spark models such as naïve Bayes classifier, trigonometric functions, deep learning convolutional neural network (CNN), time series, and NLP with sentiment scores using AFINN (sentiment analysis developed by Finn Årup Nielsen) shows promising results in the directions of benefit for an individual model’s complementary advantages. Overall, our proposed hybrid recommendation algorithm serves as an active learner of user preferences and ranking by collecting explicit information via the system and uses such rich information to make personalized augmented recommendations according to the unique preferences of travelers.

PEMBANGUNAN SISTEM INFORMASI MONITORING KARYAWAN PADA BAGIAN LOGISTIK DI PT. MOWILEX INDONESIA.

Mowilex Indonesia is a company engaged in manufacturing with more than 1000 employees. In managing employee data, this company does not yet have an integrated information system so that data management for employee activities has not been effective and efficient. Therefore, an information system is needed that can monitor all employee activities ranging from attendance, leave, mutation, promotion and other activities. With this system, companies can monitor employee activities easily and quickly, especially in making reports. The objectives of this study are 1) to create employee monitoring information system, 2) to provide convenience in making monitoring performance reports for management needs. This research uses waterfall development methods and Unified Modeling Language (UML) modeling as system design methods, while its implementation uses the PHP programming language with the help of sublime text and MYSQL databases with the help of navicat.

Rancang Bangun Sistem Informasi Inventaris Barang Pada SMKN 1 Parittiga

This research aims to design and build a web-based goods inventory system at SMKN 1 Parittiga to assist the goods inventory section in submitting goods, information on incoming and outgoing goods and the condition of the goods. The research method used is a descriptive qualitative method and the data collection method is the method of observation, interviews, literature and documentation and uses the waterfall method as a software development method. This web-based inventory information system at SMKN 1 Parittiga was built using sublime text PHP, Bootstrap, CI, database, and MySQL programming languages. The goods inventory information system at SMKN 1 Parittiga makes it easy for admins to submit goods, information on incoming and outgoing goods, and information on the condition of goods. For this reason, in this project, analysis and design of the system have been carried out, with the final result that this inventory information system has proven to facilitate and greatly assist the performance of the inventory section.

Sentiment analysis model for Airline customers’ feedback using deep learning techniques

Sentiment analysis (SA) has recently developed an automated approach for assessing sentiment, emotion, and these reviews or opinions to extract relevant and subjective information from text-based data. Analyzing sentiment on social networks, such as Twitter, has become a powerful means of learning about the users’ opinions and better understanding and satisfaction. However, it consumes time and energy to disperse and collect surveys from clients, often inaccurate and inconsistent, and evaluating and improving the accuracy of the methods in sentiment analysis is being hindered by the challenges encountered in Natural Language Processing (NLP). This paper uses NLP, text analysis, biometrics, and computational linguistics to detect and extract replies, moods, or emotions from Skytrax Airline Customers' Feedback SACF data. This research uses deep learning models to analyze various approaches applied to small SACF to solve sentiment analysis problems. We applied word embedding (Glove embedding models) to improve the sentiment classification performance of a series of datasets extensively utilized for feature extractions. Finally, a comparative study has been conducted on the SACF data analysis utilizing deep learning (DL)for evaluating the performance of the different models and input features, which is Recurrent Neural Networks (RNN), long short-term memory (LSTM), Gated Recurrent Unit (GRU), 1D Convolutional Neural Networks (CONV1D), and Bidirectional Encoder Representations from Transformers (BERT) for application to big datasets in 2019. This approach was assessed using each classification technique; the precision, recall, f1-score, and accuracy metrics for sentiment analysis have been identified. And The results show that LSTM outperforms in classification accuracy; the outcome was 91%.

Assessing the likelihood of drought impact occurrence with extreme gradient boosting: a case study on the public water supply in South Korea

AbstractDrought is quantified with one or a set of drought indices for monitoring and risk management. These indices have a limited ability to capture drought impacts. Drought impact prediction models have been developed to explore the interactions between the drought impact data and the physical drought indices. This study demonstrates the use of extreme gradient boosting (XGB), a well-known machine learning technique, to predict the likelihood of impact occurrence (LIO) of drought on public water supply as a function of drought indices, with high accuracy and low uncertainty. Using text-based drought impact data from multiple sources, the prediction accuracy of drought LIO on the public water supply of South Korea was evaluated using XGB and reference models (log-logistic, support vector machine, and random forest). We also analyzed receiver operating characteristics and quantified the uncertainty of each model with bootstrapping. This study shows that XGB and random forest have a high level of suitability. However, random forest presents a higher level of uncertainty than XGB for predicting drought LIO on the public water supply in South Korea. Although some limitations exist, the results suggest that text-based drought impact data collected from multiple sources can provide insightful information for drought risk management.

Transformer transfer learning emotion detection model: synchronizing socially agreed and self-reported emotions in big data

Tactics to determine the emotions of authors of texts such as Twitter messages often rely on multiple annotators who label relatively small data sets of text passages. An alternative method gathers large text databases that contain the authors’ self-reported emotions, to which artificial intelligence, machine learning, and natural language processing tools can be applied. Both approaches have strength and weaknesses. Emotions evaluated by a few human annotators are susceptible to idiosyncratic biases that reflect the characteristics of the annotators. But models based on large, self-reported emotion data sets may overlook subtle, social emotions that human annotators can recognize. In seeking to establish a means to train emotion detection models so that they can achieve good performance in different contexts, the current study proposes a novel transformer transfer learning approach that parallels human development stages: (1) detect emotions reported by the texts’ authors and (2) synchronize the model with social emotions identified in annotator-rated emotion data sets. The analysis, based on a large, novel, self-reported emotion data set (n = 3,654,544) and applied to 10 previously published data sets, shows that the transfer learning emotion model achieves relatively strong performance.

Drawing Ageing: Using Participant-Generated Drawing to Explore Older Australians Expectations and Experiences of Ageing in a Retirement Village

This article discusses the use of an arts-based visual methodology, drawing, to explore older people’s experiences and expectations of ageing in a retirement village. Tactile, generative, and visual, drawing is a quick, inexpensive, and extremely participatory process, which, compared to traditional text-based data, provides rare and compelling insight into conscious and unconscious feelings, emotions, sentiments, and experiences. As part of a broader project exploring life in retirement villages, 12 older adults in their 70s and 80s were asked to sketch their experiences of ageing, as well as their expectations and experiences of retirement village life. Sketches were analysed using reflexive thematic analysis, which revealed that participants drew ageing as both a time for opportunity and enjoyment and decline, while retirement village life very much met their expectations in terms of being a place of fun, friendship, and leisure. While drawing as a method is rarely used in gerontological research, the outcomes of this project demonstrate how it enables the powerful production of evocative, interactive, and memorable imagery, and it should be a greater part of the methodological toolbox.

International experience of regulation of odourous substances in the ambient air (literature review)

The article provides an overview of the foreign literature data on the justification of permissible content of odourous substances in the ambient air. The process of harmonization of Russian legislation with international norms and rules, including the field of regulating atmospheric air pollution with specific odours, is shown to necessitate significantly expanding approaches to the issues of standardization and assessing environmental pollution by emissions from enterprises - odour sources. Analysis of foreign experience in odour management in the environment shows the main criteria for assessing air quality to include the absence of “annoyance” of the population by odours, maximum permissible concentrations for individual substances, maximum permissible concentrations for ambient odours, permissible odour frequency, minimum distances from the source, odour intensity, the maximum permissible amount of emissions, compliance with technological standards. Accordingly, in different countries recommended or mandatory limiting values were established on the base on which criterion for assessing odour exposure is decisive in this case. Typically, different jurisdictions use more than one approach to odour assessment, as do various regulatory indicators depending on the situation with the type of enterprise, the characteristics of residential sites and other receptor points. According to many authors, the application of various air quality standards for odour and a carefully thought-out approach to odour management can successfully or completely resolve most conflicts when working with the local population. The search for sources devoted to the issues of standardization of odourous substances was carried out in the text databases as PubMed, Scopus, Science Direct, Web of Science, Research Gate, Springer Link and the scientific electronic library eLibrary.ru. The article analyzes the articles of journals indexed in the RSCI, Scopus, for 2001-2021.

Natural Language Processing Applications for Computer-Aided Diagnosis in Oncology.

In the era of big data, text-based medical data, such as electronic health records (EHR) and electronic medical records (EMR), are growing rapidly. EHR and EMR are collected from patients to record their basic information, lab tests, vital signs, clinical notes, and reports. EHR and EMR contain the helpful information to assist oncologists in computer-aided diagnosis and decision making. However, it is time consuming for doctors to extract the valuable information they need and analyze the information from the EHR and EMR data. Recently, more and more research works have applied natural language processing (NLP) techniques, i.e., rule-based, machine learning-based, and deep learning-based techniques, on the EHR and EMR data for computer-aided diagnosis in oncology. The objective of this review is to narratively review the recent progress in the area of NLP applications for computer-aided diagnosis in oncology. Moreover, we intend to reduce the research gap between artificial intelligence (AI) experts and clinical specialists to design better NLP applications. We originally identified 295 articles from the three electronic databases: PubMed, Google Scholar, and ACL Anthology; then, we removed the duplicated papers and manually screened the irrelevant papers based on the content of the abstract; finally, we included a total of 23 articles after the screening process of the literature review. Furthermore, we provided an in-depth analysis and categorized these studies into seven cancer types: breast cancer, lung cancer, liver cancer, prostate cancer, pancreatic cancer, colorectal cancer, and brain tumors. Additionally, we identified the current limitations of NLP applications on supporting the clinical practices and we suggest some promising future research directions in this paper.

Effect of exercise therapy on PICC-associated venous thromboembolism: A meta-analysis.

Peripherally inserted central catheter (PICC) is widely used in clinical practice because of its long retention time and easy maintenance. However, PICC-associated venous thromboembolism (VTE) is the most serious complication of PICC. Guidelines recommend exercise therapy to prevent PICC-associated VTE. However, inconsistent findings have been reported across the literature. This study conducted a meta-analysis to further evaluate the effect of exercise therapy on PICC-associated VTE. We searched CNKI, Wanfang database, Chinese Science and Technology Journal Full Text Database, PubMed, Embase, Web of Science and Cochrane Library databases and included all randomized controlled trials (RCTs) of exercise therapy for the prevention of PICC-associated VTE. Two investigators independently screened the literature, extracted information, and evaluated the risk of bias for eligible RCTs. Meta-analysis was conducted by RevMan5.4 software. Eleven RCTs were included, including 1919 patients. Meta-analysis showed that the incidence of PICC-associated VTE was lower in the exercise therapy group than in the usual care group (RR = 0.30, 95% CI: 0.22-0.41, p < 0.00001).Exercise therapy increased the axillary vein maximum velocity (SMD = 0.93, 95% CI: 0.58-1.28, p < 0.00001) and the axillary vein time-mean flow velocity (SMD = 0.86, 95% CI: 0.53-1.20, p < 0.00001). Subgroup analysis showed statistically significant differences for the incidence of PICC-associated VTE for intervention times<4weeks (RR = 0.26, 95% CI: 0.17-0.40, p < 0.00001) and intervention times≥4weeks (RR = 0.35, 95% CI: 0.22-0.54, p < 0.00001). For axillary vein maximum velocity, the difference was statistically significant for both intervention time <4weeks (SMD = 0.73, 95% CI: 0.55-0.91, p < 0.00001) and intervention time ≥4weeks (SMD = 1.18, 95% CI: 0.18-2.19, p = 0.02). For axillary vein time-mean flow velocity, the intervention time <4weeks (SMD = 0.75, 95% CI: 0.46-1.04, p < 0.00001), and the difference was statistically significant; while ≥4weeks, the difference was not statistically significant (SMD = 1.14, 95% CI: -0.07 to 2.35, p = 0.06). Exercise therapy improved venous blood flow velocity and effectively reduced the incidence of PICC-associated VTE. However, RCTs with large samples and high quality are needed to further evaluate the effectiveness of exercise therapy in PICC patients.

A Deep Learning Approach to Speech Recognition for Detection of Mental Disorders

Mental disorders are conditions that affect a person’s cognitive functions, behavior or thinking, thereby impairing daily functions. The dearth of trained psychologists to the high number of patients living with a mental disorder pose significant challenges in the field of mental health. This study investigates the application of deep learning techniques to speech recognition for the purpose of detecting mental disorders. The main objective of this study is to effectively identify speech patterns associated with various mental disorders and thereafter develop a robust and accurate deep learning model system that can detect risk of a mental disorder in an individual based on their voice. The research methodology involved the collection of a dataset consisting of speech recordings from individuals diagnosed with depression and post-traumatic stress disorder (PTSD). The dataset acquired was carefully curated to include symptom severity levels, and linguistic variations. The results of this study demonstrate the effectiveness of deep learning approaches in speech recognition for mental disorder detection. The trained models achieved 95% and 94% accuracy rates in identifying and differentiating speech patterns associated with depression and PTSD respectively. The findings of this study have significant implications for the field of mental health. The developed deep learning system offers a promising avenue for the early detection and monitoring of mental disorders. Further research is warranted to validate and refine the developed models using larger and more diverse dataset. Additionally, the integration of multimodal data, such as combining speech analysis with psychological or text-based data, could enhance the diagnostic accuracy and reliability of the system. Keywords: Deep Learning, Mental Disorder, Post-traumatic Stress Disorder, Speech Recognition, Depression.

Unsupervised Learning Enables Extraction of Tactile Information From Text Database

In this work, we propose a new approach to tactile research using natural language processing of archival word corpus as the database. Tactile perception, or assessment of surfaces, is recognized as a language. Thus, by extracting touch-related words and sentences from a text corpus and learning their relationships, we can ultimately learn how humans perceive surfaces. We selected 6 adjectives and 42 onomatopoeias in Japanese as our tactile words. The adjectives represent physical properties, such as roughness and hardness, while onomatopoeias, such as “zara-zara” and “tsuru-tsuru,” are widely used to describe surfaces in Japanese and can correspond to both physical texture cognition and affective cognition. First, using natural language processing of word corpora, we successfully mapped the onomatopoeias with respect to the 6 adjectives, which matched well with the results based on an enquete-based survey. This verified the effectiveness of natural language processing for tactile research. In addition, principal component analysis revealed new tactile dimensions based on onomatopoeias, which we presumably assessaffective tactile dimensions. The proposed approach using natural language processing of archival text databases can provide a large number of datasets for tactile research and culminate in new findings and insights.

A Study of BERT-Based Classification Performance of Text-Based Health Counseling Data

The entry into a hyper-connected society increases the generalization of communication using SNS. Therefore, research to analyze big data accumulated in SNS and extract meaningful information is being conducted in various fields. In particular, with the recent development of Deep Learning, the performance is rapidly improving by applying it to the field of Natural Language Processing, which is a language understanding technology to obtain accurate contextual information. In this paper, when a chatbot system is applied to the healthcare domain for counseling about diseases, the performance of NLP integrated with machine learning for the accurate classification of medical subjects from text-based health counseling data becomes important. Among the various algorithms, the performance of Bidirectional Encoder Representations from Transformers was compared with other algorithms of CNN, RNN, LSTM, and GRU. For this purpose, the health counseling data of Naver Q&A service were crawled as a dataset. KoBERT was used to classify medical subjects according to symptoms and the accuracy of classification results was measured. The simulation results show that KoBERT model performed high performance by more than 5% and close to 18% as large as the smallest.