Big Data Methods Research Articles

Learners' Autonomous Learning Behavior in Distance Reading Based on Big Data

Some learners couldn’t get ideal learning results from distance education, to find out the root of this problem, their learning behavior and initiative should be analyzed in real time. However, in existing research results, the collected distance learning behavior data of learners are not pertinent enough, the extraction methods of big data are not proper enough, and the analysis models of learning behavior are not scientific enough. For these reasons, this paper analyzed the autonomous learning behavior of learners during distance reading based on big data, and gave the analysis contents and methods. In the text, a sequence diagram transformation method that is self-adaptive to long and short sequences had been introduced to process the learning behavior data of learners, who were then classified according to the features of different autonomous learning behavior sequences. Then, an attribute reduction algorithm based on improved Bayesian fuzzy rough set was adopted for attribute reduction, and the behavior indexes that are closely related to the autonomous learning effect of learners were selected for correlation analysis. After that, this paper proposed a method for detecting non-autonomous learning behavior based on multiple time scales, combining short-term autonomous learning pattern with long-term autonomous learning behavior and resource access behavior, this paper also analyzed the typical autonomous learning pattern of learners through the learning of hidden layer features. At last, experimental results proved the effectiveness of the proposed analysis method.

Computer-Aided College English Teaching System Based on Virtual Reality and Artificial Intelligence

People are realizing that linguistic competence is a vital aspect of communicative competence as language study and instruction have progressed. Grammar instruction is not only important but also the primary means of achieving communication skills in foreign language classes. This article focuses on the computer vision and machine learning-based virtual reality technology college English immersive context teaching approach. The goal is to increase pupils’ capacity to learn English. The experimental groups used VR innovation immersive environment education from the standpoint of constructivist theory in a compared teaching experiment with 2 classifications of freshman at a university, while the control class used standard multimedia equipment and conventional teaching techniques. Students only passively acquire a lot of material from instructors in the class, they have limited opportunity to engage in the exchange of information and express thoughts in the chosen language, and they are “immersed” in the Chinese environment most of the time. With an average score of 2.8 points higher than the control group, the overall English level was likewise higher. English teaching system based on computer big data method, optimization of oral English teaching system based on computer-aided technology, and artificial intelligence are the existing methods used for comparison. This demonstrates that using constructivism theory and virtual reality technology in college English immersing contextual education may genuinely increase students’ English levels.

Analyzing Visitors’ Review of Homestays Located in Nature-Based Settings: An NLP Based Approach

Objective: Sentiment analysis techniques such as Natural Language Processing (NLP) provide a powerful tool to analyze textual data. Along with machine learning and other big data methods, these techniques are used in improving customer service quality in different sectors. This paper utilizes sentiment analysis techniques to identify key themes surrounding visitors’ homestay experience in nature-based settings. Methodology/Approach/Scope: Analysis of 2369 TripAdvisor reviews through Structural Topic Modeling (STM) reveals how high rated homestay experiences differ from those rated low on various parameters. Findings/ Implications/Conclusion – The paper contributes to the knowledge on text mining & its application in improving customer service in the hospitality &tourism domain. The research has practical usage for homestay stakeholders and future direction for further research.

A century of integrated research on the human-environment system in Chinese human geography

Research on the integration of the human-environment system has been an important part of Chinese human geography for over a century, constituting the distinctive academic nature of the field. Human geography has been established as an interdiscipline of natural science and social science, highlighting the combination of academic inquiry and decision application, and exploring the interaction mechanisms and sustainable development model between the human sphere and natural sphere at different spatial scales. The development of the discipline is in line with the basic concepts advocated by the global research platform “Future Earth”, which has promoted the strong development of human geography in China, and has produced important societal influences. By selecting some of the most influential academic achievements, this paper briefly describes theoretical methods and social contributions to reflect the development process of human geography in the study of integrated human and environment systems in different stages in China. It also demonstrates the influence of the following elements on the adherence of Chinese human geography to the integration of human and environment systems: classical Chinese philosophical thinking on harmony between people and land, western theories of the human-environment relationship, Soviet economic geography research methods, the science of sustainability, the social demands of the construction of contemporary Chinese ecological civilization, ever-improving mathematical models and big data methods for studying enormous and complex systems, and management system reform and special scientific research system and background in China.

Construction of Higher Education Management Data Analysis Model Based on Association Rules

This paper adopts the analytical method of intelligent programming to conduct in-depth research and analysis on university education management and designs a corresponding university education management model to be applied in actual teaching. Based on the basic theories and methods of big data distributed data mining and machine learning, automated machine learning, and big data programming computational methods, this paper combines the importance and technical challenges of the algorithms themselves and the background of the practical application needs of the industry and firstly selects a series of data mining and machine learning algorithms that are commonly used based on high complexity, outstanding computational efficiency problems, and difficult to design distributed algorithms. The research on efficient large-scale distributed parallelized data mining and machine learning methods and algorithms is carried out. As an innovative teaching model, the experiential teaching model focuses on the cultivation of individual students’ independent learning ability and subjective initiative, which not only can effectively activate the classroom atmosphere and improve the teaching effect but also meet the requirements of classroom teaching for the development of the times. The empirical evidence of the experiential teaching model proposed in this paper is carried out, and the implementation process of the experiential teaching model of high school physics is further improved. In terms of the overall implementation effect, the experiential teaching model proposed in the paper can deepen students’ understanding of concepts and physical laws, thus enabling them to solve physics problems better, and has a positive and active effect on enhancing students’ learning interests and attitudes. In the case of system security, the average comprehensive index of each unit is 61.11, 22 are higher than the average index, accounting for 61.11%, 14 are lower than the average index, accounting for 38.89%, and 23 management departments’ management systems passed the safety monitoring, accounting for 63.89%. At the same time, the proposed model also provides educational practitioners with a more reliable framework for instructional design, which has realistic reference value and significance.

Outline and Impact of Firms Related to the Third Industrial Revolution: Investigation through Big Data

This article is focusing on the dynamism of the Third Industrial Revolution (TIR) in the region Hauts-de-France between 2013 and 2018. Region Hauts-de-France has been a forerunner in setting up a proactive policy in favour of the TIR. It provides a relevant and suitable context for the identification of TIR activities. We assess the job dynamism of the TIR through the implementation of big data methods for the identification of the firms involved in the TIR activities and the collection of firm microlevel data. We provide evidence of the strong dynamism of the TIR activities in a context of weak regional dynamics. We show that the growth in employment arises mainly from renewable energies, positive energy buildings, circular economy and energy efficiency. Future researches are encouraged to investigate the quality of employment and to question the distinctive characteristics of the firms involved in TIR.

Stress and the brain transcriptome: Identifying commonalities and clusters in standardized data from published experiments

Interpretation of transcriptomic experiments is hindered by many problems including false positives/negatives inherent to big-data methods and changes in gene nomenclature. To find the most consistent effect of stress on brain transcriptome, we retrieved data from 79 studies applying animal models and 3 human studies investigating post-traumatic stress disorder (PTSD). The analyzed data were obtained either with microarrays or RNA sequencing applied to samples collected from more than 1887 laboratory animals and from 121 human subjects.Based on the initial database containing a quarter million differential expression effect sizes representing transcripts in three species, we identified the most frequently reported genes in 223 stress-control comparisons. Additionally, the analysis considers sex, individual vulnerability and contribution of glucocorticoids. We also found an overlap between gene expression in PTSD patients and animals which indicates relevance of laboratory models for human stress response. Our analysis points to genes that, as far as we know, were not specifically tested for their role in stress response (Pllp, Arrdc2, Midn, Mfsd2a, Ccn1, Htra1, Csrnp1, Tenm4, Tnfrsf25, Sema3b, Fmo2, Adamts4, Gjb1, Errfi1, Fgf18, Galnt6, Slc25a42, Ifi30, Slc4a1, Cemip, Klf10, Tom1, Dcdc2c, Fancd2, Luzp2, Trpm1, Abcc12, Osbpl1a, Ptp4a2). Provided transcriptomic resource will be useful for guiding the new research.

Investigating the Potential of Data Science Methods for Sustainable Public Transport

The planning and implementation of public transport involves many data sources. These data sources in turn generate a high volume of data, in a wide variety of formats and data rates. This phenomenon is reinforced by the ongoing digitization of public transport; new data sources have continuously emerged in public transport in recent years and decades. This results in a great potential for the application and utilization of data science methods in public transport. Using big data methods and sources can, or in some cases already does, contribute to a better understanding and the further optimization of public transport networks, public transport service and public transport in general. This paper classifies data sources in the field of public transport and examines systematically for which use cases the data are used or can be used. These steps contribute by structuring ongoing discussions about the application of data science in the public transport domain and illustrate the potential of the application of data science for public transport. We present several use cases in which we applied data science methods, such as machine learning and visualization to public transport data. Several of these projects use data from automated passenger information systems, a data source that has not been widely studied to date. We report our findings for these use cases and discuss the lessons learned, to inform future research on these use cases and discuss their potential. This paper concludes with a summary of the typical problems that occur when dealing with big public transport data and a discussion of solutions for these problems. This discussion identifies future work and topics worth investigating for public transport companies as well as for researchers. Working on these topics will, in our opinion, support the improvement of public transport towards the efficiency and attractiveness that is needed for public transport to play its essential role in future sustainable mobility. The application of these methods in public transport requires the collaboration of domain experts with researchers and data scientists, calling for a mutual understanding. This paper also contributes to this understanding by providing an overview of the methods that are already used, potential new use cases, data sources, challenges and possible solutions.

A Big Data Method Based on Random BP Neural Network and Its Application for Analyzing Influencing Factors on Productivity of Shale Gas Wells

In recent years, big data and artificial intelligence technology have developed rapidly and are now widely used in fields of geophysics, well logging, and well test analysis in the exploration and development of oil and gas. The development of shale gas requires a large number of production wells, so big data and artificial intelligence technology have inherent advantages for evaluating the productivity of gas wells and analyzing the influencing factors for a whole development block. To this end, this paper combines the BP neural network algorithm with random probability analysis to establish a big data method for analyzing the influencing factors on the productivity of shale gas wells, using artificial intelligence and in-depth extraction of relevant information to reduce the unstable results from single-factor statistical analysis and the BP neural network. We have modeled and analyzed our model with a large amount of data. Under standard well conditions, the influences of geological and engineering factors on the productivity of a gas well can be converted to the same scale for comparison. This can more intuitively and quantitatively reflect the influences of different factors on gas well productivity. Taking 100 production wells in the Changning shale gas block as a case, random BP neural network analysis shows that maximum EUR can be obtained when a horizontal shale gas well has a fracture coefficient of 1.6, Type I reservoir of 18 m thick, optimal horizontal section of 1600 m long, and 20 fractured sections.

COVID-19 Induced Misinformation on YouTube: An Analysis of User Commentary

Several scholars have demonstrated a positive link between political polarization and the resistance to COVID-19 prevention measures. At the same time, political polarization has also been associated with the spread of misinformation. This study investigates the theoretical linkages between polarization and misinformation and measures the flow of misinformation about COVID-19 in the comment sections of four popular YouTube channels for over 16 months using big data sources and methods. For the analysis, we downloaded about 3.5M English language YouTube comments posted in response to videos about the pandemic. We then classified the comments into one of the two following categories by applying a supervised Natural Language Processing classifier: (1)fake: comments that contain claims and speculation which are verifiably not true; and (2)legitimate:comments that do not fall into the fake category. The results show that the level of misinformation in YouTube comment sections has increased during the pandemic, that fake comments attract statistically more likes, and that the ratio of fake comments increased by 0.4% per month. These findings suggest that once introduced into an online discussion, misinformation potentially leads to an escalating spiral of misinformation comments, which undermines public policy. Overall, the results signal alarming pandemic-related misinformation and, potentially, rising levels of affective polarization. We place these results in context and point out the limitations of our approach.

SPATIAL DATABASES OF AGRONOMIC GEOINFORMATION SYSTEMS

The work is devoted to the development of spatial databases for the assessment of agricultural land. The geodatabase is aimed at geoinformation support of assessment, agroecological typing (groups, types of land) of agricultural lands, development of adaptive-landscape farming systems. The paper presents the structure of the database of regional and local levels. Three different ways of user interaction with the AgroGIS database are proposed. For practical implementation, it is proposed to use the object-functional approach to database development, based on the use of cloud data storage technology in the DBMS SQlite.
 Background. Geoinformation support of agronomic geoinformation systems (AgroGIS) is aimed at assessing natural-territorial conditions and environmental factors in agrolandscapes, development of adaptive landscape farming systems. AgroGIS geodatabases serve to store, analyze and present spatial information on agricultural land. As shown by an analysis of literary sources, the term “geodatabase” was formed more than twenty years ago. At the same time different geodatabases are known: archaeological, cartographic, soil and others. They differ in the object of research, structure and content, as well as the way of data organization. This indicates the relevance of the topics of the present research.
 Purpose. The purpose of the work is to develop the structure and content of the geodatabase agronomic GIS.
 Materials and methods. The object-functional approach to database development, which is supported by object-oriented database management systems (DBMS) and classical relational DBMS, is used. The essence of this approach is to implement functional tasks taking into account the needs of the user.
 Results. The main components of geodatabase in the form of separate sets of spatial classes (Climate, Relief, Soil, Vegetation, Hydrography, Agrolandscape) are proposed. At the same time the paper shows the need for practical implementation of agronomic geoinformation geodatabases from several aspects.
 Conclusion. In the development of spatial databases of agronomic GIS the most important feature is the ability to constantly update information in the form of temporal component. Practical implementation of temporal geodatabases is possible with the use of non-relational database management systems, as well as methods of processing big data (Big Data).

Affective State Recognition in Livestock-Artificial Intelligence Approaches.

Simple SummaryEmotions or affective states recognition in farm animals is an underexplored research domain. Despite significant advances in animal welfare research, animal affective state computing through the development and application of devices and platforms that can not only recognize but interpret and process the emotions, are in a nascent stage. The analysis and measurement of unique behavioural, physical, and biological characteristics offered by biometric sensor technologies and the affiliated complex and large data sets, opens the pathway for novel and realistic identification of individual animals amongst a herd or a flock. By capitalizing on the immense potential of biometric sensors, artificial intelligence enabled big data methods offer substantial advancement of animal welfare standards and meet the urgent needs of caretakers to respond effectively to maintain the wellbeing of their animals.Farm animals, numbering over 70 billion worldwide, are increasingly managed in large-scale, intensive farms. With both public awareness and scientific evidence growing that farm animals experience suffering, as well as affective states such as fear, frustration and distress, there is an urgent need to develop efficient and accurate methods for monitoring their welfare. At present, there are not scientifically validated ‘benchmarks’ for quantifying transient emotional (affective) states in farm animals, and no established measures of good welfare, only indicators of poor welfare, such as injury, pain and fear. Conventional approaches to monitoring livestock welfare are time-consuming, interrupt farming processes and involve subjective judgments. Biometric sensor data enabled by artificial intelligence is an emerging smart solution to unobtrusively monitoring livestock, but its potential for quantifying affective states and ground-breaking solutions in their application are yet to be realized. This review provides innovative methods for collecting big data on farm animal emotions, which can be used to train artificial intelligence models to classify, quantify and predict affective states in individual pigs and cows. Extending this to the group level, social network analysis can be applied to model emotional dynamics and contagion among animals. Finally, ‘digital twins’ of animals capable of simulating and predicting their affective states and behaviour in real time are a near-term possibility.

Review of "Composition and Big Data edited by Amanda Licastro and Benjamin Miller," Licastro, A. & Miller, B. (Eds.). (2021). Composition and big data . University of Pittsburg Press.

The evolution of digital tools and platforms has ushered in new possibilities for researchers, scholars, and practitioners of rhetoric and composition and adjacent fields like technical communication. These technologies change the ways we can gather, store, and use larger datasets, prompting new discussions on what big data methods look like in the field. The chapters housed in Amanda Licastro and Benjamin Miller's edited collection Composition and Big Data investigate the promises, concerns, and areas for further conversation regarding the applications of big data methods in composition-focused research.

Tax evasion risk management using a Hybrid Unsupervised Outlier Detection method

Big data methods are becoming an important tool for tax fraud detection around the world. Unsupervised learning approach is the dominant framework due to the lack of label and ground truth in corresponding datasets, although these methods suffer from lower interpretability and precision compared with supervised approaches. In contrast to prior research works, we examine the possibility of a hybrid unsupervised method for tax evasion risk management that is able to internally validate and explain outliers detected in a given tax dataset. The proposed method, HUNOD (Hybrid UNsupervised Outlier Detection),11HUNOD is an abbreviation for “Hybrid UNsupervised Outlier Dection”. combines clustering and representation learning for robust outlier detection, additionally allowing its users to incorporate relevant domain knowledge into both constituent outlier detection approaches in order to identify outliers relevant for a given economic context. The interpretability of obtained outliers is achieved by training explainable-by-design surrogate models over internally validated outliers. The experimental evaluation of the HUNOD method is conducted on two datasets derived from the database on individual personal income tax declarations collected by the Tax Administration of Serbia. The obtained results show that the method indicates between 90% and 98% internally validated outliers depending on the clustering configuration and employed regularization mechanisms for representational learning.

Grade Inflation in Schools During the COVID-19 Pandemic: Unexpected Effect or Anti-Crisis Strategy?

The closure of educational institutions and the transfer of the learning process to a distance format during the COVID-19 pandemic came as a shock to everyone involved in the educational process. There was, in fact, a rupture of the educational everyday — the normal and unproblematic order of things. A “new normal”, as it came to be called, could not emerge immediately — it had to be reconstructed within the unaccustomed contexts of distance interaction for many. Collective practices of this construction were and are captured today in the narratives of their participants — teachers, students and sometimes their parents. This study attempts, through quantitative analysis, to describe the transformation of assessment in schools during the pandemic and to formulate a hypothesis as to the possible reason for the change in marking practices as one of the most significant ways of managing the learning process as well as the social and psychological context of its implementation.
 The data source used was a database of students’ grades from schools in one of the regions of the Russian Federation, accumulated from 2015 to 2021. Using big data methods and the Cohen effect coefficient, the main changes in assessment are described. Particular attention is paid to the few months of 2020, when all schools in the region were closed to face-to-face attendance. It is during this period that a significant inflationary spike in marking is recorded.
 It is suggested that teachers deliberately use the strategy of inflating marks in order to maintain a favorable social and psychological climate in school classes and to reduce the general tension in connection with the transition to the distance learning format. An attempt has been made to theorize a strategy for the grade inflation behavior during a period of cataclysm.

Exploring Evaluation of Enterprise Economic Benefits Using Big Data.

The purpose is to improve Chinese enterprises' economic benefit evaluation system based on big data and promote sustainable enterprise production. This paper studies the power supply enterprises-oriented Evaluation Index System (EIS) under the big data environment. Firstly, it expounds on the construction theory of the enterprise economic benefit model. Secondly, the comprehensive Grey Model (GM) based on improved weight and the power consumption prediction model based on Least Mean Square (LMS) neural network (NN) algorithm are introduced. Finally, the comprehensive GM model based on improved weight is used to evaluate the economic benefits of power supply enterprises. The power consumption prediction model based on the LMS-NN algorithm is used to predict the sustainable development of power supply enterprises. The results show that the profitability and solvency of joint-stock power companies are about 90 and 100, respectively, and the social contribution of state-owned power supply enterprises is the strongest. Lastly, it is predicted that the region will have 134.8 billion kWh of electricity and about 137.2 billion kWh of power consumption in 2020. The growth model and trend are consistent, but there are some errors in the specific power consumption data. Therefore, the audit method based on big data has a good evaluation effect on the economic benefits of enterprises. For example, the profits of private and joint-stock power supply enterprises are relatively high. In contrast, state-owned power supply enterprises have outstanding social contribution ability. The big data method is used to predict the power consumption in some areas, and the predicted value is consistent with the actual value. This study provides a reference for the follow-up economic benefit evaluation and sustainable development of enterprises.

Optimization Simulation of Supply-Side Structure of Agricultural Economy Based on Big Data Analysis in Data Sharing Environment.

Big data is transforming how people live their lives, and the widespread use of information technology has tremendously aided in the development and deployment of big data technologies. The use of big data technology can lower agricultural production and distribution costs, increase agricultural modernization's effectiveness, and support the transformation and upgrading of the agricultural economy. Big data technology has garnered a lot of attention as a burgeoning technological area. Big data has revolutionised the service model for “agriculture, rural areas, and farmers” and given agricultural economy supply-side structure optimization new life. In the age of big data, we should reexamine the way agricultural economic information is currently released, propose more scientific techniques for doing so, and improve the effectiveness of implementation across the board. In light of the background of big data, this research investigates and evaluates the supply-side structure of the agricultural sector. The big data method is combined in this work to explore and analyse it. This study shows that the supply-side structure of the agricultural economy, when seen against the backdrop of big data, has a definite impact, with an impact as high as 56.56%. This essay lays the groundwork for future agricultural economy research and development.

Fault Prediction of Elevator Door Lock Based on MPGA-BP Algorithm

The door lock is one of the elevator fault prone parts, and the fault may further lead to personal injury accidents. In the process of elevator operation, the door lock acts frequently, resulting in a large amount of operation data. Using big data method, the fault prediction of elevator door lock could be realized, so as to prevent and reduce accidents. BP (Back Propagation) neural network algorithm and GA-BP (Genetic Algorithm) were used as door lock fault prediction algorithms, but there were some defects in performance. BP algorithm was easy to fall into local minima and the convergence speed was uncertain, while GA-BP algorithm would reduce the genetic diversity of the population. In this paper, we use MPGA (Multiple Population Genetic Algorithm) to improve the initial weight threshold of BP algorithm, adjust the neural network, and establish a door lock fault prediction model. The simulation results show that MPGA-BP model greatly improves the generalization ability and prediction accuracy of BP neural network, compared with traditional BP and GA-BP model.

The Credit Assessment for Chinese Companies Based on the Café System by Using Bigdata Method

The Credit Assessment for Chinese Companies Based on the Café System by Using Bigdata Method

QUANTITATIVE ASSESSMENT OF TECHNOLOGICAL SINGULARITY

The article deals with the topical issue of quantitative assessment of technological singularity. The authors made an analysis of artificial intelligence tools and approaches affecting the development of superintelligence, which allowed for the first time to develop a general multifactor model of technological singularity and present it in the space of direct and indirect indicators of development. The developed approach makes it possible to move from expert judgments on the issue of technological singularity in the form of extrapolated complexity curves of various systems or qualitative description of possible scenarios of technological development to quantitative assessment of the state of technological singularity. The links between the relevant functional areas of human intelligence and modern expert systems are formalized, a structural-functional model of knowledge acquisition is developed. A conclusion is made about the real limits of the processes of modern "intelligent" systems at the level of artificial thinking and logical cognition, which corresponds to a weak artificial intelligence. The state and ways of hardware development were analyzed, which allowed making a conclusion about the complex use of different hardware architectures and information processing principles: supercomputer, neurosynaptic and quantum computers to implement the concept of technological singularity. Formalized in the form of a structural model the areas of research most influential in the development of artificial intelligence, and their relationship to existing approaches and methods of processing big data. For the first time proposed the classification of indicators of development of artificial intelligence within two classes: direct and indirect, grouped into three groups: the intensity of research and public activity; the level of applied (technological) solutions; practical implementation, most affecting the development of general artificial intelligence. The correlation between the formalized groups of indicators was revealed, which confirms the correctness of the hypothesis about the cause-effect relationship between the groups: theoretical research → applied solutions → practical implementation and their mutual influence.