THE APPLICATION OF BIG DATA
TECHNOLOGY IN ONLINE SUBJECT
EDUCATION INNOVATION RESEARCH
Chengyi Huang*
College of Teacher Education, Chongqing Three Gorges University, Chongqing,
404100, China.
lovens2018@163.com
Wengxi Tan
College of Teacher Education, Chongqing Three Gorges University, Chongqing,
404100, China.
Xin Yan
College of Teacher Education, Chongqing Three Gorges University, Chongqing,
404100, China.
Yun Tan
College of Teacher Education, Chongqing Three Gorges University, Chongqing,
404100, China.
Heyue Wan
College of Teacher Education, Chongqing Three Gorges University, Chongqing,
404100, China.
Reception: 13/04/2023 Acceptance: 16/06/2023 Publication: 03/07/2023
Suggested citation:
Huang, C., Tan, W., Yan, X., Tan, Y. and Wan, H. (2023). The application of big
data technology in online subject education innovation research. 3C
Tecnología. Glosas de innovación aplicada a la pyme, 12(2), 269-282. https://
doi.org/10.17993/3ctecno.2023.v12n2e44.269-282
https://doi.org/10.17993/3ctecno.2023.v12n2e44.269-282
3C Tecnología. Glosas de innovación aplicadas a la pyme. ISSN: 2254-4143
Ed.44 | Iss.12 | N.2 April - June 2023
269
ABSTRACT
This paper applies big data technology to promote the innovative development of
online subject education and improve students' self-learning efficiency to promote
innovative management interaction in the education industry. In the design process,
big data technology is used to mine and analyze massive educational data, combine
the learning needs of online subjects, and provide technical support for six application
levels of the online subject education system. Document transformation of education
data is performed through the DCF mechanism, and the synchronization time slot is
divided into a safe time slot and a reservation time slot. Then, the adaptive
recommendation function is used to extract valuable information from behavioral data
for personalized learning resource pushing. To verify the practical application effect of
big data technology in the online subject education innovation system, the simulation
analysis results show that after applying big data technology, the recommended
resources preference of the education system is above 86%, the subject coverage
rate is 90.48%, and the performance of test scores is improved by 17.5% relative to
Class C. This shows that big data technology optimizes the application mode of online
subject education and can provide students with better-quality educational resources.
KEYWORDS
Big data technology; online subject education; DCF mechanism; adaptive
recommendation function; subject coverage
INDEX
ABSTRACT
KEYWORDS
1. INTRODUCTION
2. ADVANTAGES OF BIG DATA TECHNOLOGY
3. APPLICATION OF BIG DATA TECHNOLOGY IN THE ONLINE EDUCATION
SYSTEM
3.1. Educational system application of big data
3.2. Transforming document data
3.3. Adaptive application of big data technology
4. ONLINE DISCIPLINE EDUCATION INNOVATION RESEARCH RESULTS
4.1. Effectiveness of educational resources recommendation
4.2. Evaluation results of education fitting indicators
4.3. Regression analysis of test scores
5. 5. CONCLUSION
REFERENCES
https://doi.org/10.17993/3ctecno.2023.v12n2e44.269-282
3C Tecnología. Glosas de innovación aplicadas a la pyme. ISSN: 2254-4143
Ed.44 | Iss.12 | N.2 April - June 2023
270
ABSTRACT
This paper applies big data technology to promote the innovative development of
online subject education and improve students' self-learning efficiency to promote
innovative management interaction in the education industry. In the design process,
big data technology is used to mine and analyze massive educational data, combine
the learning needs of online subjects, and provide technical support for six application
levels of the online subject education system. Document transformation of education
data is performed through the DCF mechanism, and the synchronization time slot is
divided into a safe time slot and a reservation time slot. Then, the adaptive
recommendation function is used to extract valuable information from behavioral data
for personalized learning resource pushing. To verify the practical application effect of
big data technology in the online subject education innovation system, the simulation
analysis results show that after applying big data technology, the recommended
resources preference of the education system is above 86%, the subject coverage
rate is 90.48%, and the performance of test scores is improved by 17.5% relative to
Class C. This shows that big data technology optimizes the application mode of online
subject education and can provide students with better-quality educational resources.
KEYWORDS
Big data technology; online subject education; DCF mechanism; adaptive
recommendation function; subject coverage
INDEX
ABSTRACT
KEYWORDS
1. INTRODUCTION
2. ADVANTAGES OF BIG DATA TECHNOLOGY
3. APPLICATION OF BIG DATA TECHNOLOGY IN THE ONLINE EDUCATION
SYSTEM
3.1. Educational system application of big data
3.2. Transforming document data
3.3. Adaptive application of big data technology
4. ONLINE DISCIPLINE EDUCATION INNOVATION RESEARCH RESULTS
4.1. Effectiveness of educational resources recommendation
4.2. Evaluation results of education fitting indicators
4.3. Regression analysis of test scores
5. 5. CONCLUSION
REFERENCES
https://doi.org/10.17993/3ctecno.2023.v12n2e44.269-282
1. INTRODUCTION
Online subject education is an Internet-mediated way of teaching and learning,
which crosses the time and space limitations of teaching and learning. Compared with
traditional education, online education is characterized by low threshold, high
efficiency, and abundant teaching resources [1]. Online education adopts diversified
teaching forms, delivers resource information through multimedia network technology,
combines the real world offline with the virtual world online, and enables learners to
grasp learning content better and faster, playing a unique role with its unique concepts
and methods [2-4]. In this context, the concept of big data and corresponding
technologies can enable the identification of educational data and the mining of its
implied information value to achieve a two-way balance between online educational
services and learners' needs [5].
With the development of big data technology, the education industry has
increasingly shown a trend of technology integration. For example, the literature [6]
constructed an online education evaluation model by analyzing the application of
current scientific paradigms in the field of education, which promoted the development
of a new paradigm for the study of big data online education technology. By applying
this paradigm, a series of educational evaluation models have been constructed at
macro and micro levels, which play an active role in the practice and evaluation of
education. The literature [7] used the Asia-Pacific Network for Health Professions
Education Reform to assess students in five Asian countries on their attitudes and
willingness to work in rural areas. The pretested anonymous questionnaire consisted
of four parts, including demographic data, attitudes toward working in rural areas,
location of work after graduation, and perceptions of the respondent's competence.
The findings showed that about 60% of the students in Bangladesh and Thailand had
positive attitudes towards working in rural areas, compared to 50% in both China and
India and only 33% in Vietnam. The literature [8] developed a theoretical model to
identify the factors influencing BDA in higher education by combining the technology
organization environment and innovation diffusion. In the development process, the
moderating effects of university size and university age were added to the developed
model using the technological factors in BDA. Structural equation modeling was used
to test the research model and 195 data samples were collected from campus
administrators of virtual universities in Pakistan using an online questionnaire to
demonstrate the relative merits of the theoretical model in educational management.
The literature [9] innovated the management of university online educational records
in the context of big data and designed a model for evaluating the construction of
university online records to further promote digital records services in universities. The
calculation and survey research methods of this model play an important influential
role in the process of developing and utilizing archival information resources in
colleges and universities. The literature [10] constructed a personalized dynamic
evaluation model based on artificial intelligence big data technology to make
evaluation the center of online education and teaching efforts. To verify the
performance of the designed model, the article conducted model analysis through a
https://doi.org/10.17993/3ctecno.2023.v12n2e44.269-282
3C Tecnología. Glosas de innovación aplicadas a la pyme. ISSN: 2254-4143
Ed.44 | Iss.12 | N.2 April - June 2023
271
practical teaching method. The results of the study showed that the model it
constructed had good performance and improved the effectiveness of online
education quality management. Based on the big data cloud computing platform and
the application scenario of online education, the literature [11] redivided the functional
modules of the system and briefly designed the system according to the functional
requirements of users for the system. The core functional modules of the innovative
system include an online experiment module, online classroom module, video course
module, online examination module, and basic function module, which effectively
improve the comprehensive management of online education. To sum up, the
educational business module after using big data technology innovation, although
briefly satisfying the thematic needs of users, lacks the technical motivation for long-
term development, and does not fully reflect the market application value and
educational teaching value.
Based on this, in the process of application, this paper firstly uses big data
technology to perform predictable mining analysis on massive education data and
provides a simple and highly fault-tolerant architecture for massively parallel
processing of massive data. Secondly, the DCF mechanism is used to transform
education data documents, which effectively avoids the problem of large errors in the
collection process of online education data, and the synchronization time slot is
divided into a safe time slot and a reservation time slot in the channel reservation
scheme based on the DCF mechanism. Again, the big data interaction window is used
to realize the adaptive function of the online education system, to provide learning
strategies and guidance to learners by using evaluation feedback, and to establish an
adaptive question bank. Finally, the application of big data technology in online
subject education system is simulated and analyzed, and its application effect is
judged by the evaluation results of educational resources recommendation effect,
students' test results, and educational fitting indexes to provide a path reference for
the innovative application of online subject education.
2. ADVANTAGES OF BIG DATA TECHNOLOGY
Big data technology is a cutting-edge technology for data analysis, which can
quickly obtain valuable information from multiple types of data and access massive,
high growth rates and diverse information assets to provide stronger decision-making
power and process optimization for online subject education with new processing
models. The innovative advantages of big data technology applied to online subject
education are shown in Table 1.
https://doi.org/10.17993/3ctecno.2023.v12n2e44.269-282
3C Tecnología. Glosas de innovación aplicadas a la pyme. ISSN: 2254-4143
Ed.44 | Iss.12 | N.2 April - June 2023
272
practical teaching method. The results of the study showed that the model it
constructed had good performance and improved the effectiveness of online
education quality management. Based on the big data cloud computing platform and
the application scenario of online education, the literature [11] redivided the functional
modules of the system and briefly designed the system according to the functional
requirements of users for the system. The core functional modules of the innovative
system include an online experiment module, online classroom module, video course
module, online examination module, and basic function module, which effectively
improve the comprehensive management of online education. To sum up, the
educational business module after using big data technology innovation, although
briefly satisfying the thematic needs of users, lacks the technical motivation for long-
term development, and does not fully reflect the market application value and
educational teaching value.
Based on this, in the process of application, this paper firstly uses big data
technology to perform predictable mining analysis on massive education data and
provides a simple and highly fault-tolerant architecture for massively parallel
processing of massive data. Secondly, the DCF mechanism is used to transform
education data documents, which effectively avoids the problem of large errors in the
collection process of online education data, and the synchronization time slot is
divided into a safe time slot and a reservation time slot in the channel reservation
scheme based on the DCF mechanism. Again, the big data interaction window is used
to realize the adaptive function of the online education system, to provide learning
strategies and guidance to learners by using evaluation feedback, and to establish an
adaptive question bank. Finally, the application of big data technology in online
subject education system is simulated and analyzed, and its application effect is
judged by the evaluation results of educational resources recommendation effect,
students' test results, and educational fitting indexes to provide a path reference for
the innovative application of online subject education.
2. ADVANTAGES OF BIG DATA TECHNOLOGY
Big data technology is a cutting-edge technology for data analysis, which can
quickly obtain valuable information from multiple types of data and access massive,
high growth rates and diverse information assets to provide stronger decision-making
power and process optimization for online subject education with new processing
models. The innovative advantages of big data technology applied to online subject
education are shown in Table 1.
https://doi.org/10.17993/3ctecno.2023.v12n2e44.269-282
Table 1. Advantages of Big Data Technology in Online Education
As can be seen from Table 1, traditional education management cannot accurately
predict the number and type of resources needed for teaching activities, which often
results in too many or too few educational resources for a certain teaching activity, not
only causing serious waste or lack of educational resources but also making
educational resources a rope limiting the smooth development of teaching activities.
Big data technology can store a large amount of online learning data, and the storage
capacity of data can even reach the level of petabytes, which can be processed in
seconds for massive data. Big data technology can be used to analyze the future
trends of online education and provide the education industry with real-time insight
into the market changes and take corresponding measures quickly. This enables the
optimal allocation of educational resources so that each educational resource can be
used to the maximum extent.
3. APPLICATION OF BIG DATA TECHNOLOGY IN THE
ONLINE EDUCATION SYSTEM
3.1. EDUCATIONAL SYSTEM APPLICATION OF BIG DATA
With the support of big data technology, combined with the learning needs of online
subject education, big data technology can provide technical updates for six levels of
the online education system:
1.
User service layer. The users of online subject education platforms contain
teachers and learners, for whom big data technology can provide four types of
services: online teaching content, teaching management, communication and
interaction, and learning management. The teaching service of big data
technology will reconstruct the information resources according to the user's
demand and provide personalized service resources for the user. The user
does not need to know the resource integration process of the background
data, which is completely done by the data resource processing layer of the
system. For example: For teachers, the system will provide real-time feedback
on the analysis of learners, especially learning styles and preferences, and
Features Content
Large Volume
Storage is big and growing fast. Large amounts of data are generated in real
time and have now jumped from the TB level to the PB level.
Many Types
Many formats, including unstructured and structured data, data analysis
challenges the traditional data analysis processing capabilities.
Value Density
The value of data is large, but the value density is low. Analysis of massive data
mining, predictable analysis of future trends and patterns, deep and complex
analysis.
Speed
Fast processing and analysis will provide real-time insight into market changes,
rapid response measures and decision-making support for enterprises to grasp
market opportunities.
https://doi.org/10.17993/3ctecno.2023.v12n2e44.269-282
3C Tecnología. Glosas de innovación aplicadas a la pyme. ISSN: 2254-4143
Ed.44 | Iss.12 | N.2 April - June 2023
273
online interactive learning services.
2.
user interaction.
3.
platform.
4.
persistently in cloud storage data centers and keeping data updated in real-
enhanced data value.
massively parallel processing of massive amounts of data [13].
5.
system and improve the reliability and security of the system.
6.
https://doi.org/10.17993/3ctecno.2023.v12n2e44.269-282
3C Tecnología. Glosas de innovación aplicadas a la pyme. ISSN: 2254-4143
Ed.44 | Iss.12 | N.2 April - June 2023
274
conduct intelligent analysis of students' behavior and learning records on the
platform. For learners, the system will constitute a learning mode that
integrates learning, question and answer, assessment, and interaction, so that
learners can fully enjoy an autonomous learning atmosphere and multi-modal
online interactive learning services.
2. Client. Big data technology will create online education platform users through
computers and smart mobile terminal devices to complete the interface and
user interaction.
3. Basic application layer. Big data technology can support the online subject
education system and enable cloud service sharing if users access to the
platform.
4. Data storage layer. The data layer is the core of the architecture, which is
divided into three parts. The lower layer is the database, the middle layer is the
data mining and analysis integration, and the upper layer is the standardized
processing. In the face of rapidly increasing complex data, big data technology
will use cloud computing and big data technology for modern data
management of online subject education systems, storing all types of data
persistently in cloud storage data centers and keeping data updated in real-
time to lay the foundation for subsequent data sharing and analysis and
enhanced data value.
When online education data is analyzed and mined, the raw data will be scattered
in different data sources. The target-driven function of big data technology will read
the education data through the application program interface that comes with the
cloud storage, pre-process it using a mapping reduction algorithm, and the resulting
file can be applied by various data analysis techniques. System mapping is used to
map a set of key-value pairs into a new set of key-value pairs, specifying concurrent
simplification functions that are used to ensure that all mapped key-value pairs have a
shared set of identical keys [12]. This process can be iterated until the information is
sufficiently simplified, the essence of which is to use big data technology to refine
massive amounts of data to provide high-density value for data mining and
intelligence analysis, and to provide a simple and highly fault-tolerant architecture for
massively parallel processing of massive amounts of data [13].
5. Management platform layer. The main task of big data technology at the
management level is to realize the normal operation of the online education
system and improve the reliability and security of the system.
6. Infrastructure layer. The use of big data technology can solve the problem of
hardware silos in the operation of the system, and the centralized management
of hardware resources can improve the reliability and availability of the system.
The use of virtualization technology can enable hardware resources to be
realized, and the use of physical server virtual machines to isolate storage
resources can improve the integrated use of storage resources. Hardware
https://doi.org/10.17993/3ctecno.2023.v12n2e44.269-282
resources such as servers are integrated to form a dynamic resource allocation
that is dynamically assigned to each application system on demand. During
peak periods of application systems, Big Data technology dynamically
allocates more hardware resources as a way to get through peak periods and
automatically reclaims excess resources to be dispatched to other application
services or automatically shut down to extend hardware life.
3.2. TRANSFORMING DOCUMENT DATA
Online subject education requires that the data collected be relevant, reliable, and
timely. Applying big data technology to the data transformation process of online
subject education by using padding for document transformation can avoid the
problem of large errors in the data collection process [14-15]. Based on the DCF
mechanism (discounted free cash method), the designed data channel reservation
framework is shown in Figure 1.
Figure 1. Data channel reservation framework
As can be seen from Figure 2, in the DCF mechanism-based data channel
reservation scheme, the synchronization time slot is divided into a secure time slot
and a reservation time slot. In the secure time slot, the PCF mechanism in
IEEE802.11 wireless LAN is used. The system application within its communication
area sends its security-related message after receiving the polling message from the
system. Sending security messages within the security time slot is a contention-free
transmission, and this approach meets the requirements for low latency in online
subject education systems while ensuring the transmission of security messages.
Within the reservation time slot, the big data nodes are reserved on the CCH using
the basic access method of the DCF mechanism, and the specific reservation process
is as follows:
https://doi.org/10.17993/3ctecno.2023.v12n2e44.269-282
3C Tecnología. Glosas de innovación aplicadas a la pyme. ISSN: 2254-4143
Ed.44 | Iss.12 | N.2 April - June 2023
275
Step 1: Users who need to reserve SCH for uploading or downloading data
services need to send RFS packets at the CCH node with the DCF mechanism.
Step 2: After the OBU node successfully transmits the RFS packet, if there is a free
SCH in the system, the RSU will allocate an SCH channel to the desired OBU and
send an ID containing the allocation to the OBU. If there is no free SCH in the system,
the RSU will send a NAK to the OBU, and the OBU will enter the backoff process and
double the contention window.
Step 3: Upon receiving an ACK from RSU response, OBU immediately switches to
the assigned SCH and transmits the data file on the SCH within the specified time.
3.3. ADAPTIVE APPLICATION OF BIG DATA TECHNOLOGY
The adaptive function of big data technology can create different learning contexts
for online education systems and tailor learning strategies and paths for learners to
realize the educational means of tailoring education to meet the needs of personalized
learning [16], as shown in Figure 2.
Figure 2. Adaptive personalized recommendation process of the online education system
As can be seen from Figure 2, in the adaptive personalized recommendation
process, learners will generate learning behavior data after ability assessment and big
data technology will combine with data mining technology to extract valuable
information from the behavior data. Using big data technology to analyze learners'
personal characteristics and build a learner model library, personalized learning
resources are pushed using collaborative filtering recommendation algorithms.
In the process of learning personalized resources, the big data interaction window
can be used to achieve the adaptive function of the online education system [17].
During the interaction process, big data technology collects learner interaction data,
matches it with the knowledge base as the basis, and digs out the learning behavior
implied behind the interaction behavior. Through the analysis engine, the learner's
https://doi.org/10.17993/3ctecno.2023.v12n2e44.269-282
3C Tecnología. Glosas de innovación aplicadas a la pyme. ISSN: 2254-4143
Ed.44 | Iss.12 | N.2 April - June 2023
276
Step 1: Users who need to reserve SCH for uploading or downloading data
services need to send RFS packets at the CCH node with the DCF mechanism.
Step 2: After the OBU node successfully transmits the RFS packet, if there is a free
SCH in the system, the RSU will allocate an SCH channel to the desired OBU and
send an ID containing the allocation to the OBU. If there is no free SCH in the system,
the RSU will send a NAK to the OBU, and the OBU will enter the backoff process and
double the contention window.
Step 3: Upon receiving an ACK from RSU response, OBU immediately switches to
the assigned SCH and transmits the data file on the SCH within the specified time.
3.3. ADAPTIVE APPLICATION OF BIG DATA TECHNOLOGY
The adaptive function of big data technology can create different learning contexts
for online education systems and tailor learning strategies and paths for learners to
realize the educational means of tailoring education to meet the needs of personalized
learning [16], as shown in Figure 2.
Figure 2. Adaptive personalized recommendation process of the online education system
As can be seen from Figure 2, in the adaptive personalized recommendation
process, learners will generate learning behavior data after ability assessment and big
data technology will combine with data mining technology to extract valuable
information from the behavior data. Using big data technology to analyze learners'
personal characteristics and build a learner model library, personalized learning
resources are pushed using collaborative filtering recommendation algorithms.
In the process of learning personalized resources, the big data interaction window
can be used to achieve the adaptive function of the online education system [17].
During the interaction process, big data technology collects learner interaction data,
matches it with the knowledge base as the basis, and digs out the learning behavior
implied behind the interaction behavior. Through the analysis engine, the learner's
https://doi.org/10.17993/3ctecno.2023.v12n2e44.269-282
knowledge system is analyzed comprehensively to plan learning strategies in a
targeted manner, and different analysis tools are invoked according to different
analysis purposes by combining the learner's learning behaviors and interaction data.
Personalized test assessment through an adaptive question bank to establish data to
correlate with student behavior. Combine multidisciplinary techniques to predict
learners' learning behaviors and results, provide learning strategies and guidance to
learners using evaluation feedback or manual intervention, and build a library of
adaptive questions.
4. ONLINE DISCIPLINE EDUCATION INNOVATION
RESEARCH RESULTS
In this paper, big data technology is applied to an innovative system for online
subject education to optimize the teaching process of online subject education. To
verify the feasibility of this application, this paper analyzes the effect of educational
resources recommendation, education fitting index evaluation results, and test
performance regression results to determine the practical application of big data
technology in online subject education.
4.1. EFFECTIVENESS OF EDUCATIONAL RESOURCES
RECOMMENDATION
The evaluation metrics in this section are Educational resource preference, server
response time, and subject coverage metrics. Educational resource preference refers
to the degree of adaptation of the system to recommend content for users when they
search for resources. Server response time refers to the average recommendation
speed of the system. Coverage is an important metric used to evaluate the
recommendation system's recommendation capability, indicating the proportion of
items predicted by the algorithm to all items.
The recommendation effect of online subject education resources with big data
technology is compared with the recommendation effect of resources based on graph
embedding. The recommendation effect of big data technology is based on the
weighted calculation of the number of user clicks and user favorites, and the more
clicks and favorites a knowledge point has, the more popular the knowledge point is.
The graph-embedded resource recommendation system is based on the number of
clicks by users. The results of this experiment are shown in Figure 3, where the
recommendation lists of length 100em-800emem are compared.
https://doi.org/10.17993/3ctecno.2023.v12n2e44.269-282
3C Tecnología. Glosas de innovación aplicadas a la pyme. ISSN: 2254-4143
Ed.44 | Iss.12 | N.2 April - June 2023
277
(a) Resource recommendation based on graph embedding
(b) Resource recommendation for big data technology
Figure 3. Comparison of the effect of educational resources recommendation
cannot meet the long-term development goal of online subject education.
https://doi.org/10.17993/3ctecno.2023.v12n2e44.269-282
3C Tecnología. Glosas de innovación aplicadas a la pyme. ISSN: 2254-4143
Ed.44 | Iss.12 | N.2 April - June 2023
278
(a) Resource recommendation based on graph embedding
(b) Resource recommendation for big data technology
Figure 3. Comparison of the effect of educational resources recommendation
From Figure 3(a), it can be seen that the average response time of the server is
4.1s when the graph-embedded resource recommendation system recommends
subject educational resources for users. In terms of the degree of preference for
educational resources, the average preference of recommended resources of the
graph-embedded resource recommendation system is around 0.56. The average
coverage rate of the tested subjects is 80.44% of all subjects, which indicates that the
accuracy of this educational resource recommendation is relatively average and
cannot meet the long-term development goal of online subject education.
From Figure 3(b), it can be seen that the server response time is short when Big
Data technology recommends subject educational resources for users of online
https://doi.org/10.17993/3ctecno.2023.v12n2e44.269-282
subject education systems, with the average response time being 1.77s and the
shortest being only 1.3s. In terms of the preference degree of educational resources,
the preference degree of resource recommendation of the online subject education
system with Big Data technology is above 0.86, and the coverage rate of the tested
subjects in all subjects is on average the average coverage rate of all subjects tested
was 90.48%. It can be seen that when applying big data technology to the resource
recommendation of the subject education system, big data technology can
automatically filter the resources that do not meet the requirements and add more
running conditions to the recommendation process, which makes the server response
time shorter and the user preference higher, thus achieving good recommendation of
subject education resources. In summary, this paper applies big data technology to
the online subject education system, which can shorten the response time of the
system server, improve the coverage of search subjects and provide more accurate
recommendation services for users based on fully satisfying user preferences.
4.2. EVALUATION RESULTS OF EDUCATION FITTING
INDICATORS
In this paper, two main aspects, teaching quality and student evaluation, are
considered in the evaluation of the fitted indicators for the effectiveness of online
subject education. In terms of teaching quality, influencing factors such as teaching
level and course content are mainly considered. In terms of student evaluation,
influencing factors such as system performance and course acceptance are mainly
considered. This experiment required the test students to make a comprehensive
evaluation of the online subject education system after the application of big data
technology on a 5-point scale, and the results are shown in Figure 4.
Figure 4. Evaluation results of education fitting indicators of the online education system
https://doi.org/10.17993/3ctecno.2023.v12n2e44.269-282
3C Tecnología. Glosas de innovación aplicadas a la pyme. ISSN: 2254-4143
Ed.44 | Iss.12 | N.2 April - June 2023
279
As can be seen from Figure 5, after the application of big data technology to the
online subject education system, students' overall evaluation of teaching quality
reached 4.81 points, of which teaching level rating reached 4.95 points, course
content reached 4.789 points, students' knowledge mastery reached 4.91 points,
lesson plan design efficiency reached 4.758 points, and teaching means optimization
efficiency reached 4.627 points The efficiency of lesson plan design was 4.758, and
the efficiency of teaching method optimization was 4.627. In terms of student
evaluation, students rated the system's resource search efficiency at 4.862, resource
integration at 4.758, overall evaluation of system performance at 4.842, and
educational satisfaction at 4.82, all achieving an excellent evaluation level of 4.75. It
shows that the application of big data technology to the online subject education
innovation system can ensure the high-quality education level of online subject
education to a large extent, and strongly stimulate the students' learning initiative and
interest.
4.3. REGRESSION ANALYSIS OF TEST SCORES
In this paper, two classes of the same major in college A were selected as the
experimental samples, and a semester-long educational experiment was conducted
on them. There were 117 students in the two classes, including 57 students in class B
as the experimental sample and 60 students in class C as the control sample, and the
experimental variables were the educational system application of big data
technology. The pre- and post-test scores of students in the two classes were
examined using regression test analysis, and the comparison results are shown in
Table 2.
Table 2. Achievement Test Results
As can be seen from Table 2, the performance test Sig values of the regression
coefficients for all samples, with a maximum of Sig = 0.002 < 0.05 and a minimum of
Sig = 0.001 < 0.05, reached a significant level of 0.05. This indicates that all reference
samples in this experiment were significantly different. Class B students reached 7.45
h of independent learning time after using big data technology for the online subject
education system, which is nearly 4.58 times higher relative to the control sample.
Models
C Variable B
Variables t Sig.
B Standard Error
Constants 49.368 1.469 37.625 1
Self-directed
Study Time
1.629 1.069 7.45 6.9415 1
Degree of
Exclusivity
3.655 1.1165 7.959 4.32 1
Interest 2.658 659 5.954 3.95 1
Achievements 78.6 0.79 95.36 3.214 2
https://doi.org/10.17993/3ctecno.2023.v12n2e44.269-282
3C Tecnología. Glosas de innovación aplicadas a la pyme. ISSN: 2254-4143
Ed.44 | Iss.12 | N.2 April - June 2023
280
As can be seen from Figure 5, after the application of big data technology to the
online subject education system, students' overall evaluation of teaching quality
reached 4.81 points, of which teaching level rating reached 4.95 points, course
content reached 4.789 points, students' knowledge mastery reached 4.91 points,
lesson plan design efficiency reached 4.758 points, and teaching means optimization
efficiency reached 4.627 points The efficiency of lesson plan design was 4.758, and
the efficiency of teaching method optimization was 4.627. In terms of student
evaluation, students rated the system's resource search efficiency at 4.862, resource
integration at 4.758, overall evaluation of system performance at 4.842, and
educational satisfaction at 4.82, all achieving an excellent evaluation level of 4.75. It
shows that the application of big data technology to the online subject education
innovation system can ensure the high-quality education level of online subject
education to a large extent, and strongly stimulate the students' learning initiative and
interest.
4.3. REGRESSION ANALYSIS OF TEST SCORES
In this paper, two classes of the same major in college A were selected as the
experimental samples, and a semester-long educational experiment was conducted
on them. There were 117 students in the two classes, including 57 students in class B
as the experimental sample and 60 students in class C as the control sample, and the
experimental variables were the educational system application of big data
technology. The pre- and post-test scores of students in the two classes were
examined using regression test analysis, and the comparison results are shown in
Table 2.
Table 2. Achievement Test Results
As can be seen from Table 2, the performance test Sig values of the regression
coefficients for all samples, with a maximum of Sig = 0.002 < 0.05 and a minimum of
Sig = 0.001 < 0.05, reached a significant level of 0.05. This indicates that all reference
samples in this experiment were significantly different. Class B students reached 7.45
h of independent learning time after using big data technology for the online subject
education system, which is nearly 4.58 times higher relative to the control sample.
Models
C Variable
B
Variables
t
Sig.
B
Standard Error
Constants
49.368
1.469
37.625
1
Self-directed
Study Time
1.629
1.069
7.45
6.9415
1
Degree of
Exclusivity
3.655
1.1165
7.959
4.32
1
Interest
2.658
659
5.954
3.95
1
Achievements
78.6
0.79
95.36
3.214
2
https://doi.org/10.17993/3ctecno.2023.v12n2e44.269-282
The degree of exclusivity and interest dimensions for the subject reached 7.959 and
5.954, respectively, a basic increase of 220%. Moreover, the mean test score
performance of students in Class B was 95.36, which was significantly higher than
that of Class C at 78.6, indicating positive changes in students' cognitive abilities in
the subject after participation in the experiment in Class B. The data from this test
indicates that big data technology can have a positive and significant impact on
student's performance, starting from the interesting and relevant knowledge of the
subject.
5. 5. CONCLUSION
Guided by big data technology, this paper optimizes the design of an innovative
application for online subject education in the context of big data technology, starting
from transforming data documents and designing an adaptive resource
recommendation process, and verifies the practical effect of the application in
simulation tests. The test conclusions are as follows:
1. In terms of educational resource recommendation, the average response time
of the resource recommendation server of big data technology is 1.77s, the
preference of the recommended resources is above 0.86, and the coverage
rate of the tested subjects is 90.48% of all subjects on average. It is known that
applying big data technology to the online subject education innovation system
can provide more accurate education resource recommendation services for
users.
2.
After using big data technology, the overall level of online subject education
reached more than 4.62 points at the level of teaching quality and more than
4.75 points at the level of student evaluation. This indicates that big data
technology has ensured the high-quality education level of online subject
education to a greater extent and stimulated students' learning initiatives.
3. The results of the achievement test showed that Class B, after using big data
technology for online subject education learning, had a mean performance
value of 95.36 in test scores and 7.45h of independent learning time, which
was nearly 4.58 times higher relative to Class C. And the degree of exclusivity
and interest dimensions of the subject matter increased by 220%. The test
data illustrates the significant performance-enhancing effect of big data
technology on online subject education.
REFERENCES
(1) Wang, Z., Wan, Y., & Liang, H. (2022). The Impact of Cloud Computing-Based
Big Data Platform on IE Education. Wireless Communications and Mobile
Computing, 2022(JAN), 1-13.
https://doi.org/10.17993/3ctecno.2023.v12n2e44.269-282
3C Tecnología. Glosas de innovación aplicadas a la pyme. ISSN: 2254-4143
Ed.44 | Iss.12 | N.2 April - June 2023
281
(2)
Data Analysis. Neurocomputing, 275.
(3)
Intelligent and Fuzzy Systems, 40(4), 1-12.
(4)
International Journal of Art & Design Education, 36(2), 188-199.
(5)
Implementation, and Outcomes. Nurse educator, 41(5), 270-273.
(6)
education. Journal of Intelligent and Fuzzy Systems, 40(7), 1-11.
(7)
16(1), 238.
(8) Baig, M. I., Shuib, L., & Yadegaridehkordi, E. (2021). A Model for Decision-
13995.
(9)
1-7.
(10)
Intelligent and Fuzzy Systems, 2021(3), 1-10.
(11)
40(1), 1-11.
(12)
HEALTH CARE, 30(3), 227-233.
(13) Muhammad, S., Norma, F., Li, D., et al. (2017). An Open Source-Based Real-
Sustainability, 9(11), 2139.
(14)
Journal of proteomics, 151, 12-23.
(15)
Neuroscience Bulletin, 34(3), 465-475.
(16)
Information Society, 15(3), 329-343.
(17)
Nonlinear Mathematical Equation. Applied Mathematics and Nonlinear Sciences.
https://doi.org/10.17993/3ctecno.2023.v12n2e44.269-282
3C Tecnología. Glosas de innovación aplicadas a la pyme. ISSN: 2254-4143
Ed.44 | Iss.12 | N.2 April - June 2023
282