Analysis of the Coping Path of College Education Under Algorithm

Recommendation Technology

Meiyan Tian

Department of Teaching Support Service Center, Jilin Open University, Jilin, 130022, China

Keywords: Algorithmic Recommendation Technology, Recommendation Theory, Higher Education Paths, Education.

Abstract: This study first conducted an in-depth analysis of the characteristics of virtual space, and then explored the

importance of algorithm recommendation technology in virtual space path analysis. By comparing and

analyzing different algorithm recommendation techniques, this study proposes a deep learning based

algorithm recommendation model that can better adapt to user needs and improve recommendation accuracy.

Finally, this study validated the effectiveness of the proposed algorithm recommendation model through

experiments. The experimental results showed that the model can significantly improve the information

retrieval efficiency of users in virtual space, thereby improving the user experience..

1 INTRODUCTION

The personalized recommendation mechanism is one

of the important contents of the coping path of college

education, which is of great significance to the

improvement of the teaching quality of colleges and

universities. However, in the process of teaching

quality evaluation, there is a lack of pertinence in the

teaching quality evaluation program (Agarwal,

2023), which brings certain reputation losses to

college education and teaching(Atik, Sari, et al.

2023). Some scholars believe that the application of

algorithm recommendation technology to the analysis

of the coping path of college education can

effectively analyze the teaching quality evaluation

scheme and provide corresponding support for

teaching quality evaluation (Cokley, Garba, et al.

2023). On this basis, this paper proposes an algorithm

recommendation technique to optimize the teaching

quality evaluation scheme and verify the

effectiveness of the model(Copeland, Kamis, et al.

2023).

(1) Intelligent recommendation algorithm is

widely used in the field of college education, which

can be optimized from the following aspects

(Oliveira, Borges, et al. 2023):

1) Individualized tutoring. Traditional teaching

mode is often one size fits all, which is difficult to

meet the learning needs of each student, and easily

leads to students' low learning enthusiasm and poor

learning effect (Eno, Armstrong, et al. 2023). The

intelligent recommendation algorithm can customize

personalized learning programs and counseling

methods by analyzing students' data, and improve

students' learning efficiency and interest (Fang, and

Zhu, 2023). For example, based on students' study

habits and achievements, we recommend teaching

resources suitable for students and personalized

counseling programs for students(Findlay, Bearrick,

et al. 2023).

Intelligent recommendation algorithm can predict

students' learning needs according to students'

learning history and preferences, thus providing

students with personalized learning resources and

recommendations. For example, in the field of college

education, intelligent recommendation algorithm can

recommend courses ( Gruda, McCleskey, et al.

2023), learning resources, academic papers, scientific

research projects, etc. that meet students' needs

according to their learning history and hobbies, thus

improving students' learning efficiency and learning

achievements (Gu, and Mao, 2023).

2) Subject resource recommendation (Hurstak, et

al. 2023). In the process of learning in colleges and

universities, students need to master the knowledge

taught by teachers in class, and also need to carry out

a lot of autonomous learning. Intelligent

recommendation algorithm can recommend subject

resources that meet students' learning needs (Kim,

Woo, et al. 2023), such as online courses, popular

science videos, etc., according to students' learning

Tian, M.

Analysis of the Coping Path of College Education Under Algorithm Recommendation Technology.

DOI: 10.5220/0013544400004664

Paper published under CC license (CC BY-NC-ND 4.0)

In Proceedings of the 3rd International Conference on Futuristic Technology (INCOFT 2025) - Volume 1, pages 405-410

ISBN: 978-989-758-763-4

405

situation and interests, so as to improve students'

learning enthusiasm and hobbies (Lehrer-Stein and

Berger, 2023).

The application of intelligent recommendation

algorithm can promote the innovation and

development of higher education. Intelligent

recommendation algorithm can provide effective

feedback and teaching suggestions for teachers by

analyzing students' behavior data (Lilo, Mashhadany,

et al. 2023), thus promoting teachers' teaching

innovation and improvement. Through the

application of intelligent recommendation algorithm,

the teaching cost of colleges and universities can be

reduced. Intelligent recommendation algorithm can

automatically provide students with learning

resources and recommendations (Li, Wang, et al.

2023), and reduce the production and management

costs of teaching content and recommendation

resources.

3) The optimization of curriculum content is the

key to improve teaching quality and adaptability (Li,

Hu, et al. 2023). Through intelligent

recommendation algorithm to analyze various data

such as course content and student feedback, the

course content is optimized and adjusted to improve

the teaching quality and adaptability of the course.

For example, according to students' learning situation

and feedback, the difficulty, content and teaching

methods of the course are adjusted (Liu, et al. 2023).

4) Intelligent enrollment. Intelligent

recommendation algorithm can provide personalized

enrollment consultation and service for students by

analyzing students' information and academic

achievements, and improve enrollment efficiency and

enrollment quality. For example, according to

students' interests and learning situation, recommend

suitable majors and disciplines to students, as well as

enrollment consultation and services for

students(Poll-Hunter, et al. 2023). Intelligent

recommendation algorithm can realize personalized

education, and provide personalized recommendation

and education for students according to their study

habits, hobbies and learning needs. Individualized

education can better meet students' learning needs

and hobbies, and improve students' learning

enthusiasm and learning effect.

(2) The research of intelligent algorithm in college

education has always been a hot topic. In recent years,

there are many research results and application cases

about intelligent algorithm in college education. The

following are some research overviews:

1) Teaching recommendation system. Teaching

recommendation system is one of the common

applications of intelligent algorithms in higher

education. This recommendation system can

recommend personalized courses, teaching materials

and learning resources for students based on the

analysis of students' personal information, learning

history, interest and other data. For example, MITx,

an online education platform, has been developed by

Massachusetts Institute of Technology in the United

States, which adopts a large number of intelligent

algorithms and has achieved remarkable results in

recommending courses and learning resources for

students.

2) Student behavior analysis. Student behavior

analysis is another important application of intelligent

algorithm in higher education. By analyzing students'

clicking, browsing, searching and other behavior

data, we can deeply understand students' learning

habits and needs, and provide teachers with more

effective teaching feedback and suggestions, so as to

realize personalized education. For example, the

University of Toronto uses behavior analysis

technology to track and analyze students' learning

behavior and provide students with personalized

teaching recommendations and suggestions.

3) Intelligent education platform. Intelligent

education platform is another form of applying

intelligent algorithms to higher education. This

platform integrates a variety of intelligent algorithms,

which can provide teachers and students with all-

round educational services and learning resources.

For example, Tsinghua University has developed an

intelligent education platform called "Tsinghua

School", which combines a variety of intelligent

algorithms and provides students with massive

learning resources and teaching feedback.

In a word, intelligent algorithms are widely used

in college education, from personalized

recommendation to student behavior analysis,

intelligent education platform and so on. In the future,

with the continuous development and innovation of

intelligent algorithm technology, its application in

higher education will continue to increase and

improve.

2 RELATED CONCEPTS

2.1 Mathematical description of

algorithmic recommendation

techniques

The algorithm recommendation technology uses the

recommendation theory to optimize the teaching

quality evaluation scheme, and according to the

INCOFT 2025 - International Conference on Futuristic Technology

406

indicators in the teaching quality evaluation, finds the

unqualified values in the coping path of college

education, and evaluates the teaching quality The

plan is integrated to finally judge the feasibility of the

coping path of college education. Algorithm

recommendation technology combines the

advantages of recommendation theory, and uses the

coping path of college education to quantify, which

can improve the application effect of personalized

recommendation mechanism for teaching quality

evaluation.

Hypothesis I. The requirements for teaching

quality evaluation are, the teaching quality evaluation

plan is,

v the satisfaction of the teaching quality

evaluation program is, and

v the teaching quality

evaluation

is The scheme judgment function is

S shown in Equation (1).

⋅

(1)

2.2 Selection of personalized

recommendation mechanism

scheme

Hypothesis II The response path function of college

education is and the

weight coefficient is , then, the

teaching quality evaluation requires the

unqualified college education response path as shown

in Equation (2).

()

DXY



(2)

2.3 Improvement of teaching quality

evaluation programs

Before carrying out the algorithm recommendation

technology, it is necessary to conduct a multi-

dimensional analysis of the teaching quality

evaluation scheme, map the teaching quality

evaluation requirements to the university education

response path library, and eliminate the unqualified

teaching quality evaluation scheme. First, college

education should conduct a comprehensive analysis

of the path, and set the threshold and index weight of

the teaching quality evaluation scheme to ensure the

accuracy of the algorithm recommendation

technology. The response path of college education is

to systematically test the teaching quality evaluation

scheme, which needs to be innovative. If the coping

path of higher education is in a non-normal

distribution, its teaching quality evaluation scheme

will be affected, reducing the accuracy of the overall

teaching quality evaluation. In order to improve the

accuracy of algorithm recommendation technology

and improve the level of teaching quality evaluation,

the teaching quality evaluation scheme should be

selected, and the specific scheme selection is shown

in Figure 1.

Personalized

recommendation mechanism

Communication

methods

The Definition Model of

Audience Microdifferentiation

The diversified structural

form of the subject

Figure 1: Selection results of personalized recommendation

mechanism scheme

The survey teaching quality evaluation scheme

shows that the personalized recommendation

mechanism scheme presents a multi-dimensional

distribution, which is in line with the objective facts.

The coping path of college education is not

directional, indicating that the personalized

recommendation mechanism scheme has strong

randomness, so it is regarded as a high analytical

study. The coping path of college education meets

the normal requirements, mainly recommending the

theory to adjust the coping path of college education,

eliminating duplicate and irrelevant schemes, and

supplementing the default scheme, so that the

dynamic correlation of the entire teaching quality

evaluation scheme is strong.

3 OPTIMIZATION STRATEGIES

FOR COPING PATHS IN

COLLEGE EDUCATION

The algorithm recommendation technology adopts

the random optimization strategy for the college

education response path, and adjusts the education

recommendation parameters to realize the scheme

optimization of the college education response path.

The algorithm recommendation technology divides

the coping paths of college education into different

Analysis of the Coping Path of College Education Under Algorithm Recommendation Technology

407

teaching quality evaluation levels, and randomly

selects different schemes. In the iterative process, the

teaching quality evaluation scheme of different

teaching quality evaluation levels is optimized. After

the optimization is completed, the teaching quality

evaluation level of different programs is compared,

and the best university education response path is

recorded.

4 PRACTICAL CASES OF

UNIVERSITY EDUCATION

COPING PATHS

4.1 Introduction to the evaluation of

teaching quality

In order to facilitate the evaluation of teaching

quality, this paper takes the response path of college

education under complex conditions as the research

object, with 12 paths and a test time of 12 h, and the

specific response path of college education The

teaching quality assessment scheme is shown in Table

Table 1: Requirements for the evaluation of teaching

quality in colleges and universities

Scope of

application

Grade Diversified

needs

Personalized

Recommendation

mechanis

Freshman I 38.5600 36.1882

II 39.5805 38.3143

Sophomore I 40.7154 37.9205

II 36.7660 36.8367

Junior I 38.5587 38.2383

II 39.5789 38.2286

Senior I 37.4382 38.3044

II 37.6569 38.8385

The teaching quality assessment process in Table

1 is shown in Figure 2.

Compared with the traditional classroom teaching

method, the teaching quality evaluation scheme of

algorithm recommendation technology is closer to the

actual teaching quality evaluation requirements. In

terms of the rationality and fluctuation range of the

coping path of college education, the algorithm

recommendation technology far exceeds the

traditional classroom teaching method. Through the

change of teaching quality evaluation scheme in

Figure 2, it can be seen that the algorithm

The Response Path of Higher Education

Reflection on the Survival

State of the Internet

Enhancing

Students' New

Media Literacy

Master the characteristics of

algorithm recommendation

Figure 2: The exploration process of the coping path of

college education

recommendation technology has better stability and

faster judgment speed. Therefore, the teaching quality

evaluation scheme of algorithm recommendation

technology and the teaching quality evaluation

stability of personalized recommendation mechanism

scheme are better.

4.2 The response path of college

education

The teaching quality evaluation scheme of the

university education response path includes

unstructured information, semi-structured

information and structural information. After the pre-

selection of algorithm recommendation technology, a

preliminary teaching quality evaluation scheme for

the coping path of college education is obtained, and

the coping path of college education is obtained

Analyze the feasibility of teaching quality evaluation

programs. In order to more accurately verify the

innovative effect of college education response path,

the university education response path with different

teaching quality evaluation levels is selected, and the

teaching quality evaluation scheme is shown in Table

2 shown.

Table 2: The overall picture of the personalized

recommendation mechanism scheme

Cate

Personalize Precision

Freshman 69.0236 55.6782

Sophomore 72.4857 55.7209

Junio

73.4571 57.5391

Senio

72.0903 56.8535

INCOFT 2025 - International Conference on Futuristic Technology

408

4.3 Personalized recommendation

mechanism and stability of teaching

quality evaluation

In order to verify the accuracy of the algorithm

recommendation technique, the teaching quality

evaluation scheme is compared with the traditional

classroom teaching method, and the teaching quality

evaluation scheme is shown in Figure 3.

Figure 3: Personalized recommendation mechanism for

different algorithms

It can be seen from Figure 3 that the personalized

recommendation mechanism of algorithm

recommendation technology is higher than that of

traditional classroom teaching methods, but the error

rate is lower, indicating that the teaching quality

evaluation of algorithm recommendation technology

is relatively stable. The teaching quality evaluation of

traditional classroom teaching methods is uneven.

The average teaching quality evaluation scheme of

the above algorithm is shown in Table 3.

Table 3: Comparison of teaching quality evaluation

accuracy of different methods

Algorithm Recommende

d frequency

Degree

match

Relativ

e error

Algorithmic

recommendatio

n techni

ues

92.4589 91.312

91.8882

Traditional

classroom

teaching

72.4857 73.457

71.5882

By Table 3, it can be seen that the traditional

classroom teaching method has shortcomings in the

stability of the personalized recommendation

mechanism in the response path of college education,

and the response path of college education has

changed significantly, and the error rate is high. The

personalized recommendation mechanism of the

general results of the algorithm recommendation

technology is higher than the traditional classroom

teaching method. At the same time, the

recommendation frequency of the algorithm

recommendation technology is greater than 90%, and

the accuracy has not changed significantly. In order

to further verify the superiority of the algorithmic

recommendation technique. In order to further verify

the effectiveness of the proposed method, the

algorithm recommendation technique is generally

analyzed by different methods, Figure 4 shown.

Figure 4: Personalized recommendation mechanism for

teaching quality evaluation of algorithm recommendation

technology

By Figure 4, it can be seen that the personalized

recommendation mechanism of algorithm

recommendation technology is significantly better

than the traditional classroom teaching method, and

the reason is that the algorithm recommendation

technology increases the adjustment coefficient of the

coping path of college education. And set the

threshold of education recommendation, and

eliminate the teaching quality evaluation scheme that

does not meet the requirements.

5 CONCLUSIONS

Aiming at the problem that the personalized

recommendation mechanism of college education

coping path is not ideal, this paper proposes an

algorithmic recommendation technology, and

combines recommendation theory to optimize the

coping path of college education. At the same time,

the innovation of teaching quality evaluation and

threshold innovation is analyzed in depth, and the

collection of education recommendations is

constructed. The research shows that the algorithm

recommendation technology can improve the

747270

60.0

58.5

57.0

55.5

54.0

60.058.557.055.554.0

Traditional classroom teaching methods

Algorithm recommendation technology

2018161412108642

180

160

140

120

100

sample data(piece)

Recommended frequency(%)

Traditional classroom teaching methods

Algorithm recomm endation technology

Analysis of the Coping Path of College Education Under Algorithm Recommendation Technology

409

accuracy and stability of the coping path of college

education, and can generalize the coping path of

college education Evaluation of teaching quality.

However, in the process of applying algorithm

recommendation technology, too much attention is

paid to the analysis of teaching quality evaluation,

resulting in irrationality in the selection of teaching

quality evaluation indicators.

REFERENCES

S. M. Agarwal, "Go-Brown, Go-Green and smart initiatives

implemented by the University of Delhi for

environmental sustainability towards futuristic smart

universities: Observational study," Heliyon, Article vol.

9, no. 3, Mar 2023.

A. D. Atik, H. I. Sari, and Y. Dogan, "The effects of

closeness to nature, connectedness to nature and eco-

friendly behaviours on environmental identity: a study

of public university students in South-eastern Turkey,"

Australian Journal of Environmental Education, Article

vol. 39, no. 1, pp. 80-94, Mar 2023.

K. Cokley, R. Garba, K. Harris, N. Krueger, M. Bailey, and

S. Hall, "Student-Faculty Interactions, University

Environment, and Academic Attitudes Among Black

College Students: The Role of School Racial

Composition," Journal of Higher Education, Article

vol. 94, no. 4, pp. 444-472, Jun 7 2023.

M. Copeland, C. Kamis, and G. Varela, "Pathways from

peers to mental health: Adolescent networks, role

attainment, and adult depressive symptoms," Social

Science & Medicine, Article vol. 324, May 2023.

H. d. V. de Oliveira, M. K. Borges, and C. Andion,

"Training administrators: analysis of the training path

in the light of course pedagogical projects," Revista De

Gestao E Secretariado-Gesec, Article vol. 14, no. 3, pp.

3859-3873, 2023 2023.

J. P. Eno, E. A. Armstrong, S. R. Levitsky, and K. Kennon,

""How is a Student to Know Who They Can Talk To?":

University Website Communication about Sexual

Assault in the Context of Compelled Disclosure,"

Review of Higher Education, Article vol. 46, no. 3, pp.

373-406, 2023 2023.

M. Fang and Z. Zhu, "An Empirical Study of the

Influencing Factors of University-Enterprise Authentic

Cooperation on Cross-Border E-Commerce

Employment: The Case of Zhejiang," Sustainability,

Article vol. 15, no. 8, Apr 2023.

B. L. Findlay, E. N. Bearrick, C. F. Granberg, and K. Koo,

"Path to Parity: Trends in Female Representation

Among Physicians, Trainees, and Applicants in

Urology and Surgical Specialties," Urology, vol. 172,

pp. 228-233, 2023-02 2023.

D. Gruda, J. McCleskey, and I. Khoury, "Cause we are

living in a Machiavellian world, and I am a

Machiavellian major: Machiavellianism and academic

major choice," Personality and Individual Differences,

Article vol. 205, Apr 2023.

X. Gu and E. Mao, "The impacts of academic stress on

college students' problematic smartphone use and

Internet gaming disorder under the background of

neijuan: Hierarchical regressions with mediational

analysis on escape and coping motives," Frontiers in

Psychiatry, Article vol. 13, Jan 5 2023.

E. E. Hurstak et al., "The mediating effect of health literacy

on COVID-19 vaccine confidence among a diverse

sample of urban adults in Boston and Chicago,"

Vaccine, Article vol. 41, no. 15, pp. 2562-2571, Apr 6

2023.

D. Kim, Y. Woo, J. Song, and S. Son, "The relationship

between faculty interactions, sense of belonging, and

academic stress: a comparative study of the post-

COVID-19 college life of Korean and international

graduate students in South Korea," Frontiers in

Psychiatry, Article vol. 14, May 10 2023.

J. Lehrer-Stein and J. Berger, "A path towards true

inclusion: Disabled students and higher education in

America," International Journal of Discrimination and

the Law, Article vol. 23, no. 1-2, pp. 126-143, Jun 2023.

A. Leibing, F. Peter, S. Waights, and C. K. Spiess, "Gender

gaps in early wage expectations," Economics of

Education Review, Article vol. 94, Jun 2023.

H. Li, "The construction and practice path of safety

education mechanism in colleges and universities

integrating the psychological characteristics of students

in the new era," Frontiers in Psychology, Article vol.

13, Jan 6 2023.

S. Li, Y. Hu, L. Wang, and E. Xia, "Involvement, leadership

and social practice to the development of postgraduate

attributes: evidence from extracurricular education with

Chinese characteristics," Frontiers in Psychology,

Article vol. 14, May 30 2023.

X. Liu et al., "Medical Education Systems in China:

Development, Status, and Evaluation," Academic

Medicine, Article vol. 98, no. 1, pp. 43-49, Jan 2023.

N. I. I. Poll-Hunter et al., "Increasing the Representation of

Black Men in Medicine by Addressing Systems

Factors," Academic Medicine, Article vol. 98, no. 3, pp.

304-312, Mar 2023.

INCOFT 2025 - International Conference on Futuristic Technology

410