Learning platform for university innovation and entrepreneurship projects based on the joint gated graph attention group recommendation algorithm

Abstract

In order to solve the problem of low competitiveness of college students in the job market and high unemployment rate, a new joint gate graph neural network recommendation algorithm is proposed. In the experimental results, the proposed joint gated graph neural network recommendation algorithm shows excellent performance on multiple datasets. In four datasets of different sizes, the average recall rate of the algorithm is as high as 85%, and the average F1 value is 0.87, showing the ability to significantly outperform the traditional recommendation algorithm. In addition, when the size of the dataset increases, the performance of the algorithm also improves correspondingly, and the average values of NDCG and HR reach 0.59 and 0.55, respectively, indicating that the algorithm has superior performance in personalized recommendation. The experiment also shows that the optimal embedding dimension is 85, and the convergence performance of the algorithm stops changing when the number of iterations reaches 10. This paper proposes a new recommendation algorithm, which combines long- and short-term memory mechanism and two-layer attention grouping to solve the shortcomings of traditional recommendation systems in processing large amounts of user data and interest matching. The practical impact of the proposed approach is to more effectively match learners’ interests with course content, improve learning efficiency, and encourage students to improve their social skills and innovative thinking on their own, thus enhancing their employability competitiveness.

Keywords

gated attention group learning platforms innovation and entrepreneurship recommendation algorithms project courses

Get full access to this article

View all access options for this article.

References

Huang

Jia

Zuo

. Improved collaborative filtering personalized recommendation algorithm based on k-means clustering and weighted similarity on the reduced item space. Math Model Control 2023; 3(1): 39–49.

Jain

Mahara

Sharma

. Performance evaluation of time-based recommendation system in collaborative filtering technique. Procedia Comput Sci 2023; 218(5): 1834–1844.

Widayanti

Chakim

MHR

Lukita

, et al. Improving recommender systems using hybrid techniques of collaborative filtering and content-based filtering. J Appl Data Sci 2023; 4(3): 289–302.

Gao

Chen

, et al. ICS-GNN: lightweight interactive community search via graph neural network. Proc VLDB Endow 2021; 14(6): 1006–1018.

Chen

Zhang

You

, et al. A GNN-based supervised learning framework for resource allocation in wireless IoT networks. IEEE Internet Things J 2021; 9(3): 1712–1724.

Zhang

Cui

Pei

, et al. Eigen-gnn: a graph structure preserving plug-in for gnns. IEEE Trans Knowl Data Eng 2021; 35(3): 2544.

Wang

Huang

Chandak

, et al. Extending the nested model for user-centric XAI: a design study on GNN-based drug repurposing. IEEE Trans Vis Comput Graph 2022; 29(1): 1266–1276.

Khanal

Prasad

Alsadoon

, et al. A systematic review: machine learning based recommendation systems for e-learning. Educ Inf Technol 2020; 25(4): 2635–2664.

Zhang

Gao

, et al. Personalized graph neural networks with attention mechanism for session-aware recommendation. IEEE Trans Knowl Data Eng 2020; 34(8): 3946–3957.

10.

. Aspect-based fashion recommendation with attention mechanism. IEEE Access 2020; 8: 141814–141823.

11.

Huang

Zhu

, et al. An efficient group recommendation model with multiattention-based neural networks. IEEE Transact Neural Networks Learn Syst 2020; 31(11): 4461–4474.

12.

Guo

Wang

. A deep graph neural network-based mechanism for social recommendations. IEEE Trans Ind Inf 2020; 17(4): 2776–2783.

13.

Wang

Xiang

, et al. Attentive sequential model based on graph neural network for next poi recommendation. World Wide Web 2021; 24(6): 2161–2184.

14.

Hebbi

Mamatha

. Comprehensive dataset building and recognition of isolated handwritten Kannada characters using machine learning models. Artif Intell Appl 2023; 1(3): 179–190.

15.

Wang

Yen

, et al. DeepGD: a deep learning framework for graph drawing using GNN. IEEE Comput Graph Appl 2021; 41(5): 32–44.

16.

Bhosle

Musande

. Evaluation of deep learning CNN model for recognition of devanagari digit. Artif Intell Appl 2023; 1(2): 114–118.

17.

Alrahis

Sengupta

Knechtel

, et al. GNN-RE: graph neural networks for reverse engineering of gate-level netlists. IEEE Trans Comput Aided Des Integrated Circ Syst 2021; 41(8): 2435–2448.

18.

Shao

, et al. Distributed graph neural network training: a survey. ACM Comput Surv 2024; 56(8): 1–39.

19.

Shi

Wurster

, et al. Gnn-surrogate: a hierarchical and adaptive graph neural network for parameter space exploration of unstructured-mesh ocean simulations. IEEE Trans Vis Comput Graph 2022; 28(6): 2301–2313.

20.

Guo

Wen

Huang

, et al. A collaborative filtering recommendation algorithm based on DeepWalk and self-attention. Int J Comput Sci Eng 2023; 26(3): 296–304.

21.

Liu

Pei

Wang

, et al. An attention-based category-aware GRU model for the next POI recommendation. Int J Intell Syst 2021; 36(7): 3174–3189.

22.

. Development strategy of online English teaching based on attention mechanism and recurrent neural network recommendation method. Int J Data Min Bioinf 2024; 28(2): 140–155.

23.

Yannam

Kumar

Babu

, et al. Improving group recommendation using deep collaborative filtering approach. Int J Inf Technol 2023; 15(3): 1489–1497.

24.

Paun

Moshfeghi

Ntarmos

. White box: on the prediction of collaborative filtering recommendation systems’ performance. ACM Trans Internet Technol 2023; 23(1): 1–29.

25.

Alhijawi

Obeid

Awajan

, et al. New hybrid semantic-based collaborative filtering recommender systems. Int J Inf Technol 2022; 14(7): 3449–3455.

26.

Kataria

Batra

. Co-clustering neighborhood—based collaborative filtering framework using formal concept analysis. Int J Inf Technol 2022; 14(4): 1725–1731.