<abstract xmlns="http://www.w3.org/1999/xhtml"><p>In this article, based on the collaborative deep learning (CDL) and convolutional matrix factorisation (ConvMF), the language model BERT is used to replace the traditional word vector construction method, and the bidirectional long–short time memory network Bi-LSTM is used to construct an improved collaborative filtering model BMF, which not only solves the phenomenon of ‘polysemy’, but also alleviates the problem of sparse scoring matrix data. Experiments show that the proposed model is effective and superior to CDL and ConvMF. The trained MSE value is 1.031, which is 9.7% lower than ConvMF.</p></abstract>

In this article, based on the collaborative deep learning (CDL) and convolutional matrix factorisation (ConvMF), the language model BERT is used to replace the traditional word vector construction method, and the bidirectional long–short time memory network Bi-LSTM is used to construct an improved collaborative filtering model BMF, which not only solves the phenomenon of ‘polysemy’, but also alleviates the problem of sparse scoring matrix data. Experiments show that the proposed model is effective and superior to CDL and ConvMF. The trained MSE value is 1.031, which is 9.7% lower than ConvMF.

Agricultural Product Recommendation Model based on BMF

Key Laboratory of China's Ethnic Languages and Information Technology of Ministry of Education Northwest

Applied Mathematics and Nonlinear Sciences

This work is licensed under the Creative Commons Attribution 4.0 International License.

{"article-title":"Agricultural Product Recommendation Model based on BMF"}

In this article, based on the collaborative deep learning (CDL) and convolutional matrix factorisation (ConvMF), the language model BERT is used to replace the...

Fields	Description
UserID	User id
ItemID	Commodity id
Rating	User's rating of commodities
Review	User comment text
ItemText	Item content text
Timestap	Time stamp

Environment	Description
Operating system	Centos7
Experimental language	Python 3.5.6
Deep Learning Framework	Tensorflow_gpu-1.3.0
GPU	NVIDIA Tesla
CUDA	8
cuDNN	6

Agricultural Product Recommendation Model based on BMF

Pubblicato online: 21 dic 2020

Pagine: 415 - 424

Ricevuto: 10 lug 2020

Accettato: 14 ago 2020

DOI: https://doi.org/10.2478/amns.2020.2.00060

Parole chiave
Recommendation system, BERT model, Bi-LSTM cost

© 2020 Fucheng Wan et al., published by Sciendo

This work is licensed under the Creative Commons Attribution 4.0 International License.

Fig. 1

Fig. 2

Fig. 3

Fig. 4

Fig. 5

Data set composition

Experimental environment settings

Experimental results

Model	MSE
PMF	1.473
CDL	1.324
ConvMF	1.142
Our	1.031

Agricultural Product Recommendation Model based on BMF

Pubblicato online: 21 dic 2020

Pagine: 415 - 424

Ricevuto: 10 lug 2020

Accettato: 14 ago 2020

DOI: https://doi.org/10.2478/amns.2020.2.00060

Parole chiaveRecommendation system, BERT model, Bi-LSTM cost

© 2020 Fucheng Wan et al., published by Sciendo

This work is licensed under the Creative Commons Attribution 4.0 International License.

Fig. 1

Fig. 2

Fig. 3

Fig. 4

Fig. 5

Data set composition

Experimental environment settings

Experimental results

Parole chiave
Recommendation system, BERT model, Bi-LSTM cost