Title: Optimisation driven generative adversarial network for course recommendation in e-learning

Authors: Jobin Varghese P.; R. Vijayakumar

Addresses: KE (Kuriakose Elias) College Mannanam, Kottayam, Kerala, India ' Jyothi Engineering College, Vettikattiri, Cheruthuruthi, Kerala, India

Abstract: This research created a mechanism for course recommendation based on collaborative filtering to categorise the attitudes. Here, the positively reviewed courses are identified using sentiment categorisation using the recommended Shuffled Shepherd Bat Optimisation-based Generative Adversarial Network (SSBO-based GAN). The input data is fed into a matrix creation process where the data-driven matrix form is created. For course grouping, the Enhanced Fuzzy C-means Method (FCM) is used. The course matching is then completed using Canberra distance and holoentropy. The GAN classifier then does the sentiment categorisation. The Bat Algorithm (BA) and the Shuffled Shepherd Optimisation Algorithm (SSOA) are combined to create the Shuffled Shepherd Bat Optimisation (SSBO), which is used to train the GAN. Positive course reviews are gleaned from categorised attitudes in this case, aiding in course selection. The suggested SSBO-based GAN displayed improved performance with an F-measure of 96.6%, a recall of 97.1% and a precision of 96.1%.

Keywords: collaborative filtering; enhanced fuzzy C-means algorithm; course recommendation; Canberra distance; generative adversarial network.

DOI: 10.1504/IJWMC.2023.134668

International Journal of Wireless and Mobile Computing, 2023 Vol.25 No.3, pp.235 - 249

Received: 05 Mar 2022
Received in revised form: 31 Oct 2022
Accepted: 16 Nov 2022
Published online: 03 Nov 2023 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article