A social network security user recommendation algorithm based on community user emotions Online publication date: Tue, 12-Mar-2024
by Huajin Liu; Chunhua Ju; Houyuan Zhang
International Journal of Security and Networks (IJSN), Vol. 19, No. 1, 2024
Abstract: Social networks play a vital role in people's lives and work, but have problems with sparse data and cold start. This study establishes a social network model and innovatively improves the classic user interest point recommendation algorithm based on community information and user emotion. A sequential learning ranking algorithm is designed to simulate user preferences from a sequence of recommended objects and convert user ratings into ranking scores, combined with a network security dictionary, Node2vec method, and hot coding to capture network security vocabulary. This study also uses the heuristic firefly optimisation algorithm to solve the problem and confirms that community CU-SNR has good experimental results. The improved LDA algorithm is used to adjust the social media emotion data, and three real social network data sets verify the algorithm's performance. Numerical experiment results show that the algorithm simulation has a certain effect when facing social networks.
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Security and Networks (IJSN):
Login with your Inderscience username and password:
Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.
If you still need assistance, please email subs@inderscience.com