English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

In existing recommendation systems, there exist the issues of &#x201C;cold start&#x201D; and &#x201C;excessively mature recommendation,&#x201D; which cause the recommendation systems to have weak effectiveness; thus, a trust-based recommendation model with a small recommendation probability for unknown items (RM-UI) is proposed for social networks. In the RM-UI scheme, the recommendation values of items are primarily derived from the probabilities calculated by a similar mature recommendation system during the initiation stage of the recommendation system. Thus, the &#x201C;cold start&#x201D; phenomenon can be overcome. When the recommendation system enters the period of maturation, the recommendation probabilities mainly adopt the recommendation values computed by the self-system. However, in the existing recommendation systems, there remains the problem of &#x201C;excessively mature recommendation,&#x201D; which causes the system to lose the opportunity to recommend more optimized items. Thus, in the RM-UI scheme, except for recommending items with higher recommendation probabilities, we recommend items with lower recommendation probabilities with a small probability to enable those items that can bring greater welfare to recommendation systems to be recommended. This breaks the weakness of a confined recommendation that exists in previous recommendation systems, and it enlarges the welfare of the system. After theoretical analysis, it has been proven that the RM-UI scheme can achieve greater welfare than the previous recommendation scheme and gain more vitality. Experiments based on real social network data are conducted to show the effectiveness and efficiency of the RM-UI scheme: in the initiation stage, the performance criteria of precision ratio, recall ratio, and F1-measure are improved by approximately 21.08%, 21.57%, and 21.32%, respectively, over the previous schemes, and in the mature stage, although the three indications are similar to those of the previous schemes, the improvement in the overall revenue of the system is 17.6%.

A Similarity Scenario-Based Recommendation Model With Small Disturbances for Unknown Items in Social Networks