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 Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

We address the problem of recommending relevant items to a user in order to"complete" a partial set of items already known. We consider the two scenariosof citation and subject label recommendation, which resemble differentsemantics of item co-occurrence: relatedness for co-citations and diversity forsubject labels. We assess the influence of the completeness of an already knownpartial item set on the recommender performance. We also investigate datasparsity through a pruning parameter and the influence of using additionalmetadata. As recommender models, we focus on different autoencoders, which areparticularly suited for reconstructing missing items in a set. We extendautoencoders to exploit a multi-modal input of text and structured data. Ourexperiments on six real-world datasets show that supplying the partial item setas input is helpful when item co-occurrence resembles relatedness, whilemetadata are effective when co-occurrence implies diversity. This outcome meansthat the semantics of item co-occurrence is an important factor. The simpleitem co-occurrence model is a strong baseline for citation recommendation.However, autoencoders have the advantage to enable exploiting additionalmetadata besides the partial item set as input and achieve comparableperformance. For the subject label recommendation task, the title is the mostimportant attribute. Adding more input modalities sometimes even harms theresult. In conclusion, it is crucial to consider the semantics of the itemco-occurrence for the choice of an appropriate recommendation model andcarefully decide which metadata to exploit.

Recommendations for Item Set Completion: On the Semantics of Item Co-Occurrence With Data Sparsity, Input Size, and Input Modalities