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

Recent years have witnessed the increasing popularity of Location-basedSocial Network (LBSN) services, which provides unparalleled opportunities tobuild personalized Point-of-Interest (POI) recommender systems. Existing POIrecommendation and location prediction tasks utilize past information forfuture recommendation or prediction from a single direction perspective, whilethe missing POI category identification task needs to utilize the check-ininformation both before and after the missing category. Therefore, along-standing challenge is how to effectively identify the missing POIcategories at any time in the real-world check-in data of mobile users. To thisend, in this paper, we propose a novel neural network approach to identify themissing POI categories by integrating both bi-directional global non-personaltransition patterns and personal preferences of users. Specifically, wedelicately design an attention matching cell to model how well the check-incategory information matches their non-personal transition patterns andpersonal preferences. Finally, we evaluate our model on two real-worlddatasets, which clearly validate its effectiveness compared with thestate-of-the-art baselines. Furthermore, our model can be naturally extended toaddress next POI category recommendation and prediction tasks with competitiveperformance.

Exploiting Bi-directional Global Transition Patterns and Personal Preferences for Missing POI Category Identification