Collection

Special issue on spatiotemporal data management and analytics for recommender systems

Submission status
Closed

Recent advances in geo-positioning services and online social networks have fundamentally enhanced user experience in a variety of location-aware applications, including real-time route planning, online food ordering and delivery, location-aware crowdsourcing, and trip advisories. As such, one of a most popular and prominent research topics regarding location-aware applications is developing effective location-based recommender systems to enable users to acquire their preferred results in a timely manner over massive-scale spatiotemporal data.

In order to develop effective location-based recommender systems, the first step for data scientists is to get high-quality spatial data efficiently, which lay foundation for subsequent recommendations. Basically, spatiotemporal data is formulated by a single time-stamped spatial point or a sequence of time-stamped spatial points augmented with other information (e.g., textual description, attribute-value pairs). Some representative examples include Points of Interest (PoIs) and check-in data from online map services, user trajectories generated from wearable devices, and vehicle trajectories generated by online ride hailing applications. Thanks to the big data era and recent developments in spatiotemporal data management and recommender systems, research communities of recommender systems have been paying much attention towards developing effective recommender systems based on spatiotemporal data acquired from various location-aware applications. As such, users are able to be fed with a variety of recommendation results that may satisfy their location-based preferences. However, how to cope with spatiotemporal data streams of multisource and multimodality to maximize their usability to recommender systems while ensuring privacy and reliability is still an open challenge.

Analytics of multisource and multimodal spatiotemporal data enable us to extract timely information and knowledge that are useful to recommender systems, which may further improve the effectiveness, reliability, and efficiency of various recommender systems. This special issue aims to develop effective spatiotemporal data management techniques, novel spatiotemporal database frameworks, multisource streaming data processing techniques, privacy-preserving spatial data analytics, and location-aware query authentication to establish a variety of effective and efficient location-based recommender systems.

Topics of Interest:

Topics include, but are not limited to, the following:

-Spatiotemporal data preprocessing, including data cleaning, feature selection and extraction, data clustering, and map-matching

-Deep learning/reinforcement learning/federated learning on spatiotemporal data

-Spatiotemporal data mining

-Next-generation location-based recommender systems

-Multisource data stream analytics

-Effective processing of multimodal data

-Optimization of location-based recommender systems

-Location-based services and location-based social networks

-Privacy-preserving management of spatial data

-Location-aware query results authentications

Guest Editors:

Prof. Shuo Shang (jedi.shang@gmail.com), Professor, University of Electronic Science and Technology of China (Managing Guest Editor)

Prof. Xiangliang Zhang (xzhang33@nd.edu), Associate Professor, University of Notre Dame, USA

Prof. Panos Kalnis (panos.kalnis@kaust.edu.sa), Professor, King Abdullah University of Science and Technology, Saudi Arabia

Important dates

Submissions due: extended to 30 June, 2022

First round of reviews: 30 August, 2022

Author revision deadline: 30 October, 2022

Final decision notification: 30 December, 2022

Editors

  • Shuo Shang Shuo Shang , 

    Shuo Shang

    Prof. Shuo Shang (jedi.shang@gmail.com), Professor, University of Electronic Science and Technology of China

  • Prof. Xiangliang Zhang Prof. Xiangliang Zhang  &

    Prof. Xiangliang Zhang

    Prof. Xiangliang Zhang (xzhang33@nd.edu), Associate Professor, University of Notre Dame, USA

  • Prof. Panos Kalnis Prof. Panos Kalnis

    Prof. Panos Kalnis

    Prof. Panos Kalnis (panos.kalnis@kaust.edu.sa), Professor, King Abdullah University of Science and Technology, Saudi Arabia

Articles (18 in this collection)