Event attendance prediction in social networks / Xiaomei Zhang, Guohong Cao.

Unlimited

Authorized users

Can lend chapters, not whole ebooks

Event attendance prediction in social networks / Xiaomei Zhang, Guohong Cao.

9783030892623 (electronic bk.)
303089262X (electronic bk.)
9783030892616 (print)
3030892611

Cham, Switzerland : Springer, 2021.

English

1 online resource (viii, 54 pages) : illustrations (some color).

10.1007/978-3-030-89262-3 doi

QA76.9.D343

006.3/12

This volume focuses on predicting users' attendance at a future event at specific time and location based on their common interests. Event attendance prediction has attracted considerable attention because of its wide range of potential applications. By predicting event attendance, events that better fit users' interests can be recommended, and personalized location-based or topic-based services related to the events can be provided to users. Moreover, it can help event organizers estimating the event scale, identifying conflicts, and help manage resources. This book first surveys existing techniques on event attendance prediction and other related topics in event-based social networks. It then introduces a context-aware data mining approach to predict the event attendance by learning how users are likely to attend future events. Specifically, three sets of context-aware attributes are identified by analyzing users' past activities, including semantic, temporal, and spatial attributes. This book illustrates how these attributes can be applied for event attendance prediction by incorporating them into supervised learning models, and demonstrates their effectiveness through a real-world dataset collected from event-based social networks.

Includes bibliographical references.

Access limited to authorized users.

text file PDF

Online resource; title from PDF title page (SpringerLink, viewed January 7, 2022).

SpringerBriefs in statistics.

Print version: 9783030892616

Online Resources > Ebooks
All Resources