DEvIR: Data Collection and Analysis for the Recommendation of Events and Itineraries

Date
2019-01-08
Authors
Nurbakova, Diana
Laporte, Léa
Calabretto, Sylvie
Gensel, Jerome
Journal Title
Journal ISSN
Volume Title
Publisher
Abstract
Distributed events such as multi-day festivals and conventions attract thousands of attendees. Their programs are usually very dense, which makes it difficult for users to select activities to perform. Recent works have proposed event and itinerary recommendation algorithms to solve this problem. Although several datasets have been made available for the evaluation of event recommendation algorithms, they do not suit well for the case of distributed events or itinerary recommendation. Based on the study of available online resources, we define dataset attributes required to perform event and itinerary recommendations in the context of distributed events, and discuss the compliance of existing datasets to these requirements. Revealing the lack of publicly available datasets with desired features, we describe a data collection process to acquire the publicly available data from a major comic book convention website. We present the characteristics of the collected data and discuss its usability for evaluating recommendation algorithms.
Description
Keywords
Data Analytics, Data Mining and Machine Learning for Social Media, Digital and Social Media, data collection, dataset, distributed events, event recommendation, itinerary recommendation
Citation
Rights
Access Rights
Email libraryada-l@lists.hawaii.edu if you need this content in ADA-compliant format.