Event attendance classification in social media
- Submitting institution
-
University of Glasgow
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 11-05335
- Type
- D - Journal article
- DOI
-
10.1016/j.ipm.2018.11.001
- Title of journal
- Information Processing and Management
- Article number
- -
- First page
- 687
- Volume
- 56
- Issue
- 3
- ISSN
- 0306-4573
- Open access status
- Access exception
- Month of publication
- May
- Year of publication
- 2019
- URL
-
http://eprints.gla.ac.uk/172483/
- Supplementary information
-
-
- Request cross-referral to
- -
- Output has been delayed by COVID-19
- No
- COVID-19 affected output statement
- -
- Forensic science
- No
- Criminology
- No
- Interdisciplinary
- No
- Number of additional authors
-
5
- Research group(s)
-
-
- Citation count
- 6
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- ORIGINALITY: First work that identifies tweets related to large music events using tailored classifiers (including those built upon word embeddings) that account for the events’ dynamics (before/during/after the event) while being transferable between different events. RIGOUR: Reports extensive experiments using two major music festival datasets, and demonstrates a use-case of our models for organising transportation to the events. SIGNIFICANCE: Appeared in a top IR/IS journal; Extension of our ASONAM2017 paper (acceptance rate ~26%), which was cited by The Routledge Handbook of Festivals (2018). Our models allow organisers and service providers to better plan their safety/transport provisions.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -