Abstract | ||
---|---|---|
Popular events are well reflected on social media, where people share their feelings and discuss their experiences. In this paper, we investigate the novel problem of exploiting the content of non-geotagged posts on social media to infer the users’ attendance of large events in three temporal periods: before, during and after an event. We detail the features used to train event attendance classifiers and report on experiments conducted on data from two large music festivals in the UK, namely the VFestival and Creamfields events. Our classifiers attain very high accuracy with the highest result observed for the Creamfields festival ( ∼ 91% accuracy at classifying users that will participate in the event). We study the most informative features for the tasks addressed and the generalization of the learned models across different events. Finally, we discuss an illustrative application of the methodology in the field of transportation. |
Year | DOI | Venue |
---|---|---|
2019 | 10.1016/j.ipm.2018.11.001 | Information Processing & Management |
Keywords | Field | DocType |
Social media analysis,Event attendance prediction,Classification | Social media,Information retrieval,Computer science,Temporal periods,Attendance,Feeling | Journal |
Volume | Issue | ISSN |
56 | 3 | 0306-4573 |
Citations | PageRank | References |
1 | 0.41 | 32 |
Authors | ||
6 |
Name | Order | Citations | PageRank |
---|---|---|---|
vinicius monteiro de lira | 1 | 8 | 2.27 |
Craig Macdonald | 2 | 2588 | 178.50 |
Iadh Ounis | 3 | 3438 | 234.59 |
Raffaele Perego | 4 | 1471 | 108.91 |
Chiara Renso | 5 | 925 | 76.04 |
Valéria Cesário Times | 6 | 182 | 27.52 |