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 ( similar to 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.
Event attendance classification in social media
Perego R;Renso C;
2019
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 ( similar to 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.File | Dimensione | Formato | |
---|---|---|---|
prod_416216-doc_146662.pdf
accesso aperto
Descrizione: Event attendance classification in social media
Tipologia:
Versione Editoriale (PDF)
Dimensione
1.43 MB
Formato
Adobe PDF
|
1.43 MB | Adobe PDF | Visualizza/Apri |
prod_416216-doc_164468.pdf
non disponibili
Descrizione: Event attendance classification in social media
Tipologia:
Versione Editoriale (PDF)
Dimensione
1.64 MB
Formato
Adobe PDF
|
1.64 MB | Adobe PDF | Visualizza/Apri Richiedi una copia |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.