eCoaching platforms have become powerful tools to support users in their day-to-day physical routines. More and more research works show that motivational factors are strictly linked with the user inclination to share her fitness achievements on social media platforms. In this paper, we tackle the problem of analyzing and modeling users' contextual information and real-time training data by exploiting state-of-the-art classification algorithms, to predict if a user will share her current running workout on Facebook. By analyzing user's performance, collected by means of an eCoaching platform for runners, and crossing them with contextual information such as the weather, we are able to predict with a high accuracy if the user will post or not on Facebook. Given the positive impact that social media posts have in these scenarios, understanding what are the conditions that lead a user to post or not, can turn the output of the classification process into actionable knowledge. This knowledge can be exploited inside eCoaching platforms to model user behavior in broader and deeper ways, to develop novel forms of intervention and favor users' motivation on the long term.

Modeling real-time data and contextual information from workouts in eCoaching platforms to predict users’ sharing behavior on Facebook

Boratto, Ludovico;Carta, Salvatore;Ibba, Federico;Mulas, Fabrizio;Pilloni, Paolo
2020

Abstract

eCoaching platforms have become powerful tools to support users in their day-to-day physical routines. More and more research works show that motivational factors are strictly linked with the user inclination to share her fitness achievements on social media platforms. In this paper, we tackle the problem of analyzing and modeling users' contextual information and real-time training data by exploiting state-of-the-art classification algorithms, to predict if a user will share her current running workout on Facebook. By analyzing user's performance, collected by means of an eCoaching platform for runners, and crossing them with contextual information such as the weather, we are able to predict with a high accuracy if the user will post or not on Facebook. Given the positive impact that social media posts have in these scenarios, understanding what are the conditions that lead a user to post or not, can turn the output of the classification process into actionable knowledge. This knowledge can be exploited inside eCoaching platforms to model user behavior in broader and deeper ways, to develop novel forms of intervention and favor users' motivation on the long term.
Behavior modeling; Behavior prediction; eCoaching; Healthy lifestyle; Motivation; Personalized persuasive technologies; Personalized recommendations; Social networks; 3304; Human-Computer Interaction; Computer Science Applications1707 Computer Vision and Pattern Recognition
File in questo prodotto:
File Dimensione Formato  
manuscript.pdf

Solo gestori archivio

Descrizione: articolo principale
Tipologia: versione pre-print
Dimensione 535.12 kB
Formato Adobe PDF
535.12 kB Adobe PDF   Visualizza/Apri   Richiedi una copia

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11584/263278
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 1
  • ???jsp.display-item.citation.isi??? 1
social impact