The technologies of communication, such as forums and instant messaging, available in the social media platforms open to the possibility to convey and express emotions and feelings, besides to facilitate interaction. Emotions and social relationships are often connected, indeed, emotions and feelings can make the users favorable or reluctant to socialize, as well, experiences of socialization can influence the behaviors. Being personal, emotions and feelings can be crucial in the dynamics of social communities, perhaps more than other elements, such as events and multimedia items, because the individuals tend to interact with the users with who have particular affinity or with who share sensations. In this paper we introduce the problem of tracking users who share emotional behavior with other users. The proposed method relies on a cyberspace based on emotional words extracted from social media posts. It builds emotional trajectories as sequences of points of the cyberspace characterized by highly similar emotions. We show the viability of the method on Twitter data and provide a quantitative evaluation and qualitative considerations.

Analyzing Microblogging Posts for Tracking Collective Emotional Trajectories

Loglisci, Corrado;Andresini, Giuseppina;Impedovo, Angelo;Malerba, Donato
2018

Abstract

The technologies of communication, such as forums and instant messaging, available in the social media platforms open to the possibility to convey and express emotions and feelings, besides to facilitate interaction. Emotions and social relationships are often connected, indeed, emotions and feelings can make the users favorable or reluctant to socialize, as well, experiences of socialization can influence the behaviors. Being personal, emotions and feelings can be crucial in the dynamics of social communities, perhaps more than other elements, such as events and multimedia items, because the individuals tend to interact with the users with who have particular affinity or with who share sensations. In this paper we introduce the problem of tracking users who share emotional behavior with other users. The proposed method relies on a cyberspace based on emotional words extracted from social media posts. It builds emotional trajectories as sequences of points of the cyberspace characterized by highly similar emotions. We show the viability of the method on Twitter data and provide a quantitative evaluation and qualitative considerations.
File in questo prodotto:
Non ci sono file associati a questo prodotto.

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: http://hdl.handle.net/11586/225813
 Attenzione

Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo

Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 2
  • ???jsp.display-item.citation.isi??? ND
social impact