With the advent of Web 2.0, a term used to indicate an evolution state for the internet and especially for the World Wide Web, the social dimension, the possibility of sharing and the authorship of the internet itself have undergone a radical modification, far from mere fruition. The new ways of internet possible uses open previously unseen scenarios founded on the possibilities, now given to the final users, to create and modify online multimedia contents. There is also a chance to express personal opinions though blogs, forums or systems such as Wikipedia, Youtube, Facebook, Twitter, Gmail or TripAdvisor. This new range of possible functions and products subsequently makes the user able to access an immense amount of non-structured data in real time, in order to look for useful advices, while, for instance, searching for information before the purchase of a new cell phone. This dissertation is part of an Online Reputation Management and Sentiment Analisys Project conducted by Politecnico di Milano for the City of Milan. Its aim is to find a new methodology to identify the top influencer for each desired commercial category, develop a WISPO Tool module, and experimentally analyze data inherent to the cycling event “Giro D’Italia”. All the studies regarding Twitter were confirmed. According to previous studies users’ popularity is only slightly correlated to their influence, expressed in terms of retweets and mentions. In addition to this, the methodology proved its efficiency in the identification of the so called influencers, and it is consistent with open lists of institutional influencers.
Con la nascita del Web 2.0, termine utilizzato per indicare uno stato dell' evoluzione di internet e in particolare del World Wide Web, si e’ radicalmente modificata la dimensione sociale, della condivisione e dell’autorialità della rete stessa, rispetto alla sua mera fruizione. E’ proprio la modalità di utilizzo della rete ad aprire nuovi scenari fondati sulla possibilità data all’utente di fruire e di creare/modificare i contenuti multimediali. Si hanno a disposizione anche nuove vie alternative per esprimere le proprie opinioni ed esperienze attraverso blog, forum e sistemi quali Wikipedia, Youtube, Facebook, Twitter, Gmail o TripAdvisor, portando di conseguenza l’utente a poter consultare in tempo reale un immenso bacino di dati non strutturati per cercare utili consigli, per informarsi, ad esempio, prima dell’acquisto di un cellulare. Il presente lavoro di tesi si inserisce all’interno di un progetto di gestione della reputation online e di sentiment analysis condotto dal Politecnico per il Comune di Milano. Esso si propone di individuare una metodologia per identificare i top influencer per ogni categoria commerciale desiderata, sviluppare un modulo del tool WISPO ed analizzare sperimentalmente i dati inerenti l’evento ciclistico “Giro d’Italia”. Sono stati confermati gli studi effettuati su Twitter secondo i quali la popolarità degli utenti è poco correlata alla loro influence, espressa in termini di retweet e mention. La metodologia è anche efficace nell’individuazione degli influencer e consistente con liste aperte di influencer istituzionali.
Una metodologia di analisi per l'identificazione degli influencer basata sull'ascolto di eventi rilevanti supportata dalla semantica
OLZERI, CLAUDIA
2010/2011
Abstract
With the advent of Web 2.0, a term used to indicate an evolution state for the internet and especially for the World Wide Web, the social dimension, the possibility of sharing and the authorship of the internet itself have undergone a radical modification, far from mere fruition. The new ways of internet possible uses open previously unseen scenarios founded on the possibilities, now given to the final users, to create and modify online multimedia contents. There is also a chance to express personal opinions though blogs, forums or systems such as Wikipedia, Youtube, Facebook, Twitter, Gmail or TripAdvisor. This new range of possible functions and products subsequently makes the user able to access an immense amount of non-structured data in real time, in order to look for useful advices, while, for instance, searching for information before the purchase of a new cell phone. This dissertation is part of an Online Reputation Management and Sentiment Analisys Project conducted by Politecnico di Milano for the City of Milan. Its aim is to find a new methodology to identify the top influencer for each desired commercial category, develop a WISPO Tool module, and experimentally analyze data inherent to the cycling event “Giro D’Italia”. All the studies regarding Twitter were confirmed. According to previous studies users’ popularity is only slightly correlated to their influence, expressed in terms of retweets and mentions. In addition to this, the methodology proved its efficiency in the identification of the so called influencers, and it is consistent with open lists of institutional influencers.| File | Dimensione | Formato | |
|---|---|---|---|
|
2011_10_Olzeri.pdf
non accessibile
Descrizione: Testo della tesi
Dimensione
4.94 MB
Formato
Adobe PDF
|
4.94 MB | Adobe PDF | Visualizza/Apri |
I documenti in POLITesi sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
https://hdl.handle.net/10589/28981