The explosion of data from blogs , online forums, social networks , Allows Those who possess the right analysis tools , to identify the sentiment and the preferences of user on the various events , products or services in general. The purpose of this thesis is the application of the techniques of Sentiment Analysis and Opinion Analysis for messages relating to the various Italian universities from the two main social networks: Facebook and Twitter. The study it started with an initial phase of hand - coding of data sets related to the case study in question. Then it proceeded to analysis of mathematical methods and parameters used and their relative tuning. They are then examined in detail the results achieved , also seeking a mathematical model for grasp the evolution of the sentiments expressed by the students on social networks. In conclusion there are highlighted the critical issues encountered , the outstanding problems and possible improvements to achieve the most precise and accurate results.
L'esplosione dei dati provenienti dai blogs, forum online, social network, permette, a chi in possesso dei giusti strumenti di analisi, di individuare il sentiment e le preferenze degli utenti sui vari eventi, prodotti o servizi in genere. Lo scopo di questa tesi è l'applicazione delle tecniche di Sentiment Analysis e Opinion Analysis per i messaggi relativi ai diversi atenei italiani provenienti dai due social network principali: Facebook e Twitter. Lo studio ha previsto una prima fase di hand-coding dei dataset relativi al case study in esame. Successivamente si è proceduto ad analisi dei parametri dei metodi matematici utilizzati e il loro relativo tuning. Vengono successivamente esaminati in dettaglio i risultati conseguiti, ricercando inoltre un modello matematico in grado di cogliere l'evoluzione dei sentimenti espressi dagli studenti sui social network. In conclusione vengono evidenziate tutte le criticità incontrate, i problemi ancora aperti e le possibili migliorie per conseguire risultati più precisi e accurati.
Analisi dei social network : sentiment e opinion analysis applicate agli atenei italiani
MIGNOGNA, RICCARDO
2014/2015
Abstract
The explosion of data from blogs , online forums, social networks , Allows Those who possess the right analysis tools , to identify the sentiment and the preferences of user on the various events , products or services in general. The purpose of this thesis is the application of the techniques of Sentiment Analysis and Opinion Analysis for messages relating to the various Italian universities from the two main social networks: Facebook and Twitter. The study it started with an initial phase of hand - coding of data sets related to the case study in question. Then it proceeded to analysis of mathematical methods and parameters used and their relative tuning. They are then examined in detail the results achieved , also seeking a mathematical model for grasp the evolution of the sentiments expressed by the students on social networks. In conclusion there are highlighted the critical issues encountered , the outstanding problems and possible improvements to achieve the most precise and accurate results.File | Dimensione | Formato | |
---|---|---|---|
2016_04_Mignogna.pdf
accessibile in internet per tutti
Descrizione: Testo della tesi
Dimensione
1.48 MB
Formato
Adobe PDF
|
1.48 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/10589/120549