logo SBA

ETD

Archivio digitale delle tesi discusse presso l’Università di Pisa

Tesi etd-11102017-112209


Tipo di tesi
Tesi di laurea magistrale
Autore
OSSOLA, GIACOMO
URN
etd-11102017-112209
Titolo
Predicting New Product Success from Social Network Data
Dipartimento
INGEGNERIA DELL'ENERGIA, DEI SISTEMI, DEL TERRITORIO E DELLE COSTRUZIONI
Corso di studi
INGEGNERIA GESTIONALE
Relatori
relatore Bonaccorsi, Andrea
correlatore Dott. Chiarello, Filippo
Parole chiave
  • microblogs
  • New product success forecasting
  • social media prediction
  • Twitter
Data inizio appello
29/11/2017
Consultabilità
Non consultabile
Data di rilascio
29/11/2087
Riassunto
In recent years, social media has become ubiquitous and important for social networking and content sharing. Moreover, the content that is generated from these websites remains largely untapped. Some researchers proved that social media has been a valuable source to predict the future outcomes of some events such as box-office movies revenues or political elections. In 2017,a grad student of University of Pisa, with his thesis work, tried to predict success or failure of a panel of products disclosed at IFA Berlin 2016. He collected tweets produced by users for a period of about one month after the conclusion of the trade show. Then, he analysed the tweets applying for the first time an extraction software that may allow detecting, inside the conversations, the advantages and disadvantages that users are observing using a product. Finally, he found positive correlations between his results and the review of the selected products. With this thesis work, we want to verify the results of the previous work, conduct an effective study of the state of the art about data mining tools and methods for gathering data from social media, and replicate the experiment on a new dataset.We discovered that our advantages and drawbacks analysis is a more powerful tool than sentiment analysis when it evaluates technical-functional opinion about products.
File