Carregant...
Fitxers
Tipus de document
Treball de fi de màsterData de publicació
Llicència de publicació
Si us plau utilitzeu sempre aquest identificador per citar o enllaçar aquest document: https://hdl.handle.net/2445/173181
Big data and Sentiment Analysis considering reviews from e-commerce platforms to predict consumer behavior
Títol de la revista
Autors
ISSN de la revista
Títol del volum
Resum
Nowadays and since the last two decades, digital data is generated on a massive scale, this phenomenon is known as Big Data (BD). This phenomenon supposes a change in the way of managing and drawing conclusions from data. Moreover, techniques and methods used in artificial intelligence shape new ways of analysis considering BD. Sentiment Analysis (SA) or Opinion Mining (OM) is a topic widely studied for the last few years due to its potential in extracting value from data. However, it is a topic that has been more explored in the fields of engineering or linguistics and not so much in business and marketing fields. For this reason, the aim of this study is to provide a reachable guide that includes the main BD concepts and technologies to those who do not come from a technical field such as Marketing directors. This essay is articulated in two parts. Firstly, it is described the BD ecosystem and the technologies involved. Secondly, it is conducted a systematic literature review in which articles related with the field of SA are analysed. The contribution of this study is a summarization and a brief description of the main technologies behind BD, as well as the techniques and procedures currently involved in SA.
Descripció
Treballs Finals del Màster de Recerca en Empresa, Facultat d'Economia i Empresa, Universitat de Barcelona, Curs: 2019-2020, Tutor: Javier Manuel Romaní Fernández ; Jaime Gil Lafuente
Matèries (anglès)
Citació
Col·leccions
Citació
PONS-MUÑOZ DE MORALES, Sergi. Big data and Sentiment Analysis considering reviews from e-commerce platforms to predict consumer behavior. [consulta: 29 de novembre de 2025]. [Disponible a: https://hdl.handle.net/2445/173181]