E-Mail: Password:
Sentiment Analysis: Polarity Classification of TripAdvisor's Hotel Reviews
Language: English This thesis is written in English
This thesis on Tesionline.it »
Contact the author
Chiara Martino, Università degli Studi di Bologna, 2016-17
Would you like to translate this thesis/dissertation?
Publish Now!
All documents can be read in PDF format
Get Adobe Reader

Academic area
Sentiment analysis, also known as opinion mining, is a relatively new field of study that analyses subjective information in texts using Natural Language Processing (NLP) techniques.
In a globalised marketplace, businesses and organisations depend increasingly on up-to-date information about customers’ satisfaction and needs. With the development of online platforms and social networks in the past two decades, these data have become easier to obtain. Therefore, it has become of paramount importance to be able to analyse online reviews and opinionated contents in a quick and accurate way. In order to do so, unstructured texts written in natural language must be processed by NLP systems that can perform sentiment analysis to extract subjective information.
The growing attention of researchers for this area is due to its many possible applications in several domains. In this work, we discussed the use of sentiment analysis in the tourism and hospitality industry, since facilities and organisations are keen to capture tourists’ perceptions, concerns, and opinions towards destinations and hotels. These data can be retrieved on websites such as TripAdvisor, in which tourists can share their experience by publishing their supposedly truthful reviews. Hence, they can help peers in their choices and facilities in the acknowledgment of their strength and weaknesses.
The first chapter of this work provides a theoretical background by giving an overview of the literature in sentiment analysis. The second chapter of this dissertation presents the OpeNER Project, an analysis system funded by the European Union and implemented by researchers from Italy, Spain and Holland. It performs, among other tasks, also sentiment analysis and it implements components that were trained on the touristic domain and, more precisely, on accommodation reviews. Moreover, it is available online for free through some web-services and a live demo. Finally, the third chapter focuses on the actual analysis of TripAdvisor’s hotel reviews, which was done with the OpeNER demo and aimed at evaluating the demo’s performances regarding polarity detection at word-level and document-level.