Introduction of the opinions of tourist services based on sentiment

One of the sources of information to detect the level of customer satisfaction is the set of reviews they leave on websites such as Trip Advisor. A problem arises when there is a large number of reviews and administrators have difficulty identifying those that reflect the client's feelings from...

Full description

Saved in:

Bibliographic Details
Published in:	2018 13th Iberian Conference on Information Systems and Technologies (CISTI) pp. 1 - 8
Main Authors:	Gomez A., Hector F., Bano N., Freddy Patricio, Martinez C., Carlos Eduardo, Alvarez Gomez, Gustavo Adolfo, Culque T., Walter V., Bustamante-Sanchez, Natalia Soledad, Estefania Sanchez Cevallos, Rosario
Format:	Conference Proceeding
Language:	English
Published:	AISTI 01-06-2018
Subjects:	Blogs Facsimile Mutual information Opinion Orientation Proposals Semantic Semantics Support vector machines Text mining Tourism
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Description
Summary:	One of the sources of information to detect the level of customer satisfaction is the set of reviews they leave on websites such as Trip Advisor. A problem arises when there is a large number of reviews and administrators have difficulty identifying those that reflect the client's feelings from the reviews. For this study, some applications generated in the Python programming language were used in order to assign an excellent and bad criterion by adding a feeling textually. The Sentistrength classifier was also used, which analyzes text to return a value of positive or negative sentiment; these two contexts were used mathematically and statistically to obtain referential data based on an analysis of the ROC curve with values of true positives and true negatives as well as false positives and false negatives.
DOI:	10.23919/CISTI.2018.8399376