Mesure de la satisfaction de clients basée sur les Commentaires en ligne
No Thumbnail Available
Date
2021
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
Abstract
Have you ever wondered how to use the mass of information we have today? An example is
the online news feed, online store reviews or social media. The problem is that this
information is often so abundant that it becomes overflowing and virtually unusable. With
over 6,000 tweets per second, we're probably missing a ton of information and losing the edge
over those who can use it. By combining text mining, natural language processing and
machine learning, it becomes possible to create an application capable of analyzing the
feeling of a text at the speed of light. Capturing such a feeling is called sentiment analysis,
and that is what we are trying to achieve in this project. The objective of this project is to go
through all the steps necessary to develop a machine learning model capable of analyzing and
classifying any customer sentiment from a text review, in theory and in practice with Python.
We will see how to clean and transform this textual data, so that it can be used efficiently by a
model. We will finally build our model and test it with real customer reviews. Now think
what we can learn if we can extract all of this useful information from this text in a reasonable
amount of time, which is what we are going to try to do in this project.