Machine learning applied to the sentiment analysis
With the evolution of the Internet, there is a large amount of information present on the web such as the opinions of users or consumers about different contexts, either to express their agreement or disagreement about a product or service received, as well as the opinion of a item purchased or abou...
| Autores Principales: | Cedeno-Moreno, Denis, Vargas, Miguel |
|---|---|
| Formato: | Artículo |
| Idioma: | Español |
| Publicado: |
Universidad Tecnológica de Panamá
2020
|
| Acceso en línea: |
https://revistas.utp.ac.pa/index.php/id-tecnologico/article/view/2833 https://ridda2.utp.ac.pa/handle/123456789/11814 |
| Sumario: |
With the evolution of the Internet, there is a large amount of information present on the web such as the opinions of users or consumers about different contexts, either to express their agreement or disagreement about a product or service received, as well as the opinion of a item purchased or about the management performed by someone. Due to the large number of opinions, comments and suggestions from users, it is very important to explore, analyze and organize their views to make better decisions. Sentiment analysis is a natural language processing and information extraction task that identifies the opinions of the users explained in the form of positive, negative or neutral comments. Several techniques can be used for this purpose, for example the use of lexical dictionaries that has been widely used and recently the use of artificial intelligence specifically supervised algorithms. In this document, we propose the use of supervised algorithm techniques to observe their use and see the performance of different models of supervised algorithms to measure the effectiveness in the classification of a data set. |
|---|