Title

EvoMSA: A Multilingual Evolutionary Approach for Sentiment Analysis

Author

MARIO GRAFF GUERRERO

SABINO MIRANDA JIMENEZ

Eric Sadit Téllez Avila

Daniela Moctezuma

Access level

Open Access

Alternative identifier

arxiv: https://arxiv.org/abs/1812.02307v3

Dataset reference

datasetURL/http://arxiv.org/abs/1812.02307

Summary or description

Sentiment analysis (SA) is a task related to understanding people's feelings in written text; the starting point would be to identify the polarity level (positive, neutral or negative) of a given text, moving on to identify emotions or whether a text is humorous or not. This task has been the subject of several research competitions in a number of languages, e.g., English, Spanish, and Arabic, among others. In this contribution, we propose an SA system, namely EvoMSA, that our participating systems in various SA competitions, making it domain independent and multilingual by processing text using only language-independent techniques.

EvoMSA is based on Genetic Programming that works by combining the output of text classifers to produce the final prediction. We analyzed EvoMSA on diferent SA competitions to provide a global overview of its performance. The results indicated that EvoMSA is competitive obtaining top rankings in several SA competitions. Furthermore, we performed an analysis of EvoMSA's components to measure their contribution to the performance; the aim was to facilitate a practitioner or newcomer to implement a competitive SA classifer. Finally, it is worth to mention that EvoMSA is available as open source software.

Publisher

Cornell University

Publish date

2019

Publication type

Article

Publication version

Accepted Version

Format

application/pdf

Source

Computation and Language

Language

English

Relation

&

Moctezuma, D. (2018). EvoMSA: A Multilingual Evolutionary Approach for Sentiment Analysis. arXiv:1812.02307 [cs, stat]. Recuperado de http://arxiv.org/abs/1812.02307

Audience

General public

Citation suggestion

Graff, M., Miranda-Jiménez, S., Tellez, E. S.,

Source repository

Repositorio Institucional de INFOTEC

Downloads

132

Comments



You need to sign in or sign up to comment.