Opinion Mining for Curriculum Enrichment Using Self-Organizing Maps

Abstract

Recently social networks have become a valuable source of information where tastes, preferences and opinions of users around the world come together. This information is an interesting challenge from the perspective of natural language processing (NLP) but is also an aspect of deep interest and great value not only as a marketing strategy for companies and political campaigns but also as an indicator for measuring consumer satisfaction with a product or service. In this paper, we present an opinion mining system that uses text mining techniques and artificial neural networks to automatically obtain useful knowledge about opinions, preferences and user trends. Making use of the Self-Organizing Maps (SOM), we train a neural network that is capable of depending on what is expressed by users in social networks, discern their mood, tastes and experiences in order to help a personnel selection company to find customers and employees necessities. The analysis of these results will make it possible to undertake corrective actions to improve the opinion of the user in relation to their work development. In all experiments, using SOM, we achieve a quantization error below 0.02. In addition, taking into account the evaluation metrics, It can be said that the model has been able to learn and relate the input context values and the results, which proves that the training has been successful and therefore the classification.

Sistemas de monitorización y seguimiento para la mejora de la movilidad inteligente y el análisis de comportamiento (SiMoMIAC). PID2019-108883RB-C21. MINISTERIO DE CIENCIA, INNOVACIÓN Y UNIVERSIDADES.