Citation

Villanueva-Vega D, Rodriguez-Martinez M. IEEE Int. Conf. Digit. Health ICDH 2021; 2021: 184-190.

Copyright

(Copyright © 2021, IEEE (Institute of Electrical and Electronics Engineers))

DOI

10.1109/icdh52753.2021.00033

PMID

35059145

PMCID

PMC8767031

Abstract

Social networks have become a very important means to facilitate the creation and sharing of information. They also provide real-time information on sales, marketing, politics, natural disasters, and crisis situations, among others. In this work, we investigate neural models for text similarity that can be used to: 1) determine if messages are related or not with a disease, 2) group similar messages to those that we have already captured, analyzed or stored, and 3) find similarity indices between messages using different learning algorithms. Our results show that we can achieve 90% accuracy on the task of classifying which of two tweets is more similar to a sample tweet.

Language: en

Keywords

Deep Learning; similarity; tweets