Synergy Crowds OÜ, 10141 Tallin, Estonia.
Department of Computer Science, Babeş-Bolyai University, 400084 Cluj-Napoca, Romania.
Sensors (Basel). 2021 Mar 24;21(7):2266. doi: 10.3390/s21072266.
This paper presents a sentiment analysis solution on tweets using Recurrent Neural Networks (RNNs). The method is can classifying tweets with an 80.74% accuracy rate, considering a binary task, after experimenting with 20 different design approaches. The solution integrates an attention mechanism aiming to enhance the network, with a two-way localization system: at memory cell level and at network level. We present an in-depth literature review for Twitter sentiment analysis and the building blocks that grounded the design decisions of our solution, employed as a core classification component within a sentiment indicator of the SynergyCrowds platform.
本文提出了一种基于循环神经网络（RNNs）的推特情感分析解决方案。该方法在尝试了 20 种不同的设计方法后，可以以 80.74%的准确率对推文进行分类，考虑到这是一个二元任务。该解决方案集成了一个注意力机制，旨在增强网络，具有双向定位系统：在记忆单元级别和网络级别。我们对推特情感分析和构建模块进行了深入的文献回顾，这些构建模块是我们解决方案设计决策的基础，作为协同 crowds 平台情感指标的核心分类组件。
