Aspect-based sentiment analysis can help consumers provide clear and objective sentiment recommendations through massive amounts of data and is conducive to overcoming ambiguous human weaknesses in subjective judgments. However, the robustness and accuracy of existing sentiment analysis methods must still be improved. In this article, deep learning and machine learning techniques are combined to construct a sentiment analysis model based on ensemble learning ideas. Furthermore, the proposed model is applied to a sentiment classification for user reviews about restaurants, which are the representative location-based and user-oriented applications in 5G networks. Specifically, a multi-aspect-labeling model is established, and an ensemble aspect-based model is proposed based on the concept of ensemble learning to predict the consumer's true consumption feelings and willingness to consume again, and to improve machine learning based on the developed model. The predictive performance of the algorithm lies within a single domain.

中文翻译：

---

5G 网络中基于方面的用户评论情感分析


基于方面的情感分析可以帮助消费者通过海量数据提供清晰客观的情感推荐，有利于克服人类主观判断上模糊的弱点。然而，现有情感分析方法的鲁棒性和准确性仍有待提高。本文结合深度学习和机器学习技术，构建了基于集成学习思想的情感分析模型。此外，所提出的模型还应用于用户对餐馆评论的情感分类，这是 5G 网络中基于位置和面向用户的代表性应用。具体来说，建立了多方面标签模型，并基于集成学习的概念提出了基于集成方面的模型来预测消费者的真实消费感受和再次消费意愿，并在开发的基础上改进机器学习模型。该算法的预测性能位于单个域内。