Abstract
Sentiment classification, a complex task in natural language processing, becomes even more challenging when analyzing passages with multiple conflicting tones. Typically, longer passages exacerbate this issue, leading to decreased model performance. The aim of this paper is to introduce novel methodologies for isolating conflicting sentiments and aggregating them to effectively predict the overall sentiment of such passages. One of the aggregation strategies involves a Multi-Layer Perceptron (MLP) model which outperforms baseline models across various datasets, including Amazon, Twitter, and SST while costing $\sim$1/100 of what fine-tuning the baseline would take.
Abstract (translated)
情感分类是自然语言处理中的一个复杂任务，当分析包含多种冲突情绪的段落时，该任务变得更加具有挑战性。通常情况下，较长的文本会使这个问题更加严重，并导致模型性能下降。本文旨在介绍一些新颖的方法来分离这些相互矛盾的情绪并将它们聚合起来，以有效预测此类文本的整体情感倾向。 其中一种聚合策略采用多层感知机（Multi-Layer Perceptron, MLP）模型，在亚马逊、推特和SST等不同数据集上均优于基准模型，并且其训练成本仅为微调基准模型的约1/100。
URL
https://arxiv.org/abs/2505.06320
