Data for the Rating Prediction (RP) sentiment analysis task such as star reviews are readily available. However, data for aspect-category detection (ACD) and aspect-category sentiment analysis (ACSA) is often desired because of the fine-grained nature but are expensive to collect. In this work, we propose Unified Sentiment Analysis (Uni-SA) to understand aspect and review sentiment in a unified manner. Specifically, we propose a Distantly Supervised Pyramid Network (DSPN) to efficiently perform ACD, ACSA, and RP using only RP labels for training. We evaluate DSPN on multi-aspect review datasets in English and Chinese and find that in addition to the internal efficiency of sample size, DSPN also performs comparably well to a variety of benchmark models. We also demonstrate the interpretability of DSPN's outputs on reviews to show the pyramid structure inherent in unified sentiment analysis.

翻译：摘要：用于评分预测（RP）情感分析任务的数据（如星级评论）易于获取。然而，由于细粒度特性，方面类别检测（ACD）和方面类别情感分析（ACSA）数据虽具有重要价值，但收集成本高昂。本研究提出统一情感分析（Uni-SA）框架，旨在以统一方式理解方面与评论情感。具体而言，我们提出一种远监督金字塔网络（DSPN），仅利用RP标签进行训练即可高效执行ACD、ACSA和RP任务。我们在英文和中文的多方面评论数据集上评估DSPN，发现除样本规模效率优势外，该模型在性能上也与多种基准模型表现相当。此外，我们通过DSPN在评论上的输出可解释性分析，展示了统一情感分析中固有的金字塔结构。