[论文解读] Boost Phrase-level Polarity Labelling with Review-level Sentiment Classification

Yongfeng Zhang, Min Zhang+2 more|arXiv (Cornell University)|Feb 11, 2015

Sentiment Analysis and Opinion Mining参考文献 47被引用 17

一句话总结

该论文提出了一种约束凸优化框架，利用评论级情感分类来改进短语级情感极性标注，通过解决星级评分与文本情感之间的不一致性，将准确率提升至89%。该方法整合了多种启发式规则，并通过凸性保证全局最优性。

ABSTRACT

Sentiment analysis on user reviews helps to keep track of user reactions towards products, and make advices to users about what to buy. State-of-the-art review-level sentiment classification techniques could give pretty good precisions of above 90%. However, current phrase-level sentiment analysis approaches might only give sentiment polarity labelling precisions of around 70%~80%, which is far from satisfaction and restricts its application in many practical tasks. In this paper, we focus on the problem of phrase-level sentiment polarity labelling and attempt to bridge the gap between phrase-level and review-level sentiment analysis. We investigate the inconsistency between the numerical star ratings and the sentiment orientation of textual user reviews. Although they have long been treated as identical, which serves as a basic assumption in previous work, we find that this assumption is not necessarily true. We further propose to leverage the results of review-level sentiment classification to boost the performance of phrase-level polarity labelling using a novel constrained convex optimization framework. Besides, the framework is capable of integrating various kinds of information sources and heuristics, while giving the global optimal solution due to its convexity. Experimental results on both English and Chinese reviews show that our framework achieves high labelling precisions of up to 89%, which is a significant improvement from current approaches.

研究动机与目标

• 解决高精度评论级情感分类与较低精度短语级情感极性标注之间的性能差距。
• 探究用户评论中数值星级评分与文本情感倾向之间的不一致性。
• 通过整合评论级情感分类结果作为监督信号，改进短语级情感极性标注。
• 开发一种灵活的凸优化框架，能够整合多种启发式规则和信息源。
• 在英文和中文评论数据集上评估该框架的有效性及其跨语言迁移能力。

提出的方法

• 将短语级情感极性标注形式化为约束凸优化问题，以保证全局最优性。
• 整合四类启发式规则：(1) 评论级情感分类，(2) 特征-观点共现，(3) 情感极性一致性，以及(4) 情感传播的结构约束。
• 采用拉格朗日对偶法结合Karush-Kuhn-Tucker (KKT) 条件，推导出具有收敛性证明的迭代优化算法。
• 采用辅助函数方法（基于Lee和Seung, 2001）以确保情感得分矩阵X的更新规则在正确性和收敛性方面得到保障。
• 通过由超参数（λ1至λ4）加权的正则化项构建目标函数，平衡数据保真度、图平滑性和约束执行。
• 使用评论级情感预测结果作为软标签来引导优化，减少对可能存在偏差的星级评分的依赖。

实验结果

研究问题

• RQ1 星级评分与文本情感是否一致的假设在短语级情感标注中成立吗？
• RQ2 能否有效利用评论级情感分类结果来改进短语级情感极性标注？
• RQ3 不同启发式规则对所提框架性能的贡献如何？
• RQ4 该框架在多大程度上可跨语言泛化，例如英文与中文？
• RQ5 该凸优化框架能否在整合多种信息源的同时保证全局最优性？

主要发现

• 所提框架在短语级情感极性标注中实现了高达89%的精确率，显著优于当前最先进方法。
• 在英文和中文数据集上的实验结果证实了该框架的有效性及其跨语言迁移能力。
• 超参数分析表明，全部四类启发式规则均对性能提升有积极贡献。
• 实证验证了星级评分与文本情感之间的不一致性，从而证明了引入评论级监督机制的必要性。
• 凸优化框架保证了全局最优性，并支持多种信息源的灵活整合。
• 迭代优化算法收敛稳定，其正确性通过辅助函数方法得到证明。