Make aspect-based sentiment classification go further: step into the long-document-level

doi:10.1007/s10489-021-02836-y

科研成果详情

题名	Make aspect-based sentiment classification go further: step into the long-document-level
作者	Wu，Zhenhao 1,2; Gao，Jianbo 1,2; Li，Qingshan 1,2; Guan，Zhi 1,3; Chen，Zhong 1,2
发表日期	2022-06-01
发表期刊	Applied Intelligence
ISSN/eISSN	0924-669X
卷号	52 期号:8 页码:8428-8447
摘要	Aspect-based sentiment classification (ABSC) is a fine-grained analysis task that obtains different sentiment polarities contained in a single text from the views of different aspects. Its practicability draws so much attention from researchers that the number of related works grows explosively. However, existing works mainly aim to obtain polarities from short texts (shorter than 100 words), only a few works analyze documents (shorter than 500 words), but almost no work analyzes long documents (LD, longer than 500 words). This situation makes ABSC powerless when dealing with some texts like in-depth analysis articles. In this paper, we make ABSC step into the LD level by proposing the Hierarchical Aspect-Oriented Framework for Long Document (HAOFL). HAOFL solves two challenges that rarely appear in short texts and normal documents. The first is the too-long input sequence that can cause the model to forget previously learned information or ignore the tailed unlearned information. The second is the unstable sentiment information of the target aspect contained in LD, which increases the difficulty for a model to draw a proper result. HAOFL constructs the data transformation module, dependency processing module, and sentiment aggregation module to solve these two challenges. Numerical experiments prove HAOFL can solve the aforementioned challenges and achieve superior performance in an effective and resource-saving way. With HAOFL, the performances of popular ABSC models on LD are improved at most 8.69% of accuracy and 11.37% of F1-score. In terms of resource-consuming, up to 82.10% of training time and 71.03% of GPU memory are saved.
关键词	Aspect-based sentiment analysis Data transformation Hierarchical architecture Long document
DOI	10.1007/s10489-021-02836-y
URL	查看来源
语种	英语English
Scopus入藏号	2-s2.0-85118368847
引用统计	被引频次：3[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	https://repository.uic.edu.cn/handle/39GCC9TT/13475
专题	个人在本单位外知识产出
通讯作者	Wu，Zhenhao
作者单位	1.Key Laboratory of High Confidence Software Technologies (Peking University),MoE,Beijing,China 2.Department of Computer Science and Technology,EECS,Peking University,Beijing,China 3.National Engineering Research Center for Software Engineering,Peking University,Beijing,China
推荐引用方式 GB/T 7714	Wu，Zhenhao,Gao，Jianbo,Li，Qingshanet al. Make aspect-based sentiment classification go further: step into the long-document-level[J]. Applied Intelligence, 2022, 52(8): 8428-8447.
APA	Wu，Zhenhao, Gao，Jianbo, Li，Qingshan, Guan，Zhi, & Chen，Zhong. (2022). Make aspect-based sentiment classification go further: step into the long-document-level. Applied Intelligence, 52(8), 8428-8447.
MLA	Wu，Zhenhao,et al."Make aspect-based sentiment classification go further: step into the long-document-level". Applied Intelligence 52.8(2022): 8428-8447.