Identifying Structural Holes for Sentiment Classification
Identifying Structural Holes for Sentiment Classification
复制标题
识别情感分类的结构漏洞
DOI：
10.1007/s10796-021-10185-x
复制
发表时间：
2021-09
影响因子：
5.9
通讯作者：
Junjie Wu
中科院分区：
文献类型：
--
作者：
Zheng Xie;Guannan Liu;Jinming Qu;Junjie Wu
文本情感分析是一种低成本但有效的识别消费者和市场的方法。情感分析的主流方法是构建基于词袋特征的分类模型，但由于词汇量大、词频分布不均匀，加之有效情感标签有限，这给情感分析带来了挑战。鉴于此，本文提出了一种基于bow的情感分类方法——基于结构孔的情感分类器（SHSC）。强化语义丰富、情感极性明确的词的分类贡献是实现语义语义匹配的关键。为此，我们精心构建了一个词共现网络来表示高频词和低频词。然后，寻找分类效率低下的词的工作被转化为所谓的桥节点的识别，桥节点占据了网络中结构孔的位置。两个有趣的测量方法，即。，信息优势随机和控制优势权重，然后为此目的精心设计，它们分别基于所提出的情感标签传播和短程计算算法。SHSC最后将这些信息作为关键正则器输入到一个简单的回归模型中，以指导参数学习。在真实世界文本数据集上的大量实验表明，我们的SHSC模型优于竞争性基准，特别是在情感标签稀缺的情况下。通过一些鲁棒性检查和演示案例，仔细验证了发现结构洞用于情感分类的有效性。
The prevalence of online user-generated content has attracted great interest in textual sentiment analysis, which provides a low-cost yet effective way to discern consumers and markets. A mainstream of sentiment analysis is to construct a classification model with Bag-of-Words (BoW) features, but the large vocabulary base and skewed distribution of term frequency consistently pose research challenges, which is made even worse by the limited valid sentiment labels. In light of this, in this paper, we propose a novel method calledStructural Holes based Sentiment Classifier(SHSC) for BoW-based sentiment classification. The key to SHSC is to reinforce the classification contribution of semantically rich words with clear-cut sentiment polarity. To this end, a word co-occurrence network is carefully constructed to represent both high and low frequency words. The work to find classification-inefficient words is then transformed into the identification of so-calledbridge nodesthat occupy the positions of structural holes in the network. Two interesting measures,i.e.,information advantage rankandcontrol advantage weight, are then designed elaborately for this purpose, which are based on the proposed sentiment-label propagation and short-path computation algorithms, respectively. SHSC finally feeds this information as the key regularizers into a simple regression model to guide parametric learning. Extensive experiments on real-world text datasets demonstrate the advantage of our SHSC model over competitive benchmarks, particularly when sentiment labels are scarce. The effectiveness of uncovering structural holes for sentiment classification is also carefully verified with some robustness checks and demonstration cases.
登录
查看更多内容
DOI：
10.25300/misq/2017/41.2.03
发表时间：
2017
期刊：
MIS Q.
影响因子：
--
作者：
Xueming Luo;B. Gu;J. Zhang;C. Phang
通讯作者：
Xueming Luo;B. Gu;J. Zhang;C. Phang
DOI：
10.2307/41703506
发表时间：
2012-12
期刊：
MIS Q.
影响因子：
--
作者：
R.S.M. Lau;S. Liao;Kam-Fai Wong;Dickson K. W. Chiu
通讯作者：
R.S.M. Lau;S. Liao;Kam-Fai Wong;Dickson K. W. Chiu
影响因子：
11.4
作者：
Elena Rudkowsky;Martin Haselmayer;Matthias Wastian;Marcelo Jenny;Stefan Emrich;M. Sedlmair
通讯作者：
Elena Rudkowsky;Martin Haselmayer;Matthias Wastian;Marcelo Jenny;Stefan Emrich;M. Sedlmair
影响因子：
7.5
作者：
Khan, Farhan Hassan;Bashir, Saba;Qamar, Usman
通讯作者：
Qamar, Usman
DOI：
--
发表时间：
2014-08
期刊：
--
影响因子：
--
作者：
Duyu Tang;Furu Wei;Bing Qin;M. Zhou;Ting Liu
通讯作者：
Duyu Tang;Furu Wei;Bing Qin;M. Zhou;Ting Liu