ReNew: A Semi-Supervised Framework for Generating Domain-Specific Lexicons and Sentiment Analysis
ReNew: A Semi-Supervised Framework for Generating Domain-Specific Lexicons and Sentiment Analysis
复制标题
DOI：
10.3115/v1/p14-1051
复制
发表时间：
2014-06
期刊：
影响因子：
--
通讯作者：
Zhe Zhang;Munindar P. Singh
中科院分区：
文献类型：
--
作者：
Zhe Zhang;Munindar P. Singh
固执己见的文本中捕捉到的情绪为社交媒体服务提供了有趣且有价值的信息。然而，由于语言表示的复杂性和多样性，建立一个准确提取此类情感的框架具有挑战性。我们提出了一个半监督框架，用于生成特定领域的情感词典并推断分段级别的情感。我们的框架可以大大减少构建高质量领域特定情感词典的人力。具体来说，在我们的评估中，仅使用 20 条手动标记的评论，它就生成了特定领域的情感词典，加权平均 FMeasure 增益为 3%。我们的情感分类模型的准确度比基于基本话语单元的最先进方法高出约 1%。
The sentiment captured in opinionated text provides interesting and valuable information for social media services. However, due to the complexity and diversity of linguistic representations, it is challenging to build a framework that accurately extracts such sentiment. We propose a semi-supervised framework for generating a domain-specific sentiment lexicon and inferring sentiments at the segment level. Our framework can greatly reduce the human effort for building a domainspecific sentiment lexicon with high quality. Specifically, in our evaluation, working with just 20 manually labeled reviews, it generates a domain-specific sentiment lexicon that yields weighted average FMeasure gains of 3%. Our sentiment classification model achieves approximately 1% greater accuracy than a state-of-the-art approach based on elementary discourse units.