Opinion Extraction from Editorial Articles based on Context Information
Opinion Extraction from Editorial Articles based on Context Information
复制标题
DOI：
10.5220/0005633503750380
复制
发表时间：
2015-11
期刊：
影响因子：
--
通讯作者：
Yoshimi Suzuki;Fumiyo Fukumoto
中科院分区：
文献类型：
--
作者：
Yoshimi Suzuki;Fumiyo Fukumoto
观点提取有助于诸如用户评论中的情感分析等各类任务，以用于推荐和社论摘要。在本文中，我们探讨从报纸社论中提取观点这一问题。为提取作者观点，我们不仅利用单句内的特征，还加入了上下文信息。上下文信息包括目标句子的位置，以及其前句和后句。我们将观点提取任务定义为一个序列标注问题，并采用条件随机场（CRF）。在实验中，我们使用了日本报纸社论，并对CRF的多种特征组合进行运用，以揭示哪些特征对观点提取有效。实验结果表明了该方法的有效性，特别是谓语表达、位置以及前句对观点提取颇为有效。
Opinion extraction supports various tasks such as sentiment analysis in user reviews for recommendations and editorial summarization. In this paper, we address the problem of opinion extraction from newspaper editorials. To extract authorâs opinion, we used context information addition to the features within a single sentence only. Context information are a location of the target sentence, and its preceding, and succeeding sentences. We defined the opinion extraction task as a sequence labeling problem, using conditional random fields (CRF). We used Japanese newspaper editorials in the experiments, and used multiple combination of features of CRF to reveal which features are effective for opinion extraction. The experimental results show the effectiveness of the method, especially, predicate expression, location and previous sentence are effective for opinion extraction.