arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1801.03032cs.CLcs.IRcs.SI
收藏

Twitter的话题姿态检测:一个基于注意力的两阶段LSTM模型

Topical Stance Detection for Twitter: A Two-Phase LSTM Model Using Attention

IBM Research(IBM研究院);NSIT(Netaji Subhas Institute of Technology);IIT(印度理工学院)

Kuntal Dey, Ritvik Shrivastava, Saroj Kaushik

摘要:

主题立场检测问题解决了检测文本内容相对于给定主题的立场:给定文本内容的情感是否对给定主题有利(积极),反对(消极)或无(中性)。使用注意力的概念,我们开发了一个两阶段的解决方案。在第一阶段,我们对主观性进行分类--一条给定的推文对于给定的主题是中立的还是主观的。在第二阶段,我们对主观推文的情感进行分类(忽略中性推文)-给定的主观推文是否对主题持赞成或反对的立场。我们为每个阶段提出了一个基于长短期记忆(LSTM)的深度神经网络,并在每个阶段嵌入注意力。在SemEval 2016立场检测Twitter任务数据集上,我们获得了68.84%的最佳情况宏F分数和60.2%的最佳情况准确率,优于现有的基于深度学习的解决方案。我们的框架T-PAN是主题立场检测文献中的第一个,它在两阶段架构中使用了深度学习。

英文摘要:

The topical stance detection problem addresses detecting the stance of the text content with respect to a given topic: whether the sentiment of the given text content is in FAVOR of (positive), is AGAINST (negative), or is NONE (neutral) towards the given topic. Using the concept of attention, we develop a two-phase solution. In the first phase, we classify subjectivity - whether a given tweet is neutral or subjective with respect to the given topic. In the second phase, we classify sentiment of the subjective tweets (ignoring the neutral tweets) - whether a given subjective tweet has a FAVOR or AGAINST stance towards the topic. We propose a Long Short-Term memory (LSTM) based deep neural network for each phase, and embed attention at each of the phases. On the SemEval 2016 stance detection Twitter task dataset, we obtain a best-case macro F-score of 68.84% and a best-case accuracy of 60.2%, outperforming the existing deep learning based solutions. Our framework, T-PAN, is the first in the topical stance detection literature, that uses deep learning within a two-phase architecture.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑