Autoregressive Affective Language Forecasting: A Self-Supervised Task.
Autoregressive Affective Language Forecasting: A Self-Supervised Task.
复制标题
DOI：
10.18653/v1/2020.coling-main.261
复制
发表时间：
2020-12
期刊：
影响因子：
--
通讯作者：
Schwartz HA
中科院分区：
文献类型：
--
作者：
Matero M;Schwartz HA
人类的自然语言是在特定的时间点上提到的，而人类的情感是随着时间而变化的。虽然许多研究已经建立了语言使用和情绪状态之间的紧密联系，但很少有人试图及时建立情绪语言的模型。在这里，我们介绍了情感语言预测任务——基于语言过去的变化来预测语言未来的变化，这是一项具有现实应用的任务，如心理健康治疗或预测消费者信心趋势。我们建立了任务的一些基本自回归特征（必要的历史大小，静态与动态长度，不同的时间步分辨率），然后建立流行的单词序列模型来代替基于语言的情感序列。在一个包含1900个用户和6种情绪和2个额外语言属性的每周+每日得分的新颖Twitter数据集上，我们发现具有衰减隐藏状态的新型双序列GRU模型获得了最佳结果（r = 0.66）。我们让我们的匿名数据集以及任务设置和评估代码可供其他人使用。
Human natural language is mentioned at a specific point in time while human emotions change over time. While much work has established a strong link between language use and emotional states, few have attempted to model emotional language in time. Here, we introduce the task of affective language forecasting – predicting future change in language based on past changes of language, a task with real-world applications such as treating mental health or forecasting trends in consumer confidence. We establish some of the fundamental autoregressive characteristics of the task (necessary history size, static versus dynamic length, varying time-step resolutions) and then build on popular sequence models for words to instead model sequences of language-based emotion in time. Over a novel Twitter dataset of 1,900 users and weekly + daily scores for 6 emotions and 2 additional linguistic attributes, we find a novel dual-sequence GRU model with decayed hidden states achieves best results (r = .66). We make our anonymized dataset as well as task setup and evaluation code available for others to build on.