IUCL at WASSA 2022 Shared Task: A Text-only Approach to Empathy and Emotion Detection
IUCL at WASSA 2022 Shared Task: A Text-only Approach to Empathy and Emotion Detection
复制标题
DOI：
10.18653/v1/2022.wassa-1.21
复制
发表时间：
2022
期刊：
影响因子：
--
通讯作者：
Yue (Eleanor) Chen;Yingnan Ju;Sandra Kübler
中科院分区：
文献类型：
--
作者：
Yue (Eleanor) Chen;Yingnan Ju;Sandra Kübler
我们的系统IUCL参加了WASSA 2022共情检测和情绪分类共享任务。我们建立这个系统的主要目标是调查人口统计属性的使用如何影响绩效。我们的（官方）结果显示，我们的纯文本系统表现非常有竞争力，在同理心检测任务中排名第一，平均皮尔逊相关系数为0.54，在情感分类任务中排名第二，达到Macro-F为0.572。我们使用文本和人口统计数据的系统竞争力较低。
Our system, IUCL, participated in the WASSA 2022 Shared Task on Empathy Detection and Emotion Classification. Our main goal in building this system is to investigate how the use of demographic attributes influences performance. Our (official) results show that our text-only systems perform very competitively, ranking first in the empathy detection task, reaching an average Pearson correlation of 0.54, and second in the emotion classification task, reaching a Macro-F of 0.572. Our systems that use both text and demographic data are less competitive.