Detecting Concept-level Emotion Cause in Microblogging
This addresses the challenge of understanding user emotions in social media for applications like sentiment analysis, though it appears incremental.
The paper tackled the problem of detecting emotion causes in microblogging by proposing a Concept-level Emotion Cause Model (CECM), which outperformed baseline methods on a Sina Weibo dataset.
In this paper, we propose a Concept-level Emotion Cause Model (CECM), instead of the mere word-level models, to discover causes of microblogging users' diversified emotions on specific hot event. A modified topic-supervised biterm topic model is utilized in CECM to detect emotion topics' in event-related tweets, and then context-sensitive topical PageRank is utilized to detect meaningful multiword expressions as emotion causes. Experimental results on a dataset from Sina Weibo, one of the largest microblogging websites in China, show CECM can better detect emotion causes than baseline methods.