紀要論文

感情認識の差の原因となる表現の獲得と時系列データを活用した感情分析

ACQUISITION OF EXPRESSIONS CAUSING DIFFERENCES IN EMOTION RECOGNITION AND SENTIMENT ANALYSIS USING TIME SERIES DATA

jpn

24368083

https://doi.org/10.15002/00030751

法政大学大学院理工学研究科

法政大学大学院紀要. 理工学研究科編

65

1

8

2024-03-24

Version of Record

It is often difficult to correctly infer a writer’s emotion from text exchanged online, and differences in recognition between writers and readers can be problematic. In this study, we propose a new framework for detecting sentences that create differences in emotion recognition between the writer and the reader and for detecting the kinds of expressions that cause such differences. Put into practical use, this framework would likely have the ability to mitigate problems based on misunderstandings. Furthermore, we constructed an extended dataset by collecting sentences posted within one hour before and after each of the 43,200 tweets in the WRIME dataset and conducted analyses utilizing the surrounding posts. The dataset constructed in this study enables analysis and emotion estimation utilizing the time-series data of posts on social networking service (SNS) and is expected to contribute to the field of emotion analysis.

Article