【Session Theme: Other AI x OS Topics】
This work is trying to teach an emotion model how to differentiate the feminine and the masculine writing styles. Features are extracted by unboxing the CNN model via open source packages. By doing so, nauced findings on gender differences of emotion expressions are here to support and extend previous evident-based gender and emotion studies.
Gender study is recently a trendy research topic in deep learning domain. Related studies focus on tackling stereotypes that are implicitly learned from human-generated contents. Our work, however, is trying to teach an emotion model how to differentiate the feminine and the masculine writing styles. By doing so, nauced findings on gender differences of emotion expressions are here to support and extend previous evident-based gender and emotion studies.
About Toby Liu
Toby Liu is a NLP researcher. He works at Mercari Inc. as a Machine Learning engineer based in Tokyo currently. He used to be a OSS community member at MozTW, COSCUP, and g0v. One of D4SG projects he participated was Predictive Risk Map of Fire Hazards in Kaohsiung 2.0. The result was presented in DataSci.tw '17, MOPCON '17, South Taiwan Statistics Conf ‘17, and PanKnowledge Festival ‘17. His research thesis in emotion analysis was published on EMNLP '18.