| 研究課題/領域番号 |
18K18085
|
|---|
| 研究機関 | 東京大学 |
|---|
研究代表者 |
ハウタサーリ アリ 東京大学, 大学院情報学環・学際情報学府, 特任准教授 (70752236)
|
|---|
| 研究期間 (年度) |
2018-04-01 – 2023-03-31
|
| キーワード | socio-emotional / multilingual / communication |
|---|
| 研究実績の概要 |
Evaluation results for the third iteration of a software tool for supporting socio-emotional communication showed that the automated method to generate unique speech balloons with ACGAN that match and convey a message sender's level of emotional arousal to the receiver outperformed emoticons as emotional cues in text chats. Moreover, the results confirmed that speech balloons convey only emotional arousal while not interfering with emotional valence transmission.
The paper detailing the system design and evaluation results was published in the top international conference ACM CHI 2022 as a full paper, and it received the ACM CHI 2022 Best Paper Award (top 1%).
The fourth iteration of the software tool is developed by combining the software and evaluation results from the previous iterations. In this iteration, emotional fonts/typefaces represent an abstraction of the emotional valence, and speech balloons represent an abstraction of the level of arousal in emotional text-based messages to non-native speakers who may have difficulties detecting the emotional nuances in second language messages. Furthermore, investigation on the effects of different types of speech balloon shapes on socio-emotional communication is underway.
|
| 現在までの達成度 (区分) |
現在までの達成度 (区分)
1: 当初の計画以上に進展している
理由
The socio-emotional communication support system development and evaluation is proceeding smoothly thanks to effective collaboration with other researchers and developers. In the third iteration, a system to automatically generate unique speech balloons with ACGAN corresponding to the level of emotional arousal in a text message was developed to display more nuanced emotional information in text-based communication. While the COVID-19 pandemic imposes limitations on conducting on-site experiments, implementing the prototype and evaluation interface as a web application afforded an effective remote controlled experiment environment. However, it was necessary to conduct additional experiments to validate the approach throughout FY2021, and organize the experiment sessions over a longer time span than originally anticipated. The experiment showed very promising results in that speech balloons may outperform emoticons as emotional cues to convey arousal level in multilingual text chats.
Fourth iteration of the communication support system is developed by combining the method of displaying emotional valence in fonts with the method for displaying emotional arousal in speech balloons. The system is evaluated through crowdsourcing and interactive experiments in multilingual settings. An investigation on the effects of different speech balloon shapes on socio-emotional communication is conducted in parallel. Furthermore, the development of a multilingual emotional type face corpus is planned for this fiscal year to support machine translation mediated socio-emotional communication.
|
| 今後の研究の推進方策 |
- Evaluate the efficacy of the system for supporting multilingual socio-emotional communication using fonts as valence and speech balloons as arousal abstraction through crowdsourcing and in a controlled laboratory setting.
- Conduct an in-depth investigation on the effects of various speech balloon types on emotional expression in text chats.
- Continue the creation of the proposed non-native sentiment corpora for further system development by utilizing a mobile application to gather human evaluations, and analyze the discrepancies in emotional word evaluations between native and non-native speakers of English.
- Create a multilingual emotional typeface corpus to support machine translation mediated socio-emotional communication.
- Naturalistic and longitudinal user studies on the effect of the proposed systems on relationship management are planned to be conducted.
- Development of a cross-cultural training program based on the research results.
|
| 次年度使用額が生じた理由 |
Travel costs were reduced due to the COVID-19 pandemic. The publication accepted to ACM CHI 2022 is presented in FY2022, and the travel costs are allocated for the purpose of travel, participation and publication costs. Personnel expenditure was reduced in FY2020 and FY2021 due to COVID-19 pandemic are allocated to be used for controlled laboratory experiments, crowdsourcing costs, as well as software development, conducted in FY2022.
|
| 備考 |
ACM CHI 2022 Best Paper Award (top 1%)
|
