Kenji Kita
Papers
5
Total Citations
20
H-Index
4
About
Kenji Kita is a leading researcher in affective computing and human-robot interaction, with a focus on enabling machines to understand and respond to human emotions. His work spans emotion recognition from speech and text, dialogue analysis, and intelligent robotics. Kita has pioneered methods for normalizing prosodic features—such as pitch and rhythm—to improve emotion detection from speech, addressing the challenge that these features vary drastically across speakers and contexts. He also developed sentence emotion classification techniques that combine word lexicons with emoticon analysis, achieving robust sentiment extraction from social media text. In dialogue systems, Kita introduced deep neural network approaches for detecting dialogue breakdowns by analyzing emotional shifts, and he proposed models to predict emotion state changes in personae based on conversational context. His research has been cited over 20 times, with key papers published between 2012 and 2022. Notably, his work on prosodic normalization and emotion prediction has direct applications in creating more natural, empathetic interactions between humans and robots, making him a key contributor to the advancement of socially intelligent agents.
Research Focus
Key Achievements
Top Papers
- 1
- 2Emotion recognition method based on normalization of prosodic features5 citations · 2013
- 3
- 4
- 5