Xielifuguli Keranmu

Papers

Total Citations

H-Index

About

Xielifuguli Keranmu is a researcher at the forefront of affective computing and human-robot interaction, with a particular focus on emotion recognition from textual data. Her work addresses the critical challenge of enabling intelligent systems to understand human emotions in social media and robotic applications. In her most-cited study, "Sentence Emotion Classification for Intelligent Robotics Based on Word Lexicon and Emoticon Emotions" (2018, 5 citations), Keranmu developed a novel hybrid approach that integrates word-level sentiment lexicons with emoticon-based emotional cues to improve sentence-level emotion classification. This contribution is significant because it bridges the gap between traditional lexicon methods and the expressive power of emoticons, which are increasingly prevalent in digital communication. By enhancing the accuracy of emotion detection, her research directly supports the development of more empathetic and responsive social robots. Though early in her career, Keranmu’s work lays a vital foundation for advancing natural language understanding in robotics, offering practical tools for creating machines that can better interpret and respond to human emotional states.