Improving Non-Native Speakers’ Participation with an Automatic Agent

Context

  • At NTT Communication Science Laboratories in Japan, I led a project to facilitate multilingual communication.

  • I identified a novel design opportunity through in-depth literature review and market research, directly driving the creation of an AI conversational robot, which significantly diverged from previous unsuccessful approaches.

  • This project increased participation by 40%, sparked interdisciplinary discussions at a major ACM conference and received news coverage for its unique contribution to the field.

What Did I do?

  • Identified a novel design opportunity after an in-depth literature review, directly driving the design of an AI conversational robot.

  • Collaborated with a cross-functional team to build the robot, increasing participation of Non-Native speakers by 40%.

  • Designed and led mixed-methods research, including experiments (A/B testing, Qualtrics surveys) and user interviews, to prove the robot’s effectiveness and generate actionable design recommendations.

  • Published and presented at a major ACM conference, and spoke with reporters about the project for news coverage.

More details about this project.

Impact

  • Increased participation of Non-Native speakers by 40% .

  • Research insights directly employed to develop a new generation of conversational robot.

  • Reached wider audience through presentations at a large ACM conference, news coverage, and podcast.

Goals

  • Use technology to facilitate more balanced communication in multilingual groups.

  • Prove the effectiveness of the technology with quantitative experiments.

  • Gather user feedback with in-depth, qualitative interviews to inform the design of future platforms.