1096
Yes, I/my team will participate in the Pitch Day and Awards Presentation Ceremony. / 是，我或我的團隊會參加最後簡報和頒獎典禮。
School of Science and Technology, Singapore
Sim Yong Seng Stanley
+65-97710244
Email hidden; Javascript is required.
| Row ID | Full name in English / 英文全名 | Full name in Chinese (if any) / 中文全名（如有） | Role / 身份 |
|---|---|---|---|
1 |
Ally Clover Ng |
黄琬晴 |
參賽選手 / Participant |
2 |
Chang Li Xuan Raeanne |
郑莉璇 |
參賽選手 / Participant |
3 |
TANG WEN QI JOVITA |
老師 / Teacher |
Using AI to help teachers track students' contributions in group discussions
As group projects become more common, it is increasingly apparent how louder voices will dominate and quieter ones will fade into the background. It can sometimes be difficult for teachers to notice this, for example, who's contributing what, who is taking charge, and who is being left behind beyond visible contributions, essential learning points, misunderstanding, motivation, or disengagement that can go unnoticed in group discussions. Learning is not done through results—it’s done through communication. When there's silence, confusion, or tension in group talk, it typically means something's deeper going on. "What are you talking about?" isn't always merely confusion—clearly shows that the group's out of whack or not working really well together. These socio-emotional dynamics can significantly affect students' individual learning and their behaviour in group settings. It can affect students' overall grades and emotions if they do not get along well with their peers arguing over one of and others points. If teachers do not understand these behind-the-scenes dynamics, it can lead to quieter students being under-supported and weaker collaboration skills overall too. Without increased awareness of group interactions, teachers and instructors cannot effectively assess each student's contribution and struggle to build a more inclusive, productive group learning environment.
In order to achieve this, we conduct interaction analysis with AI and are guided by two methods: focal analysis and preoccupational analysis. Through Natural Language Processing (NLP), speech diarisation, and live transcription, AI annotates utterances as content-based or meta-level, tracking whether students are discussing ideas, displaying confusion, or disengaging. Using techniques like text classification, sentiment analysis, and real-time transcription, AI converts conversations into written form and organise them into meaningful insights help teachers understand group dynamics. Speaker diarisation ensures each voice is recognised. NLP also highlights key phrases like "building on your point" or "I suggest we," which shows active involvement. In larger or noisy groups, speaker diarisation helps pinpoint who's speaking, while tools like Google Docs can track written contributions through edit history. Voice-to-text makes it supports verbal, written input. With Generative AI, all this data is compiled into helpful visuals—like pie charts, speaker timelines, and keyword summaries—to offer real-time insights for teachers. To make it more practical in the classroom, ceiling-mounted microphones combined with signal processing, to reduce noise, cancel echoes, and level sound, ensuring clear audio. This solution allows teachers to identify who’s contributing, spot potential leaders, and support quieter students, promoting a more balanced group environment.
Artificial intelligence tools like Natural Language Processing (NLP), transcription AI, and speaker diarisation provide real-time, objective feedback on group dynamics so no student is overlooked. These tools track both spoken and written contributions, allowing teachers to assess participation without relying on subjective judgment. NLP captures key phrases that indicate leadership and collaboration, while speaker diarisation identifies individual voices, ensuring all students are recognised. This prevents dominant voices from overshadowing quieter ones. By combining NLP to extract collaborative patterns and speaker tracking to separate individual input, the system produces a detailed multi-modal analysis of group interaction. It captures the full learning conversation—spoken and written—and interprets it using structured, research-based AI techniques. Descriptive and diagnostic insights reveal who participated and where communication broke down. Predictive AI flags potential disengagement, and prescriptive analysis suggests how to restore balance. A live dashboard visualises participation and emotional tone, giving teachers actionable insight during group activities. This enables formative assessment and inclusive teaching without interrupting discussion. Every student’s voice is considered, making collaboration fairer, clearer, and more effective. The combination of real-time data, fine-grained analysis, and visibility across project stages makes this solution both practical and scalable—enhancing learning while promoting equity in classroom group work.
No
Personal Information Collection Statement (PICS)/收集個人資料聲明:
1. The personal data collected in this form will be used for activity-organizing, record keeping and reporting only. The collected personal data will be purged within 6 years after the event.
2. Please note that it is obligatory to provide the personal data required.
3. Your personal data collected will be kept by the LTTC and will not be transferred to outside parties.
4. You have the right to request access to and correction of information held by us about you. If you wish to access or correct your personal data, please contact our staff at lttc@eduhk.hk.
5. The University’s Privacy Policy Statement can be access at https://www.eduhk.hk/en/privacy-policy.
- I have read and agree to the competition rules and privacy policy/我已閱讀並同意比賽規則和隱私權政策。