Kenny Tsu Wei Choo

Kenny Tsu Wei Choo

Auto-generated profile, based on publicly available information

Kenny Tsu Wei Choo

Singapore University of Technology and Design

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
29 November 2023 in ACM Transactions on Computer-Human Interaction
Verified
Journal Article
Open access
JGJie Gao
Jie Gao
KCKenny Tsu Wei Choo
Kenny Tsu Wei Choo
JCJunming Cao
Junming Cao
RLRoy Ka-Wei Lee
Roy Ka-Wei Lee
SPSimon Perrault
Simon Perrault
While AI-assisted individual qualitative analysis has been substantially studied, AI-assisted collaborative qualitative analysis (CQA) – a process that involves multiple researchers working together to interpret data—remains relatively unexplored. After identifying CQA practices and design opportunities through formative interviews, we designed and implemented CoAIcoder, a tool leveraging AI to enhance human-to-human collaboration within CQA through four distinct collaboration methods. With a between-subject design, we evaluated CoAIcoder with 32 pairs of CQA-trained participants across common CQA phases under each collaboration method. Our findings suggest that while using a shared AI model as a mediator among coders could improve CQA efficiency and foster agreement more quickly in the early coding stage, it might affect the final code diversity. We also emphasize the need to consider the independence level when using AI to assist human-to-human collaboration in various CQA scenarios. Lastly, we suggest design implications for future AI-assisted CQA systems.

11 May 2024
Verified
Conference Paper
Open access
JGJie Gao
Jie Gao
SGSimret Araya Gebreegziabher
Simret Araya Gebreegziabher
KCKenny Tsu Wei Choo
Kenny Tsu Wei Choo
TLToby Jia-Jun Li
Toby Jia-Jun Li
SPSimon Tangi Perrault
Simon Tangi Perrault
TMThomas W Malone
Thomas W Malone
With ChatGPT’s release, conversational prompting has become the most popular form of human-LLM interaction. However, its effectiveness is limited for more complex tasks involving reasoning, creativity, and iteration. Through a systematic analysis of HCI papers published since 2021, we identified four key phases in the human-LLM interaction flow—planning, facilitating, iterating, and testing—to precisely understand the dynamics of this process. Additionally, we have developed a taxonomy of four primary interaction modes: Mode 1: Standard Prompting, Mode 2: User Interface, Mode 3: Context-based, and Mode 4: Agent Facilitator. This taxonomy was further enriched using the “5W1H” guideline method, which involved a detailed examination of definitions, participant roles (Who), the phases that happened (When), human objectives and LLM abilities (What), and the mechanics of each interaction mode (How). We anticipate this taxonomy will contribute to the future design and evaluation of human-LLM interaction.


1 July 2024
Verified
Conference Paper
Open access
KSKellie Yu Hui Sim
Kellie Yu Hui Sim
KFKohleen Tijing Fortuno
Kohleen Tijing Fortuno
KCKenny Tsu Wei Choo
Kenny Tsu Wei Choo
Providing timely support and intervention is crucial in mental health settings. As the need to engage youth comfortable with texting increases, mental health providers are exploring and adopting text-based media such as chatbots, community-based forums, online therapies with licensed professionals, and helplines operated by trained responders. To support these text-based media for mental health–particularly for crisis care–we are developing a system to perform passive emotion-sensing using a combination of keystroke dynamics and sentiment analysis. Our early studies of this system posit that the analysis of short text messages and keyboard typing patterns can provide emotion information that may be used to support both clients and responders. We use our preliminary findings to discuss the way forward for applying AI to support mental health providers in providing better care.

13 May 2024
Verified
Conference Paper
Open access
MHMing Shan Hee
Ming Shan Hee
KSKarandeep Singh
Karandeep Singh
CMCharlotte Ng Si Min
Charlotte Ng Si Min
KCKenny Tsu Wei Choo
Kenny Tsu Wei Choo
RLRoy Ka-Wei Lee
Roy Ka-Wei Lee
The proliferation of hate speech (HS) has compromised the safety and trustworthiness of the internet, exacerbating social divides by promoting hatred and discrimination. Although recent studies have produced guidelines and developed advanced technologies for the automated detection of HS, their efficacy and adaptability in real-world applications remain unclear. Furthermore, existing guidelines on what constitutes HS might not reflect the perspectives and beliefs of individuals and communities. This paper introduces Brinjal, a multifaceted web plugin designed for the collaborative detection of HS. Brinjal enables individuals to identify instances of HS and engage in discussions to verify such content, thereby enhancing the collective understanding of HS. Additionally, Brinjal serves as a practical platform for deploying and evaluating advanced HS detection models, facilitating user interaction and performance assessment. Lastly, Brinjal includes an analytical tool for analyzing HS, offering insights based on the crowdsourced instances and discussions about HS across various websites. The video demonstration of Brinjal can be viewed here: https://youtu.be/\_JxziIVWBO4. Disclaimer: This paper contains violent and discriminatory content that may be disturbing to some readers.

10 November 2025
Verified
Conference Paper
Open access
OKOka Kurniawan
Oka Kurniawan
ECErick Chandra
Erick Chandra
CPChristopher M. Poskitt
Christopher M. Poskitt
YNYannic Noller
Yannic Noller
KCKenny Tsu Wei Choo
Kenny Tsu Wei Choo
CJCyrille Jegourel
Cyrille Jegourel