Adela S.M. Lau

Prof. Adela S.M. Lau


Research Focus & Metrics

Academic Career Length

17Years (2010-Present)

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

Representative Publications

View All Publications
18 November 2022 in Knowledge-Based Systems
Verified
Journal Article
Open access
LCLiege Cheung
Liege Cheung
YWYun Wang
Yun Wang
ALAdela S.M. Lau
Adela S.M. Lau
RCRogers M.C. Chan
Rogers M.C. Chan

1 February 2025 in The International Journal of Entrepreneurship and Innovation
Verified
Journal Article
Closed access
ALAdela S.M. Lau
Adela S.M. Lau
JWJulie Wu
Julie Wu
PMPatrick Ma
Patrick Ma
HLHerbert Lee
Herbert Lee
The current researches of metaverse have focused mainly on data management, security, networking, and 3D modeling. The deployment of 3D data visualization in metaverses for entrepreneurship applications has not been studied. To review metaverse and data visualization technologies and propose a novel method of combining 3D data visualization with exploratory analysis using artificial intelligence (AI) and ontology for data analysis and visualization in the metaverse. The research methods include exploratory reviews of metaverse and data visualization technologies, and case studies as a proof of concept of the proposed model. The review results of existing data visualization are devoid of an analytical process, are inflexible for customization, have no collaborative data interaction or evaluation, and are lack of guidance of using those tools. Artificial intelligence models, 3D visualizations, metaverse, and ontology-based AI chatbots have been proposed to solve these problems respectively. The case study demonstrates the effectiveness of these methods to guide users on 3D data visualization collaboratively to generate insights and recommendations. The research impacts are using ontology to structure the data, an AI chatbot in metaverse to explain the analysis, and a 3D data visualization in metaverse for improving collaborative work and insight generation.

19 May 2010
Verified
Book Chapter
Open access
ALAdela S.M. Lau
Adela S.M. Lau
ETEric TSUI
Eric TSUI
In clinical training, students plan, implement and evaluate their learning activities by themselves. They apply theories and concepts in a real clinical environment and learn through social interaction and reflective thinking to experience, conceptualize, apply and create new knowledge to solve clinical problems. Since students are sent to different clinical locations for training and are mentored on a one-to-one basis, it is difficult for students to share their knowledge, make enquiries or interact with their peers and mentors for social and reflective learning. Web 2.0 provides a collaborative and social interactive platform that allows learners to exchange, share, acquire, codify, distribute, and disseminate knowledge. Its functions and features are able to construct a virtual and distributed environment for learners to gather, filter and update the knowledge over different internet sources. This paper thus aims to discuss the functions and features of Web 2.0 technology and its applications to clinical training.

31 October 2025 in Electronics
Verified
Journal Article
Open access
PDF file
YWYun Wang
Yun Wang
LCLiege Cheung
Liege Cheung
PMPatrick Ma
Patrick Ma
HLHerbert Lee
Herbert Lee
ALAdela S.M. Lau
Adela S.M. Lau
One of the key limitations of AI chatbots is the lack of human-like nonverbal communication. Although there are many research studies on video or audio emotion recognition for detecting human emotions, there is no research that combines video, audio, and ontology methods to develop an AI chatbot with human-like communication. Therefore, this research aims to develop an audio-video emotion recognition model and an emotion-ontology-based chatbot engine to improve human-like communication with emotion detection. This research proposed a novel model of cluster-based audiovisual emotion recognition for improving emotion detection with both video and audio signals and compared it with existing methods using video or audio signals only. Twenty-two audio features, the Mel spectrogram, and facial action units were extracted, and the last two were fed into a cluster-based independent transformer to learn long-term temporal dependencies. Our model was validated on three public audiovisual datasets: RAVDESS, SAVEE, and RML. The results demonstrated that the accuracy scores of the clustered transformer model for RAVDESS, SAVEE, and RML were 86.46%, 92.71%, and 91.67%, respectively, outperforming the existing best model with accuracy scores of 86.3%, 75%, and 60.2%, respectively. An emotion-ontology-based chatbot engine was implemented to make inquiry responses based on the detected emotion. A case study of the HKU Campusland metaverse was used as proof of concept of the emotional AI chatbot for nonverbal communication.

26 September 2025
Verified
Book Chapter
Open access
CLChunhe Liu
Chunhe Liu
HPHewen Pan
Hewen Pan
LYLongxun Yang
Longxun Yang
YAYifan An
Yifan An
ZHZiwei Hu
Ziwei Hu
ALAdela S.M. Lau
Adela S.M. Lau
Existing healthcare chatbots suffer from diagnostic inaccuracy, poor context awareness, and reliance on static knowledge, leading to unsafe generic advice. We introduce a novel chatbot addressing these limitations. Our key contributions are: (1) A hybrid architecture combining BERT for query intent classification with a fine-tuned LLM for response generation; (2) Inclusion of Retrieval-Augmented Generation to dynamically access authoritative medical knowledge; and (3) A Gradio interface enabling user interaction. This approach significantly enhances response accuracy (alignment with medical facts), contextual relevance, and reliability (reducing model hallucinations). Evaluation shows a marked improvement over baselines: BLEU-4 increased from 14.8 to 27.5, and substantial gains in ROUGE-1 (19.7 to 25.6), ROUGE-2 (2.9 to 5.0), and ROUGE-L (9.3 to 16.1), demonstrating superior overall performance.

9 July 2026
Verified
Book Chapter
Open access
JCJinhong Chen
Jinhong Chen
ZFZeyu Fan
Zeyu Fan
YLYujia Liu
Yujia Liu
YWYining Wang
Yining Wang
ZXZhiyao Xu
Zhiyao Xu
ALAdela S.M. Lau
Adela S.M. Lau
This project presents an integrated Marketing Campaign Analysis and Decision Support System designed to transform unstructured social media data into actionable business intelligence. To address information overload, we propose a multi-stage NLP pipeline that identifies core customer concerns through advanced keyword extraction, topic modeling, and sentiment analysis. The system leverages a fine-tuned Twitter-RoBERTa transformer for high-precision sentiment classification, achieving a macro-F1 score of 0.9556, and employs a BERT-based architecture for Aspect-Based Sentiment Analysis (ABSA) to evaluate specific product features. Furthermore, ensemble predictive models forecast brand popularity trends with an Rš of approximately 0.90. Finally, these components are unified into an interactive Streamlit dashboard powered by a DeepSeek chatbot, enabling non-technical stakeholders to access multidimensional visualizations and automated strategic marketing plans.