A5010637098- Sentiment Analysis and Opinion Mining
- Topic Modeling
- Advanced Text Analysis Techniques
- Gene Regulatory Network Analysis
- Bioinformatics and Genomic Networks
- RNA and protein synthesis mechanisms
- Text and Document Classification Technologies
- Natural Language Processing Techniques
- Gene expression and cancer classification
- Genomics and Phylogenetic Studies
- Anxiety, Depression, Psychometrics, Treatment, Cognitive Processes
- Misinformation and Its Impacts
- Anomaly Detection Techniques and Applications
- Advanced Image Processing Techniques
- Generative Adversarial Networks and Image Synthesis
- Speech and dialogue systems
- Mindfulness and Compassion Interventions
- Time Series Analysis and Forecasting
- Face and Expression Recognition
- Metaheuristic Optimization Algorithms Research
- Microbial Metabolic Engineering and Bioproduction
- Emotion and Mood Recognition
- Speech and Audio Processing
- Neural Networks and Applications
- Educational Games and Gamification
James Cook University
2020-2024
Nanyang Technological University
2010-2023
Nanyang Institute of Technology
2007
Technology has enabled anyone with an Internet connection to easily create and share their ideas, opinions content millions of other people around the world. Much being posted consumed online is multimodal. With billions phones, tablets PCs shipping today built-in cameras a host new video-equipped wearables like Google Glass on horizon, amount video will only continue increase. It become increasingly difficult for researchers keep up this deluge multimodal content, let alone organize or make...
Building dialogue systems that can converse naturally with humans is a challenging yet intriguing problem of artificial intelligence. In open-domain human-computer conversation, where the conversational agent expected to respond human utterances in an interesting and engaging way, commonsense knowledge has be integrated into model effectively. this paper, we investigate impact providing about concepts covered dialogue. Our represents first attempt integrating large base end-to-end models....
Noninvasive on-skin electrodes record the electrical potential changes from human skin, which reflect body condition and are applied for healthcare, sports management, modern lifestyle. However, current have poor conformal properties under sweaty in real-life because of decreased electrode-skin adhesion with sweat film at interface. Here, we fabricated biocomposite based on silk fibroin (SF) through interfacial polymerization, is applicable skin. Interfacial polymerized conductive...
The advent of the Social Web has provided netizens with new tools for creating and sharing, in a time- cost-efficient way, their contents, ideas, opinions virtually millions people connected to World Wide Web. This huge amount information, however, is mainly unstructured as specifically produced human consumption and, hence, it not directly machine-processable. In order enable more efficient passage from information structured data, aspect-based opinion mining models relations between...
The proliferation of Web 2.0 technologies and the increasing use computer-mediated communication resulted in a new form written text, termed microtext. This poses challenges to natural language processing tools which are usually designed for well-written text. paper proposes phonetic-based framework normalizing microtext plain English and, hence, improve classification accuracy sentiment analysis. Results demonstrated that there is high (>0.8) similarity index between tweets normalized by...
Building dialog agents that can converse naturally with humans is a challenging yet intriguing problem of artificial intelligence. In open-domain human-computer conversation, where the conversational agent expected to respond human responses in an interesting and engaging way, commonsense knowledge has be integrated into model effectively. this paper, we investigate impact providing about concepts covered dialog. Our represents first attempt integrating large base end-to-end models....
Objective sentences lack sentiments and, hence, can reduce the accuracy of a sentiment classifier. Traditional methods prior to 2001 used hand-crafted templates identify subjectivity and did not generalize well for resource-deficient languages such as Spanish. Later works published between 2002 2009 proposed use deep neural networks automatically learn dictionary features (in form convolution kernels) that is portable new languages. Recently, recurrent are being model alternating subjective...
Abstract The use of computer‐mediated communication has resulted in a new form written text called Microtext, which is very different from well‐written text. Most previous approaches deal with microtext at the character level rather than just words resulting increased processing time. In this paper, we propose to transform static word vectors dynamic by modelling effect neighbouring and their sentiment strength AffectiveSpace. To evaluate approach, crawled Tweets diverse topics human...
Subjectivity detection aims to distinguish natural language as either opinionated (positive or negative) neutral. In word vector based convolutional neural network models, a meaning is simply signal that helps classify larger entities such document. Previous works do not usually consider prior distribution when using sliding windows learn embedding's and, hence, they are unable capture higher-order and long-range features in text. this paper, we employ dynamic Gaussian Bayesian networks...
The continuous sophistication in clinical informationprocessing motivates the development of a dictionary likeWordNet for Medical Events order to convey valuableinformation (e.g., event definition, sense based contextualdescription, polarity etc.) experts (e.g. medicalpractitioners) and non-experts patients) their respective fields. present paper reports enrichment medical terms such as identifying describing events, times relations between them text by employing three different lexical...
There is a large variety of products sold online and the websites are in several languages. Hence, it desirable to train model that can predict sentiments different domains simultaneously. Previous authors have used deep learning extract features from multiple domains. Here, each word represented by vector determined using co-occurrence data. Such requires all sentences same length resulting low accuracy. To overcome this challenge, we sentence variable tree called Genetic Program. The...
Video conferencing has enabled synchronous communication in a classroom and created multi-sensory content to stimulate learners. Artificial intelligence involves complex equations that are better taught using constructive pedagogy where students experiment with alternative ways of solving the same problem. Multiple-choice questions have high reliability can easily reveal student skill levels quick way. The Australian Computer Society accreditation exercise ensures for each subject serves as...