Huizhi Liang, Elly

• Postdoctoral Research

1. Australian CRC Project: Multi-Channel Content Delivery and Mobile Personalization (Queensland University of Technology, 2011)
2. Australian ARC  Linkage Project: Exposing the Anonymous Attacker: Detecting Identity Crimes using Real-Time Entity Resolution on Large Dynamic Databases (The Australian National University, 2012-2014)
3. Australian ARC Linkage Project: Personalised Topic Modelling and Sentiment Analysis for Enhanced Information Discovery over Document Streams (The University of Melbourne, 2014-2016)
4. LIP6: Representation Learning and Deep Learning (Pierre et Marie Curie University, 2016- )

• Research Visit

1. The National Institute of Advanced Industrial Science and Technology (AIST), Japan, September 2016
2. Summer School of Institute of Neuroscience, Chinese Academy of Sciences, China, August 2016
3. Tensent Shenzhen, China, May 2016

• Internship Project

Project Title: Paralleled User Profiling in Web 2.0 Using MapReduce (PDF|IEEE), Jan-March 2010 (one of the 3 winners out of 23 applications of Australia)

Sponsor: Intern of HPC Group of QUT, sponsored by Cloud Computing Internship and Competition Project of ATSE

Supervisor: A/Prof. Jim Hogan

Abstract: This Project implemented an efficient parallel user profiling approach and a scalable recommender system. The current advanced cloud computing techniques such as Hadoop, MapReduce, and Cascading were used. The experiments were conducted on Amazon EC2 Elastic MapReduce clouds and S3 with a real world large scaled dataset from Del.icio.us website.

•  Doctoral Research

Thesis Title: User Profiling based on Folksonomy Information in Web 2.0 for Personalized Recommender Systems (PDF)

Supervisors: A/Prof. Yue Xu, Prof.Yuefeng Li and A/Prof. Richi Nayak

Citation: This thesis proposed novel approaches to use the emerging user information in Web 2.0 to help users solve the information overload issue. The user created content description and classification information–Folksonomy was used to find users’ interests. Based on users’ interest profiles, personalized recommendations can be generated for each user. This thesis contributes to effectively use the wisdom of crowds to provide more accurate user profiling and recommendation approaches.

Awards: nominated as University Outstanding Thesis of QUT.