Overview
Background
I am currently a senior lecturer and an ARC DECRA fellow at the University of Queensland, where I conduct research in the field of Information Retrieval. My research focuses on efficient and effective representations for large-scale search engines, including indexing, compression, and retrieval. I am also interested in understanding how to measure improvements in the end-to-end search pipeline, including system-oriented effectiveness measurements and user behaviour analysis. I have a broad interest in empirical experimentation, operating systems, data structures, and algorithms.
Previous Positions
- From February 2020 to January 2022 I worked as a postdoctoral research fellow on an ARC discovery project with Professor Alistair Moffat at the University of Melbourne.
- I completed my PhD at RMIT University under the guidance of Professor J. Shane Culpepper and Professor Falk Scholer.
Availability
- Dr Joel Mackenzie is:
- Available for supervision
- Media expert
Fields of research
Research interests
-
Efficient Data Structures and Algorithms
Inverted Indexes, Compression, Query Processing, Distributed Search, Parallel Processing, Data structures, Algorithms, Bioinformatics, Strings
-
Evaluating Search Systems
Empirical Experimentation, Metrics, Data Visualization, User Behaviour
Works
Search Professor Joel Mackenzie’s works on UQ eSpace
2017
Conference Publication
Early termination heuristics for score-at-a-time index traversal
Mackenzie, Joel, Scholer, Falk and Culpepper, J. Shane (2017). Early termination heuristics for score-at-a-time index traversal. ADCS 2017: The 22nd Australasian Document Computing Symposium, Brisbane, QLD Australia, 7-8 December 2017. New York, NY United States: Association for Computing Machinery. doi: 10.1145/3166072.3166073
2017
Conference Publication
A comparison of document-at-a-time and score-at-a-time query evaluation
Crane, Matt, Culpepper, J. Shane, Lin, Jimmy, Mackenzie, Joel and Trotman, Andrew (2017). A comparison of document-at-a-time and score-at-a-time query evaluation. 10th ACM International Conference on Web Search and Data Mining (WSDM), Cambridge, United Kingdom, 6-10 February 2017. New York, NY United States: Association for Computing Machinery. doi: 10.1145/3018661.3018726
2017
Conference Publication
Managing Tail Latencies in Large Scale IR Systems
Mackenzie, Joel (2017). Managing Tail Latencies in Large Scale IR Systems. 40th International ACM SIGIR conference on research and development in Information Retrieval, Shinjuku, Japan, 7-11 August 2017. New York, NY United States: Association for Computing Machinery. doi: 10.1145/3077136.3084152
2016
Conference Publication
RMIT at the TREC 2016 LiveQA Track
Mackenzie, Joel, Chen, Ruey-Cheng and Culpepper, J. Shane (2016). RMIT at the TREC 2016 LiveQA Track. 25th Text REtrieval Conference, TREC 2016, Gaithersburg, MD United States, 15 November 2016. Gaithersburg, MD United States: National Institute of Standards and Technology.
2015
Conference Publication
Efficient location-aware web search
Mackenzie, Joel, Choudhury, Farhana M. and Culpepper, J. Shane (2015). Efficient location-aware web search. ADCS '15: The 20th Australasian Document Computing Symposium, Parramatta, NSW Australia, 8-9 December 2015. New York, NY United States: Association for Computing Machinery. doi: 10.1145/2838931.2838933
Funding
Current funding
Supervision
Availability
- Dr Joel Mackenzie is:
- Available for supervision
Looking for a supervisor? Read our advice on how to choose a supervisor.
Supervision history
Current supervision
-
Doctor Philosophy
Efficient Next-Generation Information Retrieval Systems
Principal Advisor
Other advisors: Professor Shane Culpepper
-
Doctor Philosophy
Political Bias in Large Language Models: a Persona-based Perspective
Associate Advisor
Other advisors: Professor Gianluca Demartini
-
Master Philosophy
Advanced Query Feedback with Large Language Models for Effective and Robust Neural Ranking
Associate Advisor
Other advisors: Dr Teerapong Leelanupab
-
Doctor Philosophy
Human-centered verification of language model outputs
Associate Advisor
Other advisors: Professor Guido Zuccon, Professor Tim Miller
-
Doctor Philosophy
Understanding and Enhancing Health Information Access
Associate Advisor
Other advisors: Professor Guido Zuccon
-
Doctor Philosophy
From Auditing to Mitigation: The Role of Persona in Studying and Controlling Ideological Biases in Large Language Models
Associate Advisor
Other advisors: Professor Gianluca Demartini
-
Doctor Philosophy
Using Large Language Models to Improve Search andRecommendation
Associate Advisor
Other advisors: Professor Shane Culpepper
-
Doctor Philosophy
Using Large Language Models and Knowledge Graphs to Improve Search and Recommendation
Associate Advisor
Other advisors: Professor Shane Culpepper
-
Doctor Philosophy
Human-Centred Artificial Intelligence for Democracy
Associate Advisor
Other advisors: Professor Gianluca Demartini
Completed supervision
-
2023
Doctor Philosophy
Teaching Pre-trained Language Models to Rank Effectively, Efficiently, and Robustly
Associate Advisor
Other advisors: Professor Guido Zuccon
Media
Enquiries
Contact Dr Joel Mackenzie directly for media enquiries about:
- Big Data
- Data Science
- Data Structures and Algorithms
- Information Retrieval
- Search Algorithms
- Search Engines
- Web Search
Need help?
For help with finding experts, story ideas and media enquiries, contact our Media team: