Womin djeka! This is my personal—not an official RMIT—website. I’m a Senior Lecturer and DECRA Fellow at RMIT University (School of Computing Technologies), deputy director of the Research Centre for Information Discovery and Data Analytics (CIDDA), an Associate Investigator at the ARC Centre of Excellence for Automated Decision-Making and Society, and a research collaborator of RMIT FactLab.
My main research interests are Information Retrieval (IR), Text Analytics, and Data Science. I currently work on evaluation of information access systems and interactive information retrieval.
In my free time, I teach Capoeira at the Associação de Capoeira Descendente do Pantera (ACDP) –where I am also known as Contramestre Camaleão– and play samba with Wombatuque.
PhD in Computer Science, 2014
UNED (Madrid, Spain)
Senior Lecturer and DECRA Fellow, School of Computing Technologies
Deputy Director, Centre for Information Discovery and Data Analytics
Associate Investigator, Centre of Excellence for Automated Decision-Making and Society
Transform your future with a transnational joint PhD from two leading universities. Attractive scholarships available including funded travel to Melbourne, Australian stipend and overseas health cover.
Title. Enhancing computing education for the visually impaired using machine-generated code summaries (BITSRMIT100090)
Project Description. Visually impaired (VI) persons use screen readers that verbalise the text on a computer screen line-by-line. While a sighted developer can comprehend program code by glancing at pieces of code quickly, it is difficult for a VI developer to comprehend code by going line by line. Thus, the aim is to develop an AI-based assistive system helping to improve (Python) code comprehension for the VI developer. Sub-tasks: 1) develop a pseudocode generator providing a natural language description of the source code, 2) develop an AI-based code summarizer generating a compact summary improving the code comprehension, and finally 3) design and develop a Visual Studio code plug-in implementing the above-mentioned models. Experiments: For source code summary generation, we aim to use a multi-modal approach consisting of source code analysis, pseudocode analysis, and feedback quantification. We will employ a forest of abstract syntax trees to generate summaries. The pseudocode will be used to extract long-distance semantics, while feedback will extract lexical features from the text. We will validate our approach against human evaluation and statistical analysis. We will deploy the designed plug-in for real-world Python teaching-learning setups for the VI students. We will compare the code comprehension and programming abilities of VI students using our tool (treatment) and without using our tool (control group).
BITS Supervisors. Dr. Swati Agarwal, Dr. Swaroop Joshi
RMIT Supervisors. Dr Damiano Spina, Dr. Johanne R. Trippas
Opportunity to join the Centre of Excellence on Automated Decision-Making and Society (ADM+S) work on developing new approaches to fairness, actionable explainability or socially considerate evaluation of Automated Decision-Making in search, conversational, recommender, or other information access systems.
Dr. Ameer Albahem, Evaluating Dynamic Search Systems for Interactive Complex Tasks (co-supervised with Lawrence Cavedon and Falk Scholer).
Dr. Johanne R. Trippas, Spoken conversational search: audio-only interactive information retrieval (co-supervised with Lawrence Cavedon and Mark Sanderson).