Meladel Mistica

whoami

I am a cross-disciplinary researcher with academic and industry experience and expertise in Computational Linguistics, working in the field of Natural Language Processing (NLP). I joined the University of Melbourne in 2019, as a Post-doctoral Research Fellow at the School of Computing and Information System, Faculty of Engineering and Information Technology (CIS, FEIT). I joined the Melbourne Data Analytics Platform (MDAP) in 2021. Post-Ph.D., I had 5 years of industry experience in the USA – 4 years as a Software Engineer (Computational Linguist) at Intel Corporation headquarters in Silicon Valley; and 1 year holding a Staff Data Science position in a Search and Experience team.

• I work as a Research Data Specialist at the Melbourne Data Analytics Platform.
• I'm part of the Natural Language Processing group.
• I am also a Centre for Artficial Intelligence and Digital Ethics researcher.

Research Projects

Mitigating the Crumple Zone: Developing Ethical AI to Support Mental Health Discussion Forums

• This work is funded through CAIDE.
• It is work undertaken in partnership with SANE Australia.

Facilitating cognitive research in clinical environments

⊕Abstract from Mistica et al. (2024)Biases in the retrieval of personal, autobiographical memories are a core feature of multiple mental health disorders, and are associated with poor clinical prognosis. However, current assessments of memory bias are either reliant on human scoring, restricting their administration in clinical settings, or when computerized, are only able to identify one memory type. Here, we developed a natural language model able to classify text-based memories as one of five different autobiographical memory types (specific, categoric, extended, semantic associate, omission), allowing easy assessment of a wider range of memory biases, including reduced memory specificity and impaired memory flexibility. Our model was trained on 17,632 text-based, human-scored memories obtained from individuals with and without experience of memory bias and mental health challenges, which was then tested on a dataset of 5880 memories. We used 20-fold cross-validation setup, and the model was fine-tuned over BERT. Relative to benchmarking and an existing support vector model, our model achieved high accuracy (95.7%) and precision (91.0%). We provide an open-source version of the model which is able to be used without further coding, by those with no coding experience, to facilitate the assessment of autobiographical memory bias in clinical settings, and aid implementation of memory-based interventions within treatment services. This project was an MDHS faculty-funded collaboration with Dr. Caitlin Hitchcock.

MDAP Internships

I am the co-coordinator for the MDAP internship program. Students can undertake an internship at MDAP as part of their internship coursework.📝Contact mdap-info@unimelb.edu.au for all internship enquiries.

Students undertaking internships get to learn about real-world problems with researchers working in a spectrum of fields. Learn about MDAP's research projects.

Publications

Under Construction