Dr Ahmed Izzidien

Interests: Artificial intelligence in the legal domain, machine learning for legal analysis, legal philosophy and its operationalisation in the digital domain. 

Publications: (Related to:The digitisation of law)

Izzidien, A., Sargeant, H., & Steffek, F. (2024).LLM vs. Lawyers: Identifying a Subset of Summary Judgments in a Large UK Case Law Dataset. arXiv:2403.04791. arXiv. Available at: http://arxiv.org/abs/2403.04791

Izzidien, A. (2023). Using the interest theory of rights and Hohfeldian taxonomy to address a gap in machine learning methods for legal document analysis. Humanities and Social Sciences Communications, 10(1), Article 1. https://doi.org/10.1057/s41599-023-01693-z

Izzidien, A., Sargeant, H., & Steffek, F. (2022). What goes on in court? Identifying contract-related topics decided by United Kingdom courts from 1709 to 2021 using machine learning. Cambridge Open Engage. https://doi:10.33774/coe-2022-p7rjg-v2 

Izzidien, A., Fitz, S., Romero, P. et al. (2022) Developing a sentence level fairness metric using word embeddings. Int J Digit Humanities. https://doi.org/10.1007/s42803-022-00049-4

Izzidien, A. (2022). Word vector embeddings hold social ontological relations capable of reflecting meaningful fairness assessments. AI & SOCIETY, 37(1), 299–318. https://doi.org/10.1007/s00146-021-01167-3

Izzidien, A. (2021, November 15). The Limits of Annotation in Machine Learning a Documents Hohfeldian Legal Entities [Poster session]. Cambridge Language Sciences Symposium, Cambridge, UK. https://doi.org/10.33774/coe-2021-dqwvg

Izzidien, A., & Stillwell, D. (2021). The Golden Rule as a Heuristic to Measure the Fairness of Texts Using Machine Learning. ArXiv:2111.00107 [Cs]. http://arxiv.org/abs/2111.00107

Izzidien, A., & Chennu, S. (2018). A Neuroscience Study on the Implicit Subconscious Perceptions of Fairness and Islamic Law in Muslims Using the EEG N400 Event Related Potential. Journal of Cognition and Neuroethics, 2(5)

Reviewer: 

Humanities and Social Sciences Communications, Springer Nature, nature.com/palcomms/

The Research Council of Norway (Grant Applications on AI & Law)

Academic Education: 

The University of Cambridge (MPhil), King's College London (BEng), MC-UCLA (Faculty of Law) (MA), University of Manchester Institute of Technology (MSc), Cardiff University (PhD).

Awards-Grants received [as a Co-Investigator or Research Associate]:

The Nuffield Foundation (Justice). Predicting the outcome of Summary Judgment cases using machine learning.
The Psychometrics Centre Research Grant, University of Cambridge. Developing a digital fairness metrics for texts. 
Cambridge Humanities Research Grants Scheme. Using artificial intelligence to predict and avoid legal conflict in contracts.
The Isaac Newton Trust Award, University of Cambridge. Developing a fairness metric for artificial intelligence.
Language Sciences Incubator Fund, University of Cambridge. Predicting and mitigating contract clause conflict using artificial intelligence.
Cambridge Judge Business School Small Research Grant Award. Developing a digital fairness metrics for texts.
Horizon 2020 NGI Trust Award (Type I). Human-centric artificial intelligence to enable fairness assessments of texts.
Horizon 2020 NGI Trust Award (Type II). Human-centric artificial intelligence to enable fairness assessments of texts.
 

Posts: (Prior)

The University of Cambridge, The Psychometrics Centre, Research Associate. 
The University of Cambridge, Social Decision-Making Lab, Senior Research Affiliate. 
The University of Cambridge, Cambridge Forum for Legal & Political Philosophy, Faculty of Law, Visiting Researcher. 
Harvard University, Social Cognition Laboratory. Visiting Post-doctoral Research Assistant.
The University of South Wales, Post-doctoral Research Assistant.

Activities:

Script writing (comedy, science fiction)  Confusions of a Gentleman: Seeking witty exits. Amazon, 2021.

Current Works:

Izzidien, A., Sargeant, H., & Steffek, F. (2024) Using graph neural networks to represent cases for outcome prediction and counterfactual analysis.
Izzidien, A., Sargeant, H., & Steffek, F. (2024) Representing cases using directed acyclic graphs to capture juridical chain-of-thought processes.