top of page

Research Agenda

I am currently working on the following two research themes:

1. Automating Legal Compliance and Forensics with Artificial Intelligence: 

Artificial Intelligence-based solutions are necessary to address the challenges of ensuring regulatory compliance due to continuously changing regulations split in different silos in multiple jurisdictions. To automate legal compliance, the correct interpretation of legal norms by machines is necessary. Therefore, my research focuses on the development of legal information retrieval systems for compliance support by using natural language processing and machine learning technologies. In particular, I am interested in the development of compliance support tools to model the semantics of legal norms and identification of national transpositions of EU directives to assist legal practitioners for cross-border legal research. The following are some major publications related to this research theme:

2. Natural Language Processing (NLP) for a Fair and Inclusive Society:

The employment sector is critical to society because it determines who can access economic opportunities to support themselves and their families (Bogen and Rieke, 2018). Job seekers find themselves increasingly duped and misled by fraudulent job advertisements, posing a threat to their privacy, security and well-being. There is a clear need for solutions that can protect innocent job seekers. Existing approaches to detecting fraudulent jobs do not scale well, function like a black-box, and lack interpretability, which is essential to guide applicants’ decision-making. Hence, this research explores to what extent different categorizations of fraudulent jobs can be classified. In addition, we intend to find what type of features are most relevant in classifying the type of fraudulent job. We develop and validate a machine learning system for identifying identity theft, corporate identity theft and multi-level marketing amongst fraudulent job advertisements.

 

 

While recruiters would naturally want to be fair and transparent in making hiring decisions, empirical studies have shown that some factors do consciously or unconsciously subvert decision makers’ objectivity (Bendick Jr and Nunes, 2013; Bertrand and Mullainathan, 2004; Gaucher et al., 2011).  Most discrimination activities appear early but subtly in the hiring process, for instance, exclusive phrasing in job advertisement discourages qualified applicants from minority groups from applying.  The existing works are limited to analysing, categorizing and highlighting the occurrence of bias in the recruitment process. In our research, we go beyond this and develop machine learning models for identifying and classifying biased and discriminatory language in job descriptions. We develop and evaluate a machine learning system for identifying five major categories of biased and discriminatory language in job advertisements.  We utilized the combination of linguistic features with recent state-of-the-art word embeddings representations as input features for various machine learning classifiers.

bottom of page