Iffat Maab

　

The University of Tokyo

Personally, I am driven by a deep passion for both academia and social service. My focus on building friendly ties with my social circle has equipped me to flexibly work in multitude of environments. I worked as a president of Pakistan Student Association Japan (PSAJ) during my first year of PhD where I managed advising services to all Pakistani students and hold different events like research seminars and farewell functions. Before coming to Japan, I stayed as a university lecturer for four years and developed strong communication skills by adapting different teaching styles I have done multiple internships in Japan related to AI, in addition I have also worked with advertising agency to write content about data science. I have worked for four years with Pink Ribbon Organization, Pakistan as a focal person to raise funds and awareness of breast cancer programs.

An Effective Approach for Informational and Lexical Bias Detection

In this paper we present a thorough investigation of automatic bias recognition on BASIL, a dataset of political news which has been annotated with different kinds of biases. We begin by unveiling several inconsistencies in prior work using this dataset, showing that most approaches focus only on certain task formulations while ignoring others, and also failing to report important evaluation details. We provide a comprehensive categorization of these approaches, as well as a more uniform and clear set of evaluation metrics. We argue about the importance of the missing formulations and also propose the novel task of simultaneously detecting different kinds of biases in news. In our work, we tackle bias on six different BASIL classification tasks in a unified manner. Eventually, we introduce a simple yet effective approach based on data augmentation and preprocessing which is generic and works very well across models and task formulations, allowing us to obtain stateof-the-art results.

 

 

Clustering probabilistic graphs using neighbourhood paths

 

 

Probabilistic graphs have gained much interest in the data mining community since the big data revolution. Our work exploits Graph clustering principle and explores the paths between nodes (including those of multiple order) to provide an estimate of the similarity between nodes with probabilistic edges. We embed this information into the fitness function and use Genetic algorithm to optimize the solution. The algorithm is tested on several benchmark datasets and compared with recent state-of-the-art algorithms.