This page contains links to my scientific publications.

[2022] Data Smells in Public Datasets

Python, Pandas, Matplotlib, org-mode

The adoption of Artificial Intelligence (AI) in high-stakes domains such as healthcare, wildlife preservation, autonomous driving and criminal justice system calls for a data-centric approach to AI. Data scientists spend the majority of their time studying and wrangling the data, yet tools to aid them with data analysis are lacking. This study identifies the recurrent data quality issues in public datasets. Analogous to code smells, we introduce a novel catalogue of data smells that can be used to indicate early signs of problems or technical debt in machine learning systems. To understand the prevalence of data quality issues in datasets, we analyse 25 public datasets and identify 14 data smells.



[2019] ACE: Art, Color and Emotions

JavaScript, D3.js

Art has been the cornerstone of human expression and social progress through time. It is no wonder that art historians and daily enthusiasts alike have spent countless hours trying to understand more than what meets the eye. What an individual can draw from a painting is very subjective, but we now know that human mind has a high sensibility for well-defined subset of traits - one of them being colour. This paper describes the process of bringing a new light on how colours and emotional tone (sentiment) can be interlaced with one another. This is achieved with the use of widespread artificial intelligence techniques, a vast dataset of art meta-data(OmniArt) and state-of-the-art visual interaction tools.


  title     = {Ace: Art, color and emotion},
  author    = {Strezoski, Gjorgji and Shome, Arumoy and Bianchi, Riccardo and Rao, Shruti and Worring, Marcel},
  booktitle = {Proceedings of the 27th ACM International Conference on Multimedia},
  pages     = {1053--1055},
  year      = {2019}