Who we are

Profile picture of Aritra Dasgupta
Aritra Dasgupta
Assistant Professor
Profile Picture of Jun Yuan
Jun Yuan
PhD Candidate
Profile Picture of Vrushali Koli
Vrushali Koli
PhD Student
Profile Picture of Kaustav Bhattacharjee
Kaustav Bhattacharjee
PhD Candidate
Profile Picture of Akm Islam
Akm Islam
University Lecturer

Research Philosophy

We are a group of data toolsmiths who develop and study the role of visualization techniques as a transparent lens between what is computed from data and what is communicated to the human mind.

As George Bernard Shaw so eloquently said: “The single biggest problem in communication is the illusion that it has taken place.”  This is oh-so-evident in today’s age, where, information, if communicated properly, can cure diseases and fuel discoveries, but, if miscommunicated, can lead to an “infodemic” in the worst-case scenario.

To solve this conundrum, at NiiV, we pursue intelligibility as the foundational principle for making information more accessible, meaningful, and actionable to experts (e.g., doctors, climate scientists) and non-experts alike.

We operationalize this principle by visualizing data, big or small, with the ultimate goal of letting human observers see, understand, and trust the information that is often generated by black-box algorithms.

By embracing a human-centered data science approach that ultimately culminates in interactive visual analytic interfaces, we preserve the best of both worlds: the power of computational methods and that of human judgment and reasoning.

Research Highlights

Explainable AI for Algorithmic Rankers
highlight 1

A Human-in-the-loop Workflow for Multi-Factorial Sensitivity Analysis of Algorithmic Rankers [HILDA 2023]

TRIVEA: Transparent Ranking Interpretation using Visual Explanation of Black-Box Algorithmic Rankers [Visual Computer 2023]

Privacy-aware Data Discovery
highlight 3

PRIVEE: A Visual Analytic Workflow for Proactive Privacy Risk Inspection of Open Data [VizSec 2022]

VALUE: Visual Analytics driven Linked data Utility Evaluation [HILDA 2023]

Transparent AI-driven Decision Making
highlight 2

Beyond Visual Analytics: Human-Machine Teaming for AI-Driven Data Sensemaking [VIS 2021]

Introducing contextual transparency for automated decision systems [Nature 2023]

Design and Analysis of Communicative Visualization
highlight 4

Visful thinking: Towards a Visual Reasoning Framework for Communicating with Data, Aritra Dasgupta  [Outlier 2023]

Conceptualizing Visual Analytic Interventions for Content Moderation  [VIS 2021]

Lab updates

Apr ’24: Bhattacharjee's poster won the best poster prize at NYC Privacy Day .

Feb ’24: Bhattacharjee's paper published at IEEE ISGT NA 2024 conference

Nov ’23: Yuan's paper accepted at XAI In Action workshop at NeurIPS 2023

Sep ’23: Dasgupta receives DOE CESER grant via PNNL

Aug ’23: Bhattacharjee delivered lightning talk at SOUPS

Aug ’23: Dasgupta awarded NSF Future of Work grant

Jul ’23: Dasgupta awarded NSF IIS grant

Jun ’23: Yuan and Bhattacharjee presented 2 papers at HILDA

Jun ’23: Dasgupta awarded DOE HELM grant via PNNL

Mar ’23: Yuan and Dasgupta published at Nature Machine Intelligence

Feb ’23: Dasgupta awarded research grant from Explorance

Feb ’23: Bhattacharjee presented paper at USEC

Jan ’23: Bhattacharjee continues internship at PNNL for Spring and summer '23

Research Areas

Explainable AI for Algorithmic Rankers

Unravel factors influencing black-box ranking models through visual analytic explanations.

Transparent AI-driven Decision Making

Apply visualization and artificial intelligence techniques for high-consequential decision-making.

Privacy-aware Data Discovery

Develop visual analytic workflows to discover joinable open datasets that can lead of disclosure of sensitive information.

Design and Analysis of Communicative Visualization

Study the role of communicative visualization in data and domain sciences.


class="wow fadeIn"

Contact us

Get in touch with us here

  • 218 Central Ave, Newark, NJ, USA - 07102

  • aritra.dasgupta@njit.edu

  • Open Positions