Khandaker Abrar Nadib

Salt Lake City, UT

I’m a 2nd Year PhD Student at the University of Utah, Kahlert School of Computing, based in Salt Lake City, Utah. I am currently co-advised by Prof. Alexander Lex and Prof. Marina Kogan and work with the Visualization Design Lab and the KORE Lab. I study how people interpret and disseminate charts and data in interactive, online environments. My work sits at the intersection of Information Visualization, Human-Computer Interaction (HCI), and Human-Centered Data Science.

Please visit my Google Scholar profile to see my publications.

Formerly, I have worked as a Full Stack Software Engineer at Optimizely and have three years of experience. I graduated from Bangladesh University of Engineering and Technology (BUET) with a BSc in Computer Science and Engineering.

Complementing my scholarly pursuits, I am passionate about films, competitive FPS gaming, and photography.

You can view/download my complete CV here.

Publications

ReVISit 2: A Full Experiment Life Cycle User Study Framework

Zach Cutler, Jack Wilburn, Hilson Shrestha, and 7 more authors

IEEE Transactions on Visualization and Computer Graphics (Proceedings of IEEE VIS), 2025

Best Paper Award
Interaction Based Credibility Analysis of News on Facebook Using Machine Learning Methodologies

Sadia Sharmin, Sudipa Saha, Tasin Hoque, and 1 more author

In 16th International Conference on Signal Image Technology & Internet Based Systems (SITIS), 2022

Abs

Fake news and its dissemination are growing more popular as social media becomes more pervasive in our daily lives and Facebook users are particularly vulnerable. Numerous studies on detecting fake news have already been published. However, a study focusing on fake news in low resource languages like Bengali propagated through Facebook is rare due to data extraction challenges. In this paper, we work with fake news in the Bengali language and used various supervised machine learning algorithms to classify Facebook posts as fake, real, or satire and found XGBoost to generate the best outputs. Instead of the content, we trained our model with the interaction data of the posts to make it resilient against adversarial attacks. We observed that ensemble methods perform well with such social media metrics.