Naimul Hoque

Seminar - Naimul Hoque,

HCILab, University of Maryland

Supporting Complex Creative Writing Tasks with AI-powered Data Visualization

Tues 30th May, 12:30 - 13:30, ELG02 (Drysdale) & Teams

Abstract:

Writing is a fundamental human activity—but today we have the opportunity to leverage Natural Language Processing (NLP) methods to help in this endeavour.

Recent tools go beyond mere spelling and grammatical support to the use of Large Language Models (LLMs) to support human-AI co-writing. While existing tools are helpful, it is still unknown how to best apply NLP to more complex and abstract narrative components such as characterisation, dialogue, and narrative structures, and how that can help writers—as well as the fans and scholars reading their work.

In this talk, Naimul will demonstrate how NLP and interactive visualizations can be combined to help writers design complex narrative components and reveal hidden patterns while revising a draft. Two case studies will be presented, one on mitigating social biases in fiction writing and one on the design of characterisation. Naimul will conclude by outlining the broader impact of his work on human-AI co-writing.

Bio:

Naimul Hoque is a Ph.D. candidate at the College of Information Studies (iSchool), University of Maryland, College Park, where he works with Professor Niklas Elmqvist in the renowned Human-Computer Interaction Lab.

His research interest is designing data representations that people with diverse needs and capabilities can use to interact with AI beneficially. This typically results in novel interactive systems, data visualization, and data sonification techniques for promoting creativity, learning, and sensemaking.

Naimul obtained a Master's in Computer Science from Stony Brook University in 2020 and a B.Sc in Computer Science from the University of Dhaka, Bangladesh in 2015. He has presented work at CHI, VIS and DIS during his PhD.

Hello Mai!

We welcome Mai Elshehaly as a Lecturer in Visualisation at the giCentre.

Mai designs, develops and evaluates visual analytics for population health management with a particular interest in the role of routine data and digital footprints in decision-making.

An Honorary Senior Research Fellow at the Wolfson Centre for Applied Health Research, Mai leads the visualisation stream at the Yorkshire and Humber Patient Safety Research Centre. She works closely with colleagues at local authorities and several partner organisations to deliver data literacy to over 30,000 young citizens in Bradford.

Mai received a PhD in Computer Science from the Center for Human-Computer Interaction at Virginia Tech, with a focus on scientific data visualisation. Her postdoctoral  research experience included NSF- and NIHR-funded fellowships at the University of Maryland, Baltimore County and University of Leeds.

Check Mai’s publications to find out more about her exciting work in visualization and public health.

Narges Mahyar & Ali Sarvghad

Seminar - Narges Mahyar & Ali Sarvghad,

University of Massachusetts (UMass) Amherst

Designing and Building Tools for Fostering Equity and Inclusion in Civic Decision-Making

Thurs 8th December, 16:00 - 17:30, ELG04 (Drysdale)

RisingEMOTIONS - capturing public emotion in response to seal level rise and flooding.

Narges Mahyar and Ali Sarvghad are doing exciting work in building tools that help communities solve real-world sociotechnical problems at the HCI-VIS Lab at UMass Amherst. They have received Best paper and Hon Mention awards at many of the major conferences in the last year or two. They will be heading here from their trip to INRIA Paris to give a talk and start a discussion on Visualization for Equity, Inclusion and Civic Decision-Making.

Please come along. Details and Bios here!

Abstract

Inclusive community engagement is paramount for fair and impartial civic decision-making. However, traditional methods rarely provide opportunities for inclusive public participation. While advances in digital civics have broadened public participation, these technologies still face several challenges in promoting inclusive participation and integrating data analysis into civic decision-making processes.

In this talk, Narges and Ali present examples of their recent work on building and studying community-centered tools for fostering equity and inclusion in civic decision-making by :

1. lowering barriers for public participation,

2. enriching data collection, and

3. facilitating more inclusive public input analysis.

They describe their vision for expanding our research on democratizing civic decision-making processes and outcomes by building, deploying, and studying socially impactful technologies that integrate data visualization, social computing, and artificial intelligence.