Arpit Narechania
@arpitnarechania
Followers
398
Following
990
Media
35
Statuses
232
Assistant Prof @HKUSTCSE @HKUST. CS PhD @gtcomputing. I study data visualization & HCI, in particular human AI collaborative guidance systems.
Mumbai ⇄ Atlanta ⇄ Hong Kong
Joined March 2016
🏆 Incredibly honored to receive the 2025 IEEE VGTC Visualization Dissertation Award for my Ph.D. thesis titled "Designing, Developing, and Democratizing Guidance for Visual Analytics." I accepted this award at the #ieeevis conference last week in Vienna.
1
2
8
0
0
0
I received my Ph.D. in Computer Science from the Georgia Tech Visualization Lab, where I was advised by Dr. Alex Endert. I am now an Assistant Professor at HKUST, where I direct the DataVisards lab. We "build cool tools" using visual analytics, HCI, and AI. Come join us!
1
0
0
You can read this dissertation at https://t.co/qJY7iubYYh. I particularly encourage you to read the Acknowledgements chapter to get to know everyone who played a part in this quest and how.
1
0
0
Checkout Exploropleth - our latest #GIS #dataviz tool! 🎯Simultaneously explore & compare 16+ data binning methods on a choropleth #map, in your browser! 🎓Teach & learn how choropleth maps can be used to mislead people! https://t.co/26S6WrOni2 w/ @Friendly_Cities @EndertAlex
New article! A fantastic new tool Exploropleth: exploratory analysis of data binning methods in choropleth maps https://t.co/NAIxZwarej
#GISchat Check out their website https://t.co/Vta6W8SWFd and video of the tool in action: https://t.co/vjQ6dEUxLQ
@GT_Vis @DataVisards
0
1
3
From Hokie🦃 to Yellow Jacket🐝! @VT_CS recognized @EndertAlex with its 2025 Distinguished Early Career Alumni Award. Alex has been with us for 12 years, and this award recognizing his achievements is well-deserved! @gtcomputing @virginia_tech
https://t.co/kWQuMEXghC
cc.gatech.edu
0
1
10
And that's a wrap! The workshop concluded with an engaging panel discussion covering different aspects of agentic AI from provenance and explaiability to trust and human interaction. A huge thanks to the panelists @estevamhruschka @arpitnarechania @kbeedkar & Ziawash Abedjan.
@eserkandogan @TUBerlin [4/n] We also have an exciting panel where the keynote spearkers will be joined by @estevamhruschka, @arpitnarechania, and @kbeedkar to discuss opportunities and challenges in developing scalable, responsible, and reliable application of agentic systems.
0
2
3
Come join us tomorrow at the First Workshop on Data-AI Systems (DAIS), alongside #ICDE2025 at Hong Kong PolyU. Thanks for the invitation to be a panelist and session chair, @subZero_saj and @MegagonLabs!
0
1
3
I am seeking 1-2 PhD students and 1-2 postdocs to work on theory in HCI, say, how the field uses theory, how to make theories more impactful in HCI, and how to develop better technology w theory. DL is June 9th, see https://t.co/gu3rYOS8nZ and https://t.co/VsptVbJGzX. 🙏 🇩🇰🎓😃
5
76
228
🙏 Big thanks to my coauthors: Alex Endert from the Georgia Tech Visualization Lab & Atanu R Sinha from Adobe Research. 📄 Paper: https://t.co/3vkdg2NGDF 📹 Video Overview: https://t.co/kbRRsW9Kr4 🎙️ Recorded Talk: https://t.co/lUQUyGYGBJ (6/6) @EndertAlex @GT_Vis @ACMIUI
0
0
0
🤔Interestingly, participants in the 🤖AI condition reported both higher post-task benefit & regret. This highlights the importance of understanding how different guidance sources impact user behavior (espec. AI), which can help design more effective guidance systems! (5/6)
1
0
0
🥁The result? Guidance Source Matters! Participants utilized guidance differently during analysis, including expressing varying levels of regret, even when its quality was constant! E.g., those receiving guidance selected a lot more attributes than those without it! (4/6)
1
0
0
💡Participants could request guidance from their assigned guidance source, in the form of attribute recommendations, one by one, up to 10 times. We held the quality of guidance constant across all sources (7 relevant & 3 irrelevant recommendations, randomly sequenced). (3/6)
1
0
0
🎯We conducted a study with 5 conditions: 1 🤖AI 2 🧙Human Expert 3 🧑🤝🧑Group of Analysts 4 💡Unattributed Guidance (no source attribution) 5 ❌No Guidance (control) We tasked participants to analyze a dataset, select relevant attributes & make #dataviz for a biz report. (2/6)
1
0
0
❓Do people’s perception & utilization of guidance change during analysis if they know its source, e.g., if it came from 🤖AI, 🧙Human Expert, or 🧑🤝🧑Group of Human Analysts? ✨Thrilled to share our new #iui2025 paper, presented last week at ACM IUI in Cagliari, Italy. (1/6)
1
1
4
Excited to share our upcoming IUI paper called "A Design Space of Behavior Change Interventions for Responsible Data Science" -- we look at how behavior change theories from cognitive and clinical psych can inform responsible data science. 📖Read it here:
0
2
15
Find more information about my work on my personal website at https://t.co/LK1gYNSEF3 Find more information about the HKUST #CSE PhD program at https://t.co/SNxnQMp2IJ [2/2]
narechania.com
Hi, I am Arpit Narechania. I am an Assistant Professor in the Computer Science and Engineering department at The Hong Kong University of Science and Technology (HKUST). I received my Ph.D. from...
0
0
1
The students in our fall Data Visualization course created a great set of projects again. Topics included hip-hop music, fish populations, the Office TV show, MLB rules, national parks, UFOs, climate change, and many other. Website: https://t.co/fz7OWNPFDO
0
5
12