Arpit Narechania
@arpitnarechania.bsky.social
Assistant Professor at HKUST. CS PhD from Georgia Tech. I build cool things leveraging data visualizations, human-computer interaction (HCI), and artificial intelligence (AI).
Website: https://narechania.com
Email: arpit@ust.hk
Website: https://narechania.com
Email: arpit@ust.hk
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!
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!
November 12, 2025 at 12:12 PM
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!
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!
You can read this dissertation at narechania.com/docs/arpit_n....
I particularly encourage you to read the Acknowledgements chapter to get to know everyone who played a part in this quest and how.
I particularly encourage you to read the Acknowledgements chapter to get to know everyone who played a part in this quest and how.
November 12, 2025 at 12:12 PM
You can read this dissertation at narechania.com/docs/arpit_n....
I particularly encourage you to read the Acknowledgements chapter to get to know everyone who played a part in this quest and how.
I particularly encourage you to read the Acknowledgements chapter to get to know everyone who played a part in this quest and how.
🙏 Big thanks to my coauthors: Alex Endert from the Georgia Tech Visualization Lab & Atanu R Sinha from Adobe Research.
📄 Paper: arxiv.org/abs/2502.00682
📹 Video Overview: youtu.be/ASgLVAljtHk
🎙️ Recorded Talk: youtu.be/eh1WVYl25Dk
(6/6)
📄 Paper: arxiv.org/abs/2502.00682
📹 Video Overview: youtu.be/ASgLVAljtHk
🎙️ Recorded Talk: youtu.be/eh1WVYl25Dk
(6/6)
April 3, 2025 at 4:30 PM
🙏 Big thanks to my coauthors: Alex Endert from the Georgia Tech Visualization Lab & Atanu R Sinha from Adobe Research.
📄 Paper: arxiv.org/abs/2502.00682
📹 Video Overview: youtu.be/ASgLVAljtHk
🎙️ Recorded Talk: youtu.be/eh1WVYl25Dk
(6/6)
📄 Paper: arxiv.org/abs/2502.00682
📹 Video Overview: youtu.be/ASgLVAljtHk
🎙️ Recorded Talk: youtu.be/eh1WVYl25Dk
(6/6)
🤔 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)
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)
April 3, 2025 at 4:30 PM
🤔 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)
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)
🥁 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)
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)
April 3, 2025 at 4:30 PM
🥁 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)
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)
💡 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)
We held the quality of guidance constant across all sources (7 relevant & 3 irrelevant recommendations, randomly sequenced)
(3/6)
April 3, 2025 at 4:30 PM
💡 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)
We held the quality of guidance constant across all sources (7 relevant & 3 irrelevant recommendations, randomly sequenced)
(3/6)
🎯 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. 🤖 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)
April 3, 2025 at 4:30 PM
🎯 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. 🤖 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)
Find more information about my work on my personal website at narechania.com
Find more information about the HKUST #CSE PhD program at cse.hkust.edu.hk/pg/admissions/
[2/2]
Find more information about the HKUST #CSE PhD program at cse.hkust.edu.hk/pg/admissions/
[2/2]
Arpit Narechania
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 Georgi...
narechania.com
January 19, 2025 at 6:31 AM
Find more information about my work on my personal website at narechania.com
Find more information about the HKUST #CSE PhD program at cse.hkust.edu.hk/pg/admissions/
[2/2]
Find more information about the HKUST #CSE PhD program at cse.hkust.edu.hk/pg/admissions/
[2/2]