Bhavya Chopra
Research Fellow, Microsoft
Contact: bhavyacind@gmail.com
CV |
Google Scholar |
Twitter |
LinkedIn |
GitHub
Hello! I am Bhavya Chopra, a pre-doctoral Research Fellow with the PROSE Team at Microsoft, advised by Dr. Austin Z. Henley. I completed my bachelors in Computer Science and Design engineering (with honors) from IIIT-Delhi in 2022.
My research interests lie in Human-Computer Interaction (HCI), Human-AI Interaction, and Software Engineering. I am interested in exploring and conducting mixed-methods research to design systems for end-users and developers. My recent research, advised by Dr. Austin Z. Henley, Dr. Chris Parnin, Dr. Anna Fariha, and Dr. Ashish Tiwari, focuses on uncovering challenges in conversational and recommendation based AI systems for data science tasks. Currently, I am leveraging our research findings to design productive human-AI experiences for Excel.
Prior to my current role, I worked in accessibility design with Prof. Richa Gupta to design an inclusive and frugal storytelling interface for children with blindness and visual impairment. I pursued my bachelor thesis under the guidance of Prof. Rahul Purandare, where I used program analysis techniques to understand how developers make use of assertions in Java open-source repositories.
Publications
Exploring Interaction Patterns for Debugging: Enhancing Conversational Capabilities of AI-assistants
Bhavya Chopra*, Yasharth Bajpai*, Param Biyani, Gustavo Soares, Arjun Radhakrishna, Chris Parnin, Sumit Gulwani (*-Equal Contribution)
[arXiv Report]
[pdf]
Conversational Challenges in AI-Powered Data Science: Obstacles, Needs, and Design Opportunities
Bhavya Chopra, Ananya Singha, Anna Fariha, Sumit Gulwani, Chris Parnin, Ashish Tiwari, Austin Z. Henley
[arXiv Report]
[pdf]
🏆 Semantically Aligned Question and Code Generation for Automated Insight Generation
Ananya Singha, Bhavya Chopra, Anirudh Khatry, Sumit Gulwani, Austin Z. Henley, Vu Le, Chris Parnin, Mukul Singh, Gust Verbruggen
LLM4Code Workshop, ICSE '24 • Best Paper Award
[pdf]
🏆 Detangler: Helping Data Scientists Explore, Understand, and Debug Data Wrangling Pipelines
Nischal Shrestha, Bhavya Chopra, Austin Z. Henley, Chris Parnin
VL/HCC '23 • Best Paper Award
[pdf] [doi]
CoWrangler: Recommender System for Data Wrangling Scripts
Bhavya Chopra, Anna Fariha, Sumit Gulwani, Austin Z. Henley, Daniel Perelman, Mohammad Raza, Sherry Shi, Danny Simmons, Ashish Tiwari
SIGMOD '23 Demonstration
[pdf] [doi] [poster]
Study of Assertions: Understanding Assertion Use in Java Projects on GitHub
Bhavya Chopra
Bachelor Thesis, IIIT-Delhi
[pdf] [poster]
StoryBox: Independent Multi-modal Interactive Storytelling for Children with Visual Impairment
Bhavya Chopra, Richa Gupta
CHI '22 Late-Breaking Work
[pdf] [doi] [video] [poster]
🥈 Reality Tales: Facilitating User-Character Interaction with Immersive Storytelling
Bhavya Chopra*, Khushali Verma*, Sonali Singhal*, Utsav Singla* (*-Equal Contribution)
CHI '21 Student Research Competition • Second Position (undergraduate category)
[pdf] [doi] [video] [poster]
Academic Service
Teaching Assistant at IIIT-Delhi
Program Analysis (CSE503), Introduction to Human-Computer Interaction (DES102)
Reviewing
CHI 2023, CHI 2022 Late-Breaking Work
Student Volunteering
CSCW 2022, CHI PLAY 2022, CSCW 2021, IndiaHCI 2021
Selected Software Projects
Designed, developed, and hosted TechTree for the academic department and faculty at IIIT-Delhi to maintain and share descriptions of over 350 courses with students. TechTree enables 3000+ students every semester to plan their courses through visualization of course pre-requisites via interactive tables and directed acyclic graphs.
[Course Directory] [Course Dependency Graph]