Shardul Sapkota

Shardul Sapkota

Auto-generated profile, based on publicly available information

Shardul Sapkota

Stanford University, Stanford, CA, USA

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
25 April 2025
Verified
Conference Paper
Open access
MJMatthew Jörke
Matthew Jörke
SSShardul Sapkota
Shardul Sapkota
LWLyndsea Warkenthien
Lyndsea Warkenthien
NVNiklas Vainio
Niklas Vainio
PSPaul Schmiedmayer
Paul Schmiedmayer
JLJames A. Landay
James A. Landay

27 September 2025
Verified
Conference Paper
Open access
OSOmar Shaikh
Omar Shaikh
SSShardul Sapkota
Shardul Sapkota
SRShan Rizvi
Shan Rizvi
EHEric Horvitz
Eric Horvitz
JPJoon Sung Park
Joon Sung Park
MBMichael S. Bernstein
Michael S. Bernstein

19 April 2023
Verified
Conference Paper
Open access
NJNuwan Nanayakkarawasam Peru Kandage Janaka
Nuwan Nanayakkarawasam Peru Kandage Janaka
SZShengdong Zhao
Shengdong Zhao
SSShardul Sapkota
Shardul Sapkota

8 November 2024
Verified
Book Chapter
Closed access
PDF file
KWKeenon Werling
Keenon Werling
JKJanelle Kaneda
Janelle Kaneda
TTTian Tan
Tian Tan
RARishi Agarwal
Rishi Agarwal
SSSix Skov
Six Skov
CLC. Karen Liu
C. Karen Liu

13 April 2026
Verified
Conference Paper
Open access
MJMatthew Jörke
Matthew Jörke
DGDefne Genç
Defne Genç
VTValentin Teutschbein
Valentin Teutschbein
SSShardul Sapkota
Shardul Sapkota
SCSarah Chung
Sarah Chung
JLJames A. Landay
James A. Landay
Large language models (LLMs) offer novel opportunities to support health behavior change, yet existing work has narrowly focused on text-only interactions. Building on decades of HCI research on effective behavior change interactions, we present Bloom, an application for physical activity promotion that integrates an LLM-based health coaching chatbot with existing design strategies and UI elements. As part of Bloom’s development, we conducted a redteaming evaluation and contribute a safety benchmark dataset. In a four-week randomized field study (N=54) comparing Bloom to a no-LLM control, we observed important shifts in psychological outcomes: participants in the LLM condition reported stronger beliefs that activity was beneficial, greater enjoyment, and more self-compassion. Both conditions significantly increased physical activity levels, doubling the proportion of participants meeting recommended weekly guidelines, though descriptively, we observed no advantage for the LLM condition in short-term physical activity levels. Instead, our findings suggest that LLMs may be more effective at shifting mindsets that precede longer-term behavior change.

2 November 2026
Verified
Conference Paper
Open access
SSShardul Sapkota
Shardul Sapkota
MJMatthew Jörke
Matthew Jörke
ZSZane Sabbagh
Zane Sabbagh
OSOmar Shaikh
Omar Shaikh
GWGrace Wang
Grace Wang
JLJames A. Landay
James A. Landay