Shelly Gupta
Papers
1
Total Citations
4
H-Index
1
About
Shelly Gupta is a researcher at the intersection of educational technology and applied machine learning, with a primary focus on automated assessment systems and adaptive testing. Her most cited work, "Auto-Tagging for Massive Online Selection Tests: Machine Learning to the Rescue" (2016, 4 citations), addresses a critical challenge in large-scale online assessments: the subjective and often inaccurate manual assignment of difficulty levels to test questions. Gupta demonstrated that difficulty is inherently relative—dependent on both the question’s position within a test and the test-takers’ performance—and proposed a machine learning framework to infer difficulty tags from historical student data. This contribution has practical implications for platforms like e-Yantra Robotics, enabling more equitable and precise evaluation in massive open online courses and competitive selection tests. While her citation count is modest, Gupta’s work is notable for its early application of data-driven methods to a pervasive problem in educational measurement, laying groundwork for adaptive testing systems that personalize question sequencing based on real-time performance. Her research underscores a commitment to making large-scale assessments both scalable and fair.
Research Focus
Key Achievements
Top Papers
- 1