Kshitish Ghate
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Kshitish Ghate has a total of 11 co-authors. Here are the top co-authors by number of shared publications:
- Aswini Kumar Mishra
Department of Economics and Finance, BITS Pilani K. K. Birla Goa Campus, Birla Institute of Technology and Science, Pilani, Pilani, India
2 shared publications - Jayashree Renganathan
Department of Computer Science, Birla Institute of Technology and Science Pilani - K K Birla Goa Campus
2 shared publications - Alfiya M. Shaikh
Computer Science and Information Systems & APPCAIR, BITS Pilani, Goa, INDIA
1 shared publication - Byomakesh Debata
Department of Economics and Finance, Birla Institute of Technology and Science (BITS) Pilani, Jhunjhunu, India
1 shared publication - Hrithik Nambiar
Computer Science and Information Systems & APPCAIR, BITS Pilani, Goa, INDIA
1 shared publication Joushita J. Kennet
1 shared publication
Latest Publications
- 20 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Affective Computing
- Vol. PP (3) , 1-16
SLAB: A Self-supervised Label Generation Framework to Reduce Annotation Overhead
Recently, many emotion-aware services have been designed to improve the user experience during online video consumption (e.g., online meeting platforms, and online tutoring mediums). These services primarily deploy a machine learning model that infers user emotion continuously based on the variation in different physiological signals . However, the major challenge to developing such models is to continuously ask the users to self-report their emotions for ground truth annotation. To address these challenges, we present SLAB (Self-supervised LABel generator), a self-supervised deep learning framework for label generation to reduce the tabular data annotation overhead. SLAB utilizes two pretext tasks coupled with a novel $log-cosh$ loss function to learn useful representations from unlabeled data that apply to the downstream task of label generation. SLAB outperforms supervised learning, semi-supervised learning, and self-supervised learning baselines such as Value Imputation and Mask Estimation (VIME) on continuous emotion annotation datasets - Continuously Annotated Signals of Emotion (CASE) and K-EmoCon. We also demonstrate the generalizability of the SLAB on a unique wheelchair surface vibration dataset (in addition to four publicly available datasets from different domains). These findings highlight that SLAB significantly reduces the annotation overhead in situations where the number of unlabeled samples vastly outnumbers labeled samples.
- 20 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Affective Computing
- Vol. PP (3) , 1-16
SLAB: A Self-supervised Label Generation Framework to Reduce Annotation Overhead
Recently, many emotion-aware services have been designed to improve the user experience during online video consumption (e.g., online meeting platforms, and online tutoring mediums). These services primarily deploy a machine learning model that infers user emotion continuously based on the variation in different physiological signals . However, the major challenge to developing such models is to continuously ask the users to self-report their emotions for ground truth annotation. To address these challenges, we present SLAB (Self-supervised LABel generator), a self-supervised deep learning framework for label generation to reduce the tabular data annotation overhead. SLAB utilizes two pretext tasks coupled with a novel $log-cosh$ loss function to learn useful representations from unlabeled data that apply to the downstream task of label generation. SLAB outperforms supervised learning, semi-supervised learning, and self-supervised learning baselines such as Value Imputation and Mask Estimation (VIME) on continuous emotion annotation datasets - Continuously Annotated Signals of Emotion (CASE) and K-EmoCon. We also demonstrate the generalizability of the SLAB on a unique wheelchair surface vibration dataset (in addition to four publicly available datasets from different domains). These findings highlight that SLAB significantly reduces the annotation overhead in situations where the number of unlabeled samples vastly outnumbers labeled samples.
- 1 March 2022
- Published by Elsevier in Resources Policy
- Vol. 75
Rolling, recursive evolving and asymmetric causality between crude oil and gold prices: Evidence from an emerging market
- 1 March 2022
- Published by Elsevier in Resources Policy
- Vol. 75
Rolling, recursive evolving and asymmetric causality between crude oil and gold prices: Evidence from an emerging market
- 16 February 2022
- Published by Elsevier in Resources Policy
- Vol. 76
Dynamic connectedness in non-ferrous commodity markets: Evidence from India using TVP-VAR and DCC-GARCH approaches
- 16 February 2022
- Published by Elsevier in Resources Policy
- Vol. 76
Dynamic connectedness in non-ferrous commodity markets: Evidence from India using TVP-VAR and DCC-GARCH approaches
- 22 November 2021
- Published by Emerald Publishing in Review of Behavioral Finance
- Vol. 15 (2) , 176-204
COVID-19 pandemic sentiment and stock market behavior: evidence from an emerging market
Purpose: This study aims to examine the relationship between pandemic sentiment (PS) and stock market returns in an emerging order-driven stock market like India.Design/methodology/approach: This study uses nonlinear causality and wavelet coherence techniques to analyze the sentiment-returns nexus. The analysis is conducted on the full sample period from January to December 2020 and further extended to two subperiods from January to June and July to December to investigate whether the associations between sentiment and market returns persist even several months after the outbreak.Findings: This study constructs two novel measures of PS: one using Google Search Volume Intensity and the other using Textual Analysis of newspaper headlines. The empirical findings suggest a high degree of interrelationship between PS and stock returns in all time-frequency domains across the full sample period. This interrelationship is found to be further heightened during the initial months of the crisis but reduces significantly during the later months. This could be because a considerable amount of uncertainty regarding the crisis is already accounted for and priced into the markets in the initial months.Originality/value: The ongoing coronavirus pandemic has resulted in sharp volatility and frequent crashes in the global equity indices. This study is an endeavor to shed light on the ongoing debate on the COVID-19 pandemic, investors’ sentiment and stock market behavior.
- 22 November 2021
- Published by Emerald Publishing in Review of Behavioral Finance
- Vol. 15 (2) , 176-204
COVID-19 pandemic sentiment and stock market behavior: evidence from an emerging market
Purpose: This study aims to examine the relationship between pandemic sentiment (PS) and stock market returns in an emerging order-driven stock market like India.Design/methodology/approach: This study uses nonlinear causality and wavelet coherence techniques to analyze the sentiment-returns nexus. The analysis is conducted on the full sample period from January to December 2020 and further extended to two subperiods from January to June and July to December to investigate whether the associations between sentiment and market returns persist even several months after the outbreak.Findings: This study constructs two novel measures of PS: one using Google Search Volume Intensity and the other using Textual Analysis of newspaper headlines. The empirical findings suggest a high degree of interrelationship between PS and stock returns in all time-frequency domains across the full sample period. This interrelationship is found to be further heightened during the initial months of the crisis but reduces significantly during the later months. This could be because a considerable amount of uncertainty regarding the crisis is already accounted for and priced into the markets in the initial months.Originality/value: The ongoing coronavirus pandemic has resulted in sharp volatility and frequent crashes in the global equity indices. This study is an endeavor to shed light on the ongoing debate on the COVID-19 pandemic, investors’ sentiment and stock market behavior.