This paper explores how FemTech platforms appropriate the term ‘care’ to create a collaborative, non-judgmental, and data-driven approach for a sexual and reproductive health condition like Polycystic Ovary Syndrome (PCOS). In contrast, offline healthcare for PCOS is insufficient owing to disruptions in treatment, gynaecological indifference, and a lack of time and attention to patient concerns. We share findings from an ethnographic study conducted in India, involving interviews and observations with FemTech platform founders, gynaecologists, and people with PCOS. Our study highlights how FemTech start-ups, led by engineering and management professionals, establish a unified digital care approach by capitalizing on the shortcomings of traditional offline gynaecological healthcare infrastructures. We identify the logics of care surrounding FemTech platforms and assess their sustainability as digital alternatives to offline gynaecological care. We offer recommendations to FemTech founders and policymakers to build sustainable and inclusive offline and online health infrastructures.

Ramit Sawhney, Puneet Mathur, Taru Jain, Akash Kumar Gautam, Rajiv Ratn Shah. Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 2021.

Natural language processing has recently made stock movement forecasting and volatility forecasting advances, leading to improved financial forecasting.Transcripts of companies' earnings calls are well studied for risk modeling, offering unique investment insight into stock performance.However, vocal cues in the speech of company executives present an underexplored rich source of natural language data for estimating financial risk.Additionally, most existing approaches ignore the correlations between stocks.Building on existing work, we introduce a neural model for stock volatility prediction that accounts for stock interdependence via graph convolutions while fusing verbal, vocal, and financial features in a semi-supervised multi-task risk forecasting formulation.Our proposed model, VolTAGE, outperforms existing methods demonstrating the effectiveness of multimodal learning for volatility prediction.