Ehsan Hoque

TL;DR: Fine-tuning MAG-BERT and MAG-XLNet significantly boosts the sentiment analysis performance over previous baselines as well as language-only fine- Tuning of BERT and XLNet.

TL;DR: Recent advances in machine learning have allowed accurate textual transcription, and analysis of prosody, pauses, energy, intonation, emotion and communication style, which has established moderate to good reliability of machine learning algorithms, comparable with human coding (or better) and some expected and unexpected associations between communication variables and patient satisfaction.

TL;DR: The results suggest that deteriorating depression and anxiety conditions have strong correlations with behavioral changes in Google Search and YouTube use during the COVID-19 pandemic, and demonstrate the feasibility of using pervasive online data to establish noninvasive surveillance systems for mental health conditions that bypasses many disadvantages of existing screening methods.

TL;DR: In this article, a method for diagnosing Parkinson's disease using the study of micro-expressions was presented. But the prediction accuracy was only 95.6% with the support vector machine (SVM).

TL;DR: In this article, the authors present an online social skills development interface for teenagers with autism spectrum disorder (ASD) which is intended to enable private conversation practice anywhere, anytime using a web browser.