Debajyoti Datta

Correctly identifying an individual's social context from passively worn sensors holds promise for delivering just-in-time adaptive interventions (JITAIs) to treat social anxiety. In this study, we present results using passively collected data from a within-subjects experiment that assessed physiological responses across different social contexts (i.e., alone vs. with others), social phases (i.e., pre- and post-interaction vs. during an interaction), social interaction sizes (i.e., dyadic vs. group interactions), and levels of social threat (i.e., implicit vs. explicit social evaluation). Participants in the study ($N=46$) reported moderate to severe social anxiety symptoms as assessed by the Social Interaction Anxiety Scale ($\geq$34 out of 80). Univariate paired difference tests, multivariate random forest models, and cluster analyses were used to explore physiological response patterns across different social and non-social contexts. Our results suggest that social context is more reliably distinguishable than social phase, group size, or level of social threat, and that there is considerable variability in physiological response patterns even among distinguishable contexts. Implications for real-world context detection and future deployment of JITAIs are discussed.

During pandemics, effective interventions require monitoring the problem at different scales and understanding the various tradeoffs between efficacy, privacy, and economic burden. To address these challenges, we propose a framework where we perform Bayesian change-point analysis on aggregate behavior markers extracted from mobile sensing data collected during the COVID-19 pandemic. Results generated by 598 participants for up to four months reveal rich insights: We observe an increase in smartphone usage around February 10th, followed by an increase in email usage around February 27th and, finally, a large reduction in participant’s mobility around March 13th. These behavior changes overlapped with important news events and government directives such as the naming of COVID-19, a spike in the number of reported cases in Europe, and the declaration of national emergency by President Trump. We also show that our detected change points align with changes in large scale external sources, including number of COVID-19 tweets, COVID-19 search traffic, and a large-scale foot traffic data collected by SafeGraph, providing further validation of our method. Our results show promise towards the feasibility of using mobile sensing to understand communities’ responses to public health interventions.

Neuromuscular disorders, such as Spinal Muscular Atrophy (SMA) and Duchenne Muscular Dystrophy (DMD), cause progressive muscular degeneration and loss of motor function for 1 in 6,000 children. Traditional upper limb motor function assessments do not quantitatively measure patient-performed motions, which makes it difficult to track progress for incremental changes. Assessing motor function in children with neuromuscular disorders is particularly challenging because they can be nervous or excited during experiments, or simply be too young to follow precise instructions. These challenges translate to confounding factors such as performing different parts of the arm curl slower or faster (phase variability) which affects the assessed motion quality. This paper uses curve registration and shape analysis to temporally align trajectories while simultaneously extracting a mean reference shape. Distances from this mean shape are used to assess the quality of motion. The proposed metric is invariant to confounding factors, such as phase variability, while suggesting several clinically relevant insights. First, there are statistically significant differences between functional scores for the control and patient populations (p$=$0.0213$\le$0.05). Next, several patients in the patient cohort are able to perform motion on par with the healthy cohort and vice versa. Our metric, which is computed based on wearables, is related to the Brooke's score ((p$=$0.00063$\le$0.05)), as well as motor function assessments based on dynamometry ((p$=$0.0006$\le$0.05)). These results show promise towards ubiquitous motion quality assessment in daily life.

A growing body of recent evidence has highlighted the limitations of natural language processing (NLP) datasets and classifiers. These include the presence of annotation artifacts in datasets, classifiers relying on shallow features like a single word (e.g., if a movie review has the word "romantic", the review tends to be positive), or unnecessary words (e.g., learning a proper noun to classify a movie as positive or negative). The presence of such artifacts has subsequently led to the development of challenging datasets to force the model to generalize better. While a variety of heuristic strategies, such as counterfactual examples and contrast sets, have been proposed, the theoretical justification about what makes these examples difficult for the classifier is often lacking or unclear. In this paper, using tools from information geometry, we propose a theoretical way to quantify the difficulty of an example in NLP. Using our approach, we explore difficult examples for several deep learning architectures. We discover that both BERT, CNN and fasttext are susceptible to word substitutions in high difficulty examples. These classifiers tend to perform poorly on the FIM test set. (generated by sampling and perturbing difficult examples, with accuracy dropping below 50%). We replicate our experiments on 5 NLP datasets (YelpReviewPolarity, AGNEWS, SogouNews, YelpReviewFull and Yahoo Answers). On YelpReviewPolarity we observe a correlation coefficient of -0.4 between resilience to perturbations and the difficulty score. Similarly we observe a correlation of 0.35 between the difficulty score and the empirical success probability of random substitutions. Our approach is simple, architecture agnostic and can be used to study the fragilities of text classification models. All the code used will be made publicly available, including a tool to explore the difficult examples for other datasets.

Machine learning techniques applied to the Natural Language Processing (NLP) component of conversational agent development show promising results for improved accuracy and quality of feedback that a conversational agent can provide. The effort required to develop an educational scenario specific conversational agent is time consuming as it requires domain experts to label and annotate noisy data sources such as classroom videos. Previous approaches to modeling annotations have relied on labeling thousands of examples and calculating inter-annotator agreement and majority votes in order to model the necessary scenarios. This method, while proven successful, ignores individual annotator strengths in labeling a data point and under-utilizes examples that do not have a majority vote for labeling. We propose using a multi-task weak supervision method combined with active learning to address these concerns. This approach requires less labeling than traditional methods and shows significant improvements in precision, efficiency, and time-requirements than the majority vote method (Ratner 2019). We demonstrate the validity of this method on the Google Jigsaw data set and then propose a scenario to apply this method using the Instructional Quality Assessment(IQA) to define the categories for labeling. We propose using probabilistic modeling of annotator labeling to generate active learning examples to further label the data. Active learning is able to iteratively improve the training performance and accuracy of the original classification model. This approach combines state-of-the art labeling techniques of weak supervision and active learning to optimize results in the educational domain and could be further used to lessen the data requirements for expanded scenarios within the education domain through transfer learning.

Significant health disparities exist between Hispanics and the general US population, complicated in part by communication, literacy, and linguistic factors. There are few available Spanish-language interactive, technology-driven health education programs that engage patients who have a range of health literacy levels. We describe the development of an interactive virtual patient educator for educating and counseling Hispanic women about cervical cancer and human papillomavirus. Specifically, we describe the iterative design methodology and rationale, usability evaluation, and pilot testing of the system with Hispanic women in a rural community in Florida. The pilot study findings provide preliminary evidence of the feasibility of the proposed patient education approach. The proposed application and the lessons learned will prove beneficial for future work targeted towards different cultural populations.