Sudeep Bhatia


2022

pdf bib
Cascading Biases: Investigating the Effect of Heuristic Annotation Strategies on Data and Models
Chaitanya Malaviya | Sudeep Bhatia | Mark Yatskar
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing

Cognitive psychologists have documented that humans use cognitive heuristics, or mental shortcuts, to make quick decisions while expending less effort. While performing annotation work on crowdsourcing platforms, we hypothesize that such heuristic use among annotators cascades on to data quality and model robustness. In this work, we study cognitive heuristic use in the context of annotating multiple-choice reading comprehension datasets. We propose tracking annotator heuristic traces, where we tangibly measure low-effort annotation strategies that could indicate usage of various cognitive heuristics. We find evidence that annotators might be using multiple such heuristics, based on correlations with a battery of psychological tests. Importantly, heuristic use among annotators determines data quality along several dimensions: (1) known biased models, such as partial input models, more easily solve examples authoredby annotators that rate highly on heuristic use, (2) models trained on annotators scoring highly on heuristic use don’t generalize as well, and (3) heuristic-seeking annotators tend to create qualitatively less challenging examples. Our findings suggest that tracking heuristic usage among annotators can potentially help with collecting challenging datasets and diagnosing model biases.

2020

pdf bib
Predicting Responses to Psychological Questionnaires from Participants’ Social Media Posts and Question Text Embeddings
Huy Vu | Suhaib Abdurahman | Sudeep Bhatia | Lyle Ungar
Findings of the Association for Computational Linguistics: EMNLP 2020

Psychologists routinely assess people’s emotions and traits, such as their personality, by collecting their responses to survey questionnaires. Such assessments can be costly in terms of both time and money, and often lack generalizability, as existing data cannot be used to predict responses for new survey questions or participants. In this study, we propose a method for predicting a participant’s questionnaire response using their social media texts and the text of the survey question they are asked. Specifically, we use Natural Language Processing (NLP) tools such as BERT embeddings to represent both participants (via the text they write) and survey questions as embeddings vectors, allowing us to predict responses for out-of-sample participants and questions. Our novel approach can be used by researchers to integrate new participants or new questions into psychological studies without the constraint of costly data collection, facilitating novel practical applications and furthering the development of psychological theory. Finally, as a side contribution, the success of our model also suggests a new approach to study survey questions using NLP tools such as text embeddings rather than response data used in traditional methods.