Papers by H. Andrew Schwartz
Responsible Evaluation of AI for Mental Health (2026.acl-long)
Copied to clipboard
Hiba Arnaout, Anmol Goel, H. Andrew Schwartz, Steffen T. Eberhardt, Dana Atzil-Slonim, Gavin Doherty, Brian Schwartz, Wolfgang Lutz, Tim Althoff, Munmun De Choudhury, Hamidreza Jamalabadi, Raj Sanjay Shah, Flor Miriam Plaza-del-Arco, Dirk Hovy, Maria Liakata, Iryna Gurevych
| Challenge: | Existing approaches to evaluating AI tools in this domain remain fragmented and inconsistent. |
| Approach: | They propose a taxonomy of AI mental health support types that integrates clinical soundness, social context, and equity to provide a structured basis for evaluation. |
| Outcome: | The proposed framework integrates clinical soundness, social context, and equity, providing a structured basis for evaluation. |
The Remarkable Benefit of User-Level Aggregation for Lexical-based Population-Level Predictions (D18-1)
Copied to clipboard
Salvatore Giorgi, Daniel Preoţiuc-Pietro, Anneke Buffone, Daniel Rieman, Lyle Ungar, H. Andrew Schwartz
| Challenge: | Social media data is often aggregated without regard to users in the Twitter populations of each community. |
| Approach: | They propose to use Twitter language to build community-level models using Twitter language aggregated by users. |
| Outcome: | The proposed method improves on four county-level tasks spanning demographic, health, and psychological outcomes over the standard approach of aggregating all tweets. |
Human Language Modeling (2022.findings-acl)
Copied to clipboard
| Challenge: | Existing language modeling models treat text sequences as if they were created independently. |
| Approach: | They propose a hierarchical extension to the language modeling problem whereby a human-level exists to connect sequences of documents and capture the notion that human language is moderated by changing human states. |
| Outcome: | The proposed model outperforms the current state-of-the-art in terms of language modeling and fine-tuning for 4 downstream tasks spanning document- and user-levels. |
Transfer and Active Learning for Dissonance Detection: Addressing the Rare-Class Challenge (2023.acl-long)
Copied to clipboard
Vasudha Varadarajan, Swanie Juhng, Syeda Mahwish, Xiaoran Liu, Jonah Luby, Christian Luhmann, H. Andrew Schwartz
| Challenge: | Active learning has been proposed to alleviate data acquisition challenges for rare-class tasks when the class label is very infrequent (e.g., 5% of samples). |
| Approach: | They propose to use transformers to train models on closely related tasks and evaluate acquisition strategies, including a proposed probability-of-rare-class approach to dissonance detection. |
| Outcome: | The proposed method improves model accuracy while iterative transfer-learning does not improve cold-start performance. |
From Word Sequences to Behavioral Sequences: Adapting Modeling and Evaluation Paradigms for Longitudinal NLP (2026.acl-long)
Copied to clipboard
Adithya V Ganesan, Vasudha Varadarajan, Oscar Kjell, Whitney Ringwald, Scott M. Feltman, Benjamin J. Luft, Roman Kotov, Ryan L. Boyd, H. Andrew Schwartz
| Challenge: | a longitudinal model for NLP relies on document-level evaluation to map isolated instances of language to an outcome. |
| Approach: | They propose a longitudinal model that aligns evaluation splits to generalization over people and time . they propose integrating a sequence inputs to incorporate history by default . |
| Outcome: | The proposed model improves on a dataset of 17k daily diary transcripts paired with PTSD symptom severity from 238 participants. |
MAQuA: Multi-outcome Adaptive Question-Asking for Mental Health using Item Response Theory (2026.eacl-long)
Copied to clipboard
Vasudha Varadarajan, Hui Xu, Rebecca Astrid Böhme, Mariam Marlen Mirström, Sverker Sikström, H. Andrew Schwartz
| Challenge: | Evaluations of large language models (LLMs) indicate that such assessments are inconsistent and in many cases less accurate than dedicated condition-specific models with established psychometric validity. |
| Approach: | They propose a multi-outcome modeling and adaptive question-asking framework for simultaneous, multidimensional mental health screening that integrates language responses with item response theory and factor analysis. |
| Outcome: | Empirical results show that MAQuA reduces the number of assessment questions required for score stabilization by 50–87% compared to random ordering. |
Empirical Evaluation of Pre-trained Transformers for Human-Level NLP: The Role of Sample Size and Dimensionality (2021.naacl-main)
Copied to clipboard
| Challenge: | In human-level NLP tasks, the number of observations is often smaller than the standard 768+ hidden state sizes of each layer within transformer-based language models. |
| Approach: | They propose to use dimension reduction methods to fine-tune large models with limited data and to use pre-trained dimension reduction regimes to improve model performance. |
| Outcome: | The proposed model outperforms other models in human-level NLP tasks with a pre-trained dimension reduction regime. |
MeLT: Message-Level Transformer with Masked Document Representations as Pre-Training for Stance Detection (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Much of natural language processing is focused on leveraging large capacity language models, typically trained over single messages with a task of predicting one or more tokens. |
| Approach: | They propose a hierarchical message-encoder pre-trained over Twitter for stance prediction task. |
| Outcome: | The proposed model achieves 67% performance on stance prediction task using a pre-trained message-encoder over Twitter. |
Characterizing Social Spambots by their Human Traits (2021.findings-acl)
Copied to clipboard
| Challenge: | Social spambots are an emerging class of spammers attempting to emulate people . previous studies show that standard spambot detection methods fail to distinguish them from genuine accounts . |
| Approach: | They hypothesize that human-like attributes of social spambots are unhuman-like . they find that social spam bots are extremely similar and average in their expressed personality, demographics, and emotion . |
| Outcome: | The proposed method is based on the human characteristics of social spambots . it shows that social bots are extremely similar and average in their expressed personality, demographics, and emotion . |
Autoregressive Affective Language Forecasting: A Self-Supervised Task (2020.coling-main)
Copied to clipboard
| Challenge: | Using natural language, we can model emotional language in time based on past changes of language. |
| Approach: | They propose a task of affective language forecasting to model emotional language in time based on past changes of language. |
| Outcome: | The proposed model outperforms existing models on a Twitter dataset of 1,900 users and scores for 6 emotions and 2 additional linguistic attributes. |
Causal Explanation Analysis on Social Media (D18-1)
Copied to clipboard
| Challenge: | Understanding causal explanations is an important psychological factor linked to physical and mental health. |
| Approach: | They propose to automate causal explanation analysis by building on discourse parsing and using a hierarchy of Bidirectional LSTMs to identify the specific phrase that is the explanation. |
| Outcome: | The proposed subtasks achieve strong accuracies but differ in their approaches . the proposed sub task is compared with the previous task and is able to identify the specific phrase that is the explanation. |
Residualized Factor Adaptation for Community Social Media Prediction Tasks (D18-1)
Copied to clipboard
| Challenge: | Existing approaches to social media language capture only socio-demographic contexts, such as age, education rates, race, and gender. |
| Approach: | They propose a method which integrates community attributes and adapts linguistic features to community attributes. |
| Outcome: | The proposed model integrates community attributes and adapts linguistic features to community attributes. |
Discourse-Level Representations can Improve Prediction of Degree of Anxiety (2023.acl-short)
Copied to clipboard
Swanie Juhng, Matthew Matero, Vasudha Varadarajan, Johannes Eichstaedt, Adithya V Ganesan, H. Andrew Schwartz
| Challenge: | Anxiety disorders are the most common of mental illnesses, but little is known about how to detect them from language. |
| Approach: | They propose to use discourse-level information in addition to lexical-level large language model embeddings to evaluate the utility of a lexico-discourse model. |
| Outcome: | The proposed model outperforms models based on state-of-the-art contextual embeddings and uses discourse patterns of causal explanations significantly more than models derived from Sentence-BERT and DiscRE, and is comparable to psychological models. |
From Text to Context: Contextualizing Language with Humans, Groups, and Communities for Socially Aware NLP (2024.naacl-tutorials)
Copied to clipboard
Adithya V Ganesan, Siddharth Mangalik, Vasudha Varadarajan, Nikita Soni, Swanie Juhng, João Sedoc, H. Andrew Schwartz, Salvatore Giorgi, Ryan L Boyd
| Challenge: | This tutorial will cover the latest techniques and libraries for doing so at each level of analysis. |
| Approach: | This tutorial will cover the latest techniques and libraries for doing so at each level of analysis. |
| Outcome: | The tutorial covers human-centered techniques that provide benefit to traditional document- or word-level NLP tasks. |
On the Distribution, Sparsity, and Inference-time Quantization of Attention Values in Transformers (2021.findings-acl)
Copied to clipboard
Tianchu Ji, Shraddhan Jain, Michael Ferdman, Peter Milder, H. Andrew Schwartz, Niranjan Balasubramanian
| Challenge: | Recent work shows that attention can be pruned to zeros with minimal loss in accuracy. |
| Approach: | They propose a pruning technique which quantizes attention to a 3-bit format without retraining . they find that 80% of attention values can be pruned to zeros with minimal loss in accuracy . |
| Outcome: | The proposed approach produces only a few unique attention values with minimal loss in accuracy. |
Predictive Biases in Natural Language Processing Models: A Conceptual Framework and Overview (2020.acl-main)
Copied to clipboard
| Challenge: | a growing number of studies address the effect of bias on predictions, but no unifying framework exists . a general phenomenon of biased predictive models in NLP is not recent, authors say . |
| Approach: | They propose a unifying framework for identifying and reducing bias in natural language processing . they propose to differentiate two consequences of bias and four potential origins of bias . |
| Outcome: | The proposed framework provides an overview of predictive bias in natural language processing . it differentiates two consequences of bias and four potential origins of bias: label bias, selection bias, model overamplification, and semantic bias. |
Identifying Locus of Control in Social Media Language (D18-1)
Copied to clipboard
| Challenge: | lexical features outperform syntactic features in expressing control in social media . authors communicate internal locus of control when they ascribe control to themselves . |
| Approach: | They examine the role of syntax and semantics in expressing users’ sense of control in annotated Facebook posts. |
| Outcome: | The proposed language outperforms syntactic features in identifying whether or not a user is in control of their circumstances. |
Hierarchical Modeling for User Personality Prediction: The Role of Message-Level Attention (2020.acl-main)
Copied to clipboard
| Challenge: | Language processing is increasingly finding use as a supplement for questionnaires to assess psychological attributes of consenting individuals, but most approaches neglect to consider whether all documents of an individual are equally informative. |
| Approach: | They propose a model that uses message-level attention to learn the relative weight of users’ social media posts for assessing their five factor personality traits. |
| Outcome: | The proposed model outperforms models with word-level attention and yields state-of-the-art accuracies for all five personality traits. |