Research on psychological risk factors for suicide has developed for decades. However, combining explainable theory with modern data-driven language model approaches is non-trivial. In this study, we propose and evaluate methods for identifying language patterns aligned with theories of suicide risk by combining theory-driven suicidal archetypes with language model-based and relative entropy-based approaches. Archetypes are based on prototypical statements that evince risk of suicidality while relative entropy considers the ratio of how unusual both a risk-familiar and unfamiliar model find the statements. While both approaches independently performed similarly, we find that combining the two significantly improved the performance in the shared task evaluations, yielding our combined system submission with a BERTScore Recall of 0.906. Consistent with the literature, we find that titles are highly informative as suicide risk evidence, despite the brevity. We conclude that a combination of theory- and data-driven methods are needed in the mental health space and can outperform more modern prompt-based methods.

Mental health issues differ widely among individuals, with varied signs and symptoms. Recently, language-based assessments haveshown promise in capturing this diversity, but they require a substantial sample of words per person for accuracy. This work introducesthe task of Adaptive Language-Based Assessment (ALBA), which involves adaptively ordering questions while also scoring an individual’s latent psychological trait using limited language responses to previous questions. To this end, we develop adaptive testing methods under two psychometric measurement theories: Classical Test Theory and Item Response Theory.We empirically evaluate ordering and scoring strategies, organizing into two new methods: a semi-supervised item response theory-basedmethod (ALIRT) and a supervised Actor-Critic model. While we found both methods to improve over non-adaptive baselines, We foundALIRT to be the most accurate and scalable, achieving the highest accuracy with fewer questions (e.g., Pearson r ≈ 0.93 after only 3 questions as compared to typically needing at least 7 questions). In general, adaptive language-based assessments of depression and anxiety were able to utilize a smaller sample of language without compromising validity or large computational costs.

Aimed at the NLP researchers or practitioners who would like to integrate human - individual, group, or societal level factors into their analyses, this tutorial will cover recent techniques and libraries for doing so at each level of analysis. Starting with human-centered techniques that provide benefit to traditional document- or word-level NLP tasks (Garten et al., 2019; Lynn et al., 2017), we undertake a thorough exploration of critical human-level aspects as they pertain to NLP, gradually moving up to higher levels of analysis: individual persons, individual with agent (chat/dialogue), groups of people, and finally communities or societies.

While transformer-based systems have enabled greater accuracies with fewer training examples, data acquisition obstacles still persist for rare-class tasks – when the class label is very infrequent (e.g. < 5% of samples). Active learning has in general been proposed to alleviate such challenges, but choice of selection strategy, the criteria by which rare-class examples are chosen, has not been systematically evaluated. Further, transformers enable iterative transfer-learning approaches. We propose and investigate transfer- and active learning solutions to the rare class problem of dissonance detection through utilizing models trained on closely related tasks and the evaluation of acquisition strategies, including a proposed probability-of-rare-class (PRC) approach. We perform these experiments for a specific rare-class problem: collecting language samples of cognitive dissonance from social media. We find that PRC is a simple and effective strategy to guide annotations and ultimately improve model accuracy while transfer-learning in a specific order can improve the cold-start performance of the learner but does not benefit iterations of active learning.

Anxiety disorders are the most common of mental illnesses, but relatively little is known about how to detect them from language. The primary clinical manifestation of anxiety is worry associated cognitive distortions, which are likely expressed at the discourse-level of semantics. Here, we investigate the development of a modern linguistic assessment for degree of anxiety, specifically evaluating the utility of discourse-level information in addition to lexical-level large language model embeddings. We find that a combined lexico-discourse model outperforms models based solely on state-of-the-art contextual embeddings (RoBERTa), with discourse-level representations derived from Sentence-BERT and DiscRE both providing additional predictive power not captured by lexical-level representations. Interpreting the model, we find that discourse patterns of causal explanations, among others, were used significantly more by those scoring high in anxiety, dovetailing with psychological literature.

We address dissonant stance detection, classifying conflicting stance between two input statements. Computational models for traditional stance detection have typically been trained to indicate pro/con for a given target topic (e.g. gun control) and thus do not generalize well to new topics. In this paper, we systematically evaluate the generalizability of dissonant stance detection to situations where examples of the topic have not been seen at all or have only been seen a few times. We show that dissonant stance detection models trained on only 8 topics, none of which are the target topic, can perform as well as those trained only on a target topic. Further, adding non-target topics boosts performance further up to approximately 32 topics where accuracies start to plateau. Taken together, our experiments suggest dissonant stance detection models can generalize to new unanticipated topics, an important attribute for the social scientific study of social media where new topics emerge daily.

Discourse relations are typically modeled as a discrete class that characterizes the relation between segments of text (e.g. causal explanations, expansions). However, such predefined discrete classes limit the universe of potential relationships and their nuanced differences. Adding higher-level semantic structure to contextual word embeddings, we propose representing discourse relations as points in high dimensional continuous space. However, unlike words, discourse relations often have no surface form (relations are in between two segments, often with no word or phrase in that gap) which presents a challenge for existing embedding techniques. We present a novel method for automatically creating discourse relation embeddings (DiscRE), addressing the embedding challenge through a weakly supervised, multitask approach to learn diverse and nuanced relations in social media. Results show DiscRE representations obtain the best performance on Twitter discourse relation classification (macro F1=0.76), social media causality prediction (from F1=0.79 to 0.81), and perform beyond modern sentence and word transformers at traditional discourse relation classification, capturing novel nuanced relations (e.g. relations at the intersection of causal explanations and counterfactuals).

Psychological states unfold dynamically; to understand and measure mental health at scale we need to detect and measure these changes from sequences of online posts. We evaluate two approaches to capturing psychological changes in text: the first relies on computing the difference between the embedding of a message with the one that precedes it, the second relies on a “human-aware” multi-level recurrent transformer (HaRT). The mood changes of timeline posts of users were annotated into three classes, ‘ordinary,’ ‘switching’ (positive to negative or vice versa) and ‘escalations’ (increasing in intensity). For classifying these mood changes, the difference-between-embeddings technique – applied to RoBERTa embeddings – showed the highest overall F1 score (0.61) across the three different classes on the test set. The technique particularly outperformed the HaRT transformer (and other baselines) in the detection of switches (F1 = .33) and escalations (F1 = .61).Consistent with the literature, the language use patterns associated with mental-health related constructs in prior work (including depression, stress, anger and anxiety) predicted both mood switches and escalations.