Alignment of brain embeddings and artificial contextual embeddings in natural language points to common geometric patterns.

Contextual embeddings, derived from deep language models (DLMs), provide a continuous vectorial representation of language. This embedding space differs fundamentally from the symbolic representations posited by traditional psycholinguistics. We hypothesize that language areas in the human brain, similar to DLMs, rely on a continuous embedding space to represent language. To test this hypothesis, we densely record the neural activity patterns in the inferior frontal gyrus (IFG) of three participants using dense intracranial arrays while they listened to a 30-minute podcast. From these fine-grained spatiotemporal neural recordings, we derive a continuous vectorial representation for each word (i.e., a brain embedding) in each patient. Using stringent zero-shot mapping we demonstrate that brain embeddings in the IFG and the DLM contextual embedding space have common geometric patterns. The common geometric patterns allow us to predict the brain embedding in IFG of a given left-out word based solely on its geometrical relationship to other non-overlapping words in the podcast. Furthermore, we show that contextual embeddings capture the geometry of IFG embeddings better than static word embeddings. The continuous brain embedding space exposes a vector-based neural code for natural language processing in the human brain.

Social Media Images Can Predict Suicide Risk Using Interpretable Large Language-Vision Models.

Background: Suicide, a leading cause of death and a major public health concern, became an even more pressing matter since the emergence of social media two decades ago and, more recently, following the hardships that characterized the COVID-19 crisis. Contemporary studies therefore aim to predict signs of suicide risk from social media using highly advanced artificial intelligence (AI) methods. Indeed, these new AI-based studies managed to break a longstanding prediction ceiling in suicidology; however, they still have principal limitations that prevent their implementation in real-life settings. These include "black box" methodologies, inadequate outcome measures, and scarce research on non-verbal inputs, such as images (despite their popularity today).Objective: This study aims to address these limitations and present an interpretable prediction model of clinically valid suicide risk from images.Methods: The data were extracted from a larger dataset from May through June 2018 that was used to predict suicide risk from textual postings. Specifically, the extracted data included a total of 177,220 images that were uploaded by 841 Facebook users who completed a gold-standard suicide scale. The images were represented with CLIP (Contrastive Language-Image Pre-training), a state-of-the-art deep-learning algorithm, which was utilized, unconventionally, to extract predefined interpretable features (eg, "photo of sad people") that served as inputs to a simple logistic regression model.Results: The results of this hybrid model that integrated theory-driven features with bottom-up methods indicated high prediction performance that surpassed common deep learning algorithms (area under the receiver operating characteristic curve [AUC] = 0.720, Cohen d = 0.82). Further analyses supported a theory-driven hypothesis that at-risk users would have images with increased negative emotions and decreased belongingness.Conclusions: This study provides a first proof that publicly available images can be leveraged to predict validated suicide risk. It also provides simple and flexible strategies that could enhance the development of real-life monitoring tools for suicide.

Perspective changes in human listeners are aligned with the contextual transformation of the word embedding space.

Word embedding representations have been shown to be effective in predicting human neural responses to lingual stimuli. While these representations are sensitive to the textual context, they lack the extratextual sources of context such as prior knowledge, thoughts, and beliefs, all of which constitute the listener's perspective. In this study, we propose conceptualizing the listeners' perspective as a source that induces changes in the embedding space. We relied on functional magnetic resonance imaging data collected by Yeshurun Y, Swanson S, Simony E, Chen J, Lazaridi C, Honey CJ, Hasson U. Same story, different story: the neural representation of interpretive frameworks. Psychol Sci. 2017:28(3):307-319, in which two groups of human listeners (n = 40) were listening to the same story but with different perspectives. Using a dedicated fine-tuning process, we created two modified versions of a word embedding space, corresponding to the two groups of listeners. We found that each transformed space was better fitted with neural responses of the corresponding group, and that the spatial distances between these spaces reflect both interpretational differences between the perspectives and the group-level neural differences. Together, our results demonstrate how aligning a continuous embedding space to a specific context can provide a novel way of modeling listeners' intrinsic perspectives.

Shared computational principles for language processing in humans and deep language models.

Departing from traditional linguistic models, advances in deep learning have resulted in a new type of predictive (autoregressive) deep language models (DLMs). Using a self-supervised next-word prediction task, these models generate appropriate linguistic responses in a given context. In the current study, nine participants listened to a 30-min podcast while their brain responses were recorded using electrocorticography (ECoG). We provide empirical evidence that the human brain and autoregressive DLMs share three fundamental computational principles as they process the same natural narrative: (1) both are engaged in continuous next-word prediction before word onset; (2) both match their pre-onset predictions to the incoming word to calculate post-onset surprise; (3) both rely on contextual embeddings to represent words in natural contexts. Together, our findings suggest that autoregressive DLMs provide a new and biologically feasible computational framework for studying the neural basis of language.

Deep neural networks detect suicide risk from textual facebook posts.

Detection of suicide risk is a highly prioritized, yet complicated task. Five decades of research have produced predictions slightly better than chance (AUCs = 0.56-0.58). In this study, Artificial Neural Network (ANN) models were constructed to predict suicide risk from everyday language of social media users. The dataset included 83,292 postings authored by 1002 authenticated Facebook users, alongside valid psychosocial information about the users. Using Deep Contextualized Word Embeddings for text representation, two models were constructed: A Single Task Model (STM), to predict suicide risk from Facebook postings directly (Facebook texts → suicide) and a Multi-Task Model (MTM), which included hierarchical, multilayered sets of theory-driven risk factors (Facebook texts → personality traits → psychosocial risks → psychiatric disorders → suicide). Compared with the STM predictions (0.621 ≤ AUC ≤ 0.629), the MTM produced significantly improved prediction accuracy (0.697 ≤ AUC ≤ 0.746), with substantially larger effect sizes (0.729 ≤ d ≤ 0.936). Subsequent content analyses suggested that predictions did not rely on explicit suicide-related themes, but on a range of text features. The findings suggest that machine learning based analyses of everyday social media activity can improve suicide risk predictions and contribute to the development of practical detection tools.