Modeling Latent Dimensions of Human Beliefs

Abstract

How we perceive our surrounding world impacts how we live in and react to it. In this study, we propose LaBel (Latent Beliefs Model), an alternative to topic modeling that uncovers latent semantic dimensions from transformer-based embeddings and enables their representation as generated phrases rather than word lists. We use LaBel to explore the major beliefs that humans have about the world and other prevalent domains, such as education or parenting. Although human beliefs have been explored in previous works, our proposed model helps automate the exploring process to rely less on human experts, saving time and manual efforts, especially when working with large corpus data. Our approach to LaBel uses a novel modification of autoregressive transformers to effectively generate texts conditioning on a vector input format. Differently from topic modeling methods, our generated texts (e.g. “the world is truly in your favor”) are discourse segments rather than word lists, which helps convey semantics in a more natural manner with full context. We evaluate LaBel dimensions using both an intrusion task as well as a classification task of identifying categories of major beliefs in tweets finding greater accuracies than popular topic modeling approaches.

NLP as a Lens for Causal Analysis and Perception Mining to Infer Mental Health on Social Media

“…State-of-the-art NLP models acquire their knowledge of syntax, semantics and pragmatics from large amounts of text, on the order of billions of words, and store this knowledge in layers of artificial neural networks thereby addressing multiple long-standing problems in psychiatry [51]. Existing well-equipped studies in pragmatic analysis of mental healthcare are empathetic conversations suggesting real-time application of online mental health support [52]- [55], and infusing commonsense knowledge [56].…”

“…Enriched with elements of (i) commonsense knowledge, (ii) domain-specific knowledge and (iii) other semantic enhancements for developing context-aware AI models for identifying, categorizing and predicting mental disorders, we more towards real-time applications such as developing conversational AI models through empathetic and personality analysis. We witness this low-level analysis through empathetic response generation [52], moral foundations [48], semantic health mentions [59], personality analysis [53], [54], human beliefs [53], [55] and cause-and-effect relationship in a given text [19], [57], [61], [62]. However, this high-level analysis misses key components to develop responsible AI models such as explainability, fairness, transparency, and accountability to deploy real-time applications in mental healthcare.…”