Personality traits influence human behavior and social interactions, making their accurate prediction essential across multiple domains. The Big Five Model, a widely recognized framework in psychological science for assessing personality traits, has become the foundation for different computational approaches to personality prediction. In recent years, a growing body of research has highlighted the dynamic interplay between emotions and personality, as individuals navigate diverse emotional experiences that evoke distinct responses and ultimately shape their behavioral patterns. In this work, we present a novel framework that systematically integrates affective information into Pre-trained Language Models for Big Five Personality trait prediction. Our framework leverages text-based embeddings, emotion-conditioned features, and learnable psycholinguistic information that bridges affective dimensions with personality traits. This design preserves established psycholinguistic knowledge while enabling adaptive refinement through data-driven learning. Our experiments showed that our framework outperformed sentence embedding-based methods and Large Language Models across various datasets from different domains, achieving an average F1-score improvement of at least 15% in out-of-domain scenarios.

Moralities, emotions, and events are complex aspects of human cognition, which are often treated separately since capturing their combined effects is challenging, especially due to the lack of annotated data. Leveraging their interrelations hence becomes crucial for advancing the understanding of human moral behaviors. In this work, we propose ME2-BERT, the first holistic framework for fine-tuning a pre-trained language model like BERT to the task of moral foundation prediction. ME2-BERT integrates events and emotions for learning domain-invariant morality-relevant text representations. Our extensive experiments show that ME2-BERT outperforms existing state-of-the-art methods for moral foundation prediction, with an average increase up to 35% in the out-of-domain scenario.

Morality serves as the foundation of societal structure, guiding legal systems, shaping cultural values, and influencing individual self-perception. With the rise and pervasiveness of generative AI tools, and particularly Large Language Models (LLMs), concerns arise regarding how these tools capture and potentially alter moral dimensions through machine-generated text manipulation. Based on the Moral Foundation Theory, our work investigates this topic by analyzing the behavior of 12 LLMs among the most widely used Open and uncensored (i.e., ”abliterated”) models, and leveraging human-annotated datasets used in moral-related analysis. Results have shown varying levels of alteration of moral expressions depending on the type of text modification task and moral-related conditioning prompt.