Character arcs are important theoretical devices employed in literary studies to understand character journeys, identify tropes across literary genres, and establish similarities between narratives. This work addresses the novel task of computationally generating event-centric, relation-based character arcs from narratives. Providing a quantitative representation for arcs brings tangibility to a theoretical concept and paves the way for subsequent applications. We present MARCUS (Modelling Arcs for Understanding Stories), an NLP pipeline that extracts events, participant characters, implied emotion, and sentiment to model inter-character relations. MARCUS tracks and aggregates these relations across the narrative to generate character arcs as graphical plots. We generate character arcs from two extended fantasy series, Harry Potter and Lord of the Rings. We evaluate our approach before outlining existing challenges, suggesting applications of our pipeline, and discussing future work.

As the utilization of language models in interdisciplinary, human-centered studies grow, the expectation of model capabilities continues to evolve. Beyond excelling at conventional tasks, models are recently expected to perform well on user-centric measurements involving confidence and human (dis)agreement -- factors that reflect subjective preferences. While modeling of subjectivity plays an essential role in cognitive science and has been extensively studied, it remains under-explored within the NLP community. In light of this gap, we explore how language models can harness subjectivity by conducting comprehensive experiments and analysis across various scenarios using both fine-tuned models and prompt-based large language models (LLMs). Our quantitative and qualitative experimental results indicate that existing post-hoc calibration approaches often fail to produce satisfactory results. However, our findings reveal that personality traits and demographical information are critical for measuring subjectivity. Furthermore, our in-depth analysis offers valuable insights for future research and development in the interdisciplinary studies of NLP and cognitive science.

Studies of human psychology have demonstrated that people are more motivated to extend empathy to in-group members than out-group members (Cikara et al., 2011). In this study, we investigate how this aspect of intergroup relations in humans is replicated by LLMs in an emotion intensity prediction task. In this task, the LLM is given a short description of an experience a person had that caused them to feel a particular emotion; the LLM is then prompted to predict the intensity of the emotion the person experienced on a numerical scale. By manipulating the group identities assigned to the LLM's persona (the "perceiver") and the person in the narrative (the "experiencer"), we measure how predicted emotion intensities differ between in-group and out-group settings. We observe that LLMs assign higher emotion intensity scores to in-group members than out-group members. This pattern holds across all three types of social groupings we tested: race/ethnicity, nationality, and religion. We perform an in-depth analysis on Llama-3.1-8B, the model which exhibited strongest intergroup bias among those tested.

The most prominent subtask in emotion analysis is emotion classification; to assign a category to a textual unit, for instance a social media post. Many research questions from the social sciences do, however, not only require the detection of the emotion of an author of a post but to understand who is ascribed an emotion in text. This task is tackled by emotion role labeling which aims at extracting who is described in text to experience an emotion, why, and towards whom. This could, however, be considered overly sophisticated if the main question to answer is who feels which emotion. A targeted approach for such setup is to classify emotion experiencer mentions (aka "emoters") regarding the emotion they presumably perceive. This task is similar to named entity recognition of person names with the difference that not every mentioned entity name is an emoter. While, very recently, data with emoter annotations has been made available, no experiments have yet been performed to detect such mentions. With this paper, we provide baseline experiments to understand how challenging the task is. We further evaluate the impact on experiencer-specific emotion categorization and appraisal detection in a pipeline, when gold mentions are not available. We show that experiencer detection in text is a challenging task, with a precision of .82 and a recall of .56 (F1 =.66). These results motivate future work of jointly modeling emoter spans and emotion/appraisal predictions.

Emotion classification in NLP assigns emotions to texts, such as sentences or paragraphs. With texts like "I felt guilty when he cried", focusing on the sentence level disregards the standpoint of each participant in the situation: the writer ("I") and the other entity ("he") could in fact have different affective states. The emotions of different entities have been considered only partially in emotion semantic role labeling, a task that relates semantic roles to emotion cue words. Proposing a related task, we narrow the focus on the experiencers of events, and assign an emotion (if any holds) to each of them. To this end, we represent each emotion both categorically and with appraisal variables, as a psychological access to explaining why a person develops a particular emotion. On an event description corpus, our experiencer-aware models of emotions and appraisals outperform the experiencer-agnostic baselines, showing that disregarding event participants is an oversimplification for the emotion detection task.

Emotion analysis in texts suffers from two major limitations: annotated gold-standard corpora are mostly small and homogeneous, and emotion identification is often simplified as a sentence-level classification problem. To address these issues, we introduce a new annotation scheme for exploring emotions and their causes, along with a new French dataset composed of autobiographical accounts of an emotional scene. The texts were collected by applying the Cognitive Analysis of Emotions developed by A. Finkel to help people improve on their emotion management. The method requires the manual analysis of an emotional event by a coach trained in Cognitive Analysis. We present a rule-based approach to automatically annotate emotions and their semantic roles (e.g. emotion causes) to facilitate the identification of relevant aspects by the coach. We investigate future directions for emotion analysis using graph structures.

The most prominent tasks in emotion analysis are to assign emotions to texts and to understand how emotions manifest in language. An observation for NLP is that emotions can be communicated implicitly by referring to events, appealing to an empathetic, intersubjective understanding of events, even without explicitly mentioning an emotion name. In psychology, the class of emotion theories known as appraisal theories aims at explaining the link between events and emotions. Appraisals can be formalized as variables that measure a cognitive evaluation by people living through an event that they consider relevant. They include the assessment if an event is novel, if the person considers themselves to be responsible, if it is in line with the own goals, and many others. Such appraisals explain which emotions are developed based on an event, e.g., that a novel situation can induce surprise or one with uncertain consequences could evoke fear. We analyze the suitability of appraisal theories for emotion analysis in text with the goal of understanding if appraisal concepts can reliably be reconstructed by annotators, if they can be predicted by text classifiers, and if appraisal concepts help to identify emotion categories. To achieve that, we compile a corpus by asking people to textually describe events that triggered particular emotions and to disclose their appraisals. Then, we ask readers to reconstruct emotions and appraisals from the text. This setup allows us to measure if emotions and appraisals can be recovered purely from text and provides a human baseline. Our comparison of text classification methods to human annotators shows that both can reliably detect emotions and appraisals with similar performance. Therefore, appraisals constitute an alternative computational emotion analysis paradigm and further improve the categorization of emotions in text with joint models.

Most research on emotion analysis from text focuses on the task of emotion classification or emotion intensity regression. Fewer works address emotions as structured phenomena, which can be explained by the lack of relevant datasets and methods. We fill this gap by releasing a dataset of 5000 English news headlines annotated via crowdsourcing with their dominant emotions, emotion experiencers and textual cues, emotion causes and targets, as well as the reader's perception and emotion of the headline. We propose a multiphase annotation procedure which leads to high quality annotations on such a task via crowdsourcing. Finally, we develop a baseline for the task of automatic prediction of structures and discuss results. The corpus we release enables further research on emotion classification, emotion intensity prediction, emotion cause detection, and supports further qualitative studies.

Are you just a computer made of meat? Are all your thoughts, feelings and experiences nothing more than circuits made from neurons in your head? If you're like a lot of people, your answer to this question will be a definitive "No!" From science to philosophy, there are lots of good reasons to hold that human beings are more than just computing machines. Unfortunately, many of the technologists bringing versions of artificial intelligence to the market are already sure they know that we are. Suddenly we might be leaving our grandmas and maybe even our kids with emotional robots because, oh well, everybody's doing it. For them people are, indeed, just biological computers.

Simply reading someone's facial expressions and body language is not enough to understand the experiences of others, new research has found. The new study found that people who'put themselves in the shoes of others' are far more empathetic. While most people assume they can understand another's emotions simply by watching them, the study's results suggest otherwise. Simply reading someone's facial expressions and body language is not enough to understand the experiences of others, new research has found. The new study found that people who'put themselves in the shoes of others' are far better at understanding them (Stock image) But the findings showed they were actually better at estimating how they had felt if they simply viewed the pictures again.