Labeling corpora constitutes a bottleneck to create models for new tasks or domains. Large language models mitigate the issue with automatic corpus labeling methods, particularly for categorical annotations. Some NLP tasks such as emotion intensity prediction, however, require text regression, but there is no work on automating annotations for continuous label assignments. Regression is considered more challenging than classification: The fact that humans perform worse when tasked to choose values from a rating scale lead to comparative annotation methods, including best-worst scaling. This raises the question if large language model-based annotation methods show similar patterns, namely that they perform worse on rating scale annotation tasks than on comparative annotation tasks. To study this, we automate emotion intensity predictions and compare direct rating scale predictions, pairwise comparisons and best-worst scaling. We find that the latter shows the highest reliability. A transformer regressor fine-tuned on these data performs nearly on par with a model trained on the original manual annotations.
If a person firmly believes in a non-factual statement, such as "The Earth is flat", and argues in its favor, there is no inherent intention to deceive. As the argumentation stems from genuine belief, it may be unlikely to exhibit the linguistic properties associated with deception or lying. This interplay of factuality, personal belief, and intent to deceive remains an understudied area. Disentangling the influence of these variables in argumentation is crucial to gain a better understanding of the linguistic properties attributed to each of them. To study the relation between deception and factuality, based on belief, we present the DeFaBel corpus, a crowd-sourced resource of belief-based deception. To create this corpus, we devise a study in which participants are instructed to write arguments supporting statements like "eating watermelon seeds can cause indigestion", regardless of its factual accuracy or their personal beliefs about the statement. In addition to the generation task, we ask them to disclose their belief about the statement. The collected instances are labelled as deceptive if the arguments are in contradiction to the participants' personal beliefs. Each instance in the corpus is thus annotated (or implicitly labelled) with personal beliefs of the author, factuality of the statement, and the intended deceptiveness. The DeFaBel corpus contains 1031 texts in German, out of which 643 are deceptive and 388 are non-deceptive. It is the first publicly available corpus for studying deception in German. In our analysis, we find that people are more confident in the persuasiveness of their arguments when the statement is aligned with their belief, but surprisingly less confident when they are generating arguments in favor of facts. The DeFaBel corpus can be obtained from https://www.ims.uni-stuttgart.de/data/defabel
Distorted science communication harms individuals and society as it can lead to unhealthy behavior change and decrease trust in scientific institutions. Given the rapidly increasing volume of science communication in recent years, a fine-grained understanding of how findings from scientific publications are reported to the general public, and methods to detect distortions from the original work automatically, are crucial. Prior work focused on individual aspects of distortions or worked with unpaired data. In this work, we make three foundational contributions towards addressing this problem: (1) annotating 1,600 instances of scientific findings from academic papers paired with corresponding findings as reported in news articles and tweets wrt. four characteristics: causality, certainty, generality and sensationalism; (2) establishing baselines for automatically detecting these characteristics; and (3) analyzing the prevalence of changes in these characteristics in both human-annotated and large-scale unlabeled data. Our results show that scientific findings frequently undergo subtle distortions when reported. Tweets distort findings more often than science news reports. Detecting fine-grained distortions automatically poses a challenging task. In our experiments, fine-tuned task-specific models consistently outperform few-shot LLM prompting.
Emotion classification in text is a challenging and subjective task, due to the involved cognitive inference processes that are required to interpret a textual stimulus. In addition, the set of emotion categories is highly domain-specific. For instance, literature analysis might require the use of aesthetic emotions (e.g., finding something beautiful), and social media analysis could benefit from fine-grained sets (e.g., separating anger from annoyance) in contrast to basic emotion categories. This renders the task an interesting field for zero-shot classifications, in which the label set is not known at model development time. Unfortunately, most resources for emotion analysis are English, and therefore, most studies on emotion analysis have been performed in English, including those that involve prompting language models for text labels. This leaves us with a research gap that we address in this paper: In which language should we prompt for emotion labels on non-English texts? This is particularly of interest when we have access to a multilingual large language model, because we could request labels with English prompts even for non-English data. Our experiments with natural language inference-based language models show that it is consistently better to use English prompts even if the data is in a different language.
Biomedical claim verification fails if no evidence can be discovered. In these cases, the fact-checking verdict remains unknown and the claim is unverifiable. To improve upon this, we have to understand if there are any claim properties that impact its verifiability. In this work we assume that entities and relations define the core variables in a biomedical claim's anatomy and analyze if their properties help us to differentiate verifiable from unverifiable claims. In a study with trained annotation experts we prompt them to find evidence for biomedical claims, and observe how they refine search queries for their evidence search. This leads to the first corpus for scientific fact verification annotated with subject-relation-object triplets, evidence documents, and fact-checking verdicts (the BEAR-Fact corpus). We find (1) that discovering evidence for negated claims (e.g., X-does-not-cause-Y) is particularly challenging. Further, we see that annotators process queries mostly by adding constraints to the search and by normalizing entities to canonical names. (2) We compare our in-house annotations with a small crowdsourcing setting where we employ medical experts and laypeople. We find that domain expertise does not have a substantial effect on the reliability of annotations. Finally, (3), we demonstrate that it is possible to reliably estimate the success of evidence retrieval purely from the claim text~(.82\F), whereas identifying unverifiable claims proves more challenging (.27\F). The dataset is available at http://www.ims.uni-stuttgart.de/data/bioclaim.
Emotion corpora are typically sampled based on keyword/hashtag search or by asking study participants to generate textual instances. In any case, these corpora are not uniform samples representing the entirety of a domain. We hypothesize that this practice of data acquisition leads to unrealistic correlations between overrepresented topics in these corpora that harm the generalizability of models. Such topic bias could lead to wrong predictions for instances like "I organized the service for my aunt's funeral." when funeral events are over-represented for instances labeled with sadness, despite the emotion of pride being more appropriate here. In this paper, we study this topic bias both from the data and the modeling perspective. We first label a set of emotion corpora automatically via topic modeling and show that emotions in fact correlate with specific topics. Further, we see that emotion classifiers are confounded by such topics. Finally, we show that the established debiasing method of adversarial correction via gradient reversal mitigates the issue. Our work points out issues with existing emotion corpora and that more representative resources are required for fair evaluation of models predicting affective concepts from text.
The term emotion analysis in text subsumes various natural language processing tasks which have in common the goal to enable computers to understand emotions. Most popular is emotion classification in which one or multiple emotions are assigned to a predefined textual unit. While such setting is appropriate to identify the reader's or author's emotion, emotion role labeling adds the perspective of mentioned entities and extracts text spans that correspond to the emotion cause. The underlying emotion theories agree on one important point; that an emotion is caused by some internal or external event and comprises several subcomponents, including the subjective feeling and a cognitive evaluation. We therefore argue that emotions and events are related in two ways. (1) Emotions are events; and this perspective is the fundament in NLP for emotion role labeling. (2) Emotions are caused by events; a perspective that is made explicit with research how to incorporate psychological appraisal theories in NLP models to interpret events. These two research directions, role labeling and (event-focused) emotion classification, have by and large been tackled separately. We contributed to both directions with the projects SEAT (Structured Multi-Domain Emotion Analysis from Text) and CEAT (Computational Event Evaluation based on Appraisal Theories for Emotion Analysis), both funded by the German Research Foundation. In this paper, we consolidate the findings and point out open research questions.
Conditional natural language generation methods often require either expensive fine-tuning or training a large language model from scratch. Both are unlikely to lead to good results without a substantial amount of data and computational resources. Prompt learning without changing the parameters of a large language model presents a promising alternative. It is a cost-effective approach, while still achieving competitive results. While this procedure is now established for zero- and few-shot text classification and structured prediction, it has received limited attention in conditional text generation. We present the first automatic prompt optimization approach for emotion-conditioned text generation with instruction-fine-tuned models. Our method uses an iterative optimization procedure that changes the prompt by adding, removing, or replacing tokens. As objective function, we only require a text classifier that measures the realization of the conditional variable in the generated text. We evaluate the method on emotion-conditioned text generation with a focus on event reports and compare it to manually designed prompts that also act as the seed for the optimization procedure. The optimized prompts achieve 0.75 macro-average F1 to fulfill the emotion condition in contrast to manually designed seed prompts with only 0.22 macro-average F1.
Models for affective text generation have shown a remarkable progress, but they commonly rely only on basic emotion theories or valance/arousal values as conditions. This is appropriate when the goal is to create explicit emotion statements ("The kid is happy."). Emotions are, however, commonly communicated implicitly. For instance, the emotional interpretation of an event ("Their dog died.") does often not require an explicit emotion statement. In psychology, appraisal theories explain the link between a cognitive evaluation of an event and the potentially developed emotion. They put the assessment of the situation on the spot, for instance regarding the own control or the responsibility for what happens. We hypothesize and subsequently show that including appraisal variables as conditions in a generation framework comes with two advantages. (1) The generation model is informed in greater detail about what makes a specific emotion and what properties it has. This leads to text generation that better fulfills the condition. (2) The variables of appraisal allow a user to perform a more fine-grained control of the generated text, by stating properties of a situation instead of only providing the emotion category. Our Bart and T5-based experiments with 7 emotions (Anger, Disgust, Fear, Guilt, Joy, Sadness, Shame), and 7 appraisals (Attention, Responsibility, Control, Circumstance, Pleasantness, Effort, Certainty) show that (1) adding appraisals during training improves the accurateness of the generated texts by 10 pp in F1. Further, (2) the texts with appraisal variables are longer and contain more details. This exemplifies the greater control for users.
Verbal deception has been studied in psychology, forensics, and computational linguistics for a variety of reasons, like understanding behaviour patterns, identifying false testimonies, and detecting deception in online communication. Varying motivations across research fields lead to differences in the domain choices to study and in the conceptualization of deception, making it hard to compare models and build robust deception detection systems for a given language. With this paper, we improve this situation by surveying available English deception datasets which include domains like social media reviews, court testimonials, opinion statements on specific topics, and deceptive dialogues from online strategy games. We consolidate these datasets into a single unified corpus. Based on this resource, we conduct a correlation analysis of linguistic cues of deception across datasets to understand the differences and perform cross-corpus modeling experiments which show that a cross-domain generalization is challenging to achieve. The unified deception corpus (UNIDECOR) can be obtained from https://www.ims.uni-stuttgart.de/data/unidecor.