Groundbreaking inventions and highly significant performance improvements in deep learning based Natural Language Processing are witnessed through the development of transformer based large Pre-trained Language Models (PLMs). The wide availability of unlabeled data within human generated data deluge along with self-supervised learning strategy helps to accelerate the success of large PLMs in language generation, language understanding, etc. But at the same time, latent historical bias/unfairness in human minds towards a particular gender, race, etc., encoded unintentionally/intentionally into the corpora harms and questions the utility and efficacy of large PLMs in many real-world applications, particularly for the protected groups. In this paper, we present an extensive investigation towards understanding the existence of "Affective Bias" in large PLMs to unveil any biased association of emotions such as anger, fear, joy, etc., towards a particular gender, race or religion with respect to the downstream task of textual emotion detection. We conduct our exploration of affective bias from the very initial stage of corpus level affective bias analysis by searching for imbalanced distribution of affective words within a domain, in large scale corpora that are used to pre-train and fine-tune PLMs. Later, to quantify affective bias in model predictions, we perform an extensive set of class-based and intensity-based evaluations using various bias evaluation corpora. Our results show the existence of statistically significant affective bias in the PLM based emotion detection systems, indicating biased association of certain emotions towards a particular gender, race, and religion.
Emotion Correlation Mining Through Deep Learning Models on Natural Language Text
Shanghai Institute for Advanced Communication and Data Science, Shanghai University（上海大学上海先进通信与数据科学研究院）；Center for Data Science and Big Data Analytics, Oakland University（奥克兰大学数据科学与大数据分析中心）
Can Induced Emotion Bias LLM Behaviors in Sequential Decision Making?
MBZUAI（穆罕默德·本·扎耶德人工智能大学）；Texas A&M University（德州农工大学）；National University of Singapore（新加坡国立大学）；UCLA（加州大学洛杉矶分校）；University of Texas at Austin（德克萨斯大学奥斯汀分校）；Mass General Hospital（麻省总医院）；Harvard Medical School（哈佛医学院）
AI in Mental Health: Emotional and Sentiment Analysis of Large Language Models' Responses to Depression, Anxiety, and Stress Queries
University of Tehran（塔里斯坦大学）；University of South Carolina（南卡罗来纳大学）；University of West London（西伦敦大学）；Azad University（阿扎德大学）；Amirkabir University of Technology（阿米卡比尔技术大学）
语言常常传达情感--情绪、感觉和态度。此外，不同的词可以传达不同程度的影响（强度）。然而，现有的手动创建的基本情绪（如愤怒和恐惧）的词典仅指示粗略类别的影响关联（例如，与愤怒相关联或不与愤怒相关联）。自动化的情感词典提供了很好的关联度，但它们往往不像人类创造的词典那样准确。在这里，我们第一次提出了一个手动创建的影响强度词汇与四种基本情绪的强度的实值分数：愤怒，恐惧，喜悦和悲伤。(We将随后添加更多情绪的条目，如厌恶，预期，信任和惊讶。我们把这个数据集称为NRC情感强度词典，简称AIL。AIL有近6,000个英语单词的条目。我们使用了一种称为最佳-最差缩放（BWS）的技术来创建词典。BWS提高了注释一致性，并获得了可靠的细粒度分数（分半可靠性> 0.91）。我们还将AIL中的条目与NRC VAD Lexicon中的条目进行了比较，NRC VAD Lexicon具有20 K英语单词的效价，唤醒和优势（VAD）分数。我们发现，愤怒、恐惧和悲伤的词平均来说具有非常相似的VAD分数。然而，悲伤的词往往比恐惧和愤怒的词有稍微低的优势分数。情感强度词典在诸如商业、教育、情报和公共卫生等许多领域的自动情感分析中有应用。AIL在构建自然语言生成系统中也是有用的。
A Customer Journey in the Land of Oz: Leveraging the Wizard of Oz Technique to Model Emotions in Customer Service Interactions
Translation Technology Team, Ghent University（翻译技术团队，根特大学）；IDLab, Internet technology and Data science Lab（IDLab，互联网技术与数据科学实验室）；Data science Lab, Ghent University--imec（数据科学实验室，根特大学--imec）
本文通过Wizard of Oz实验构建EmoWOZ-CS语料库，评估基于WOZ的运营商引导情感轨迹设计，量化人类标注性能差异，并基准检测与前瞻性情绪推断在实时支持中的挑战。
MOPO: Multi-Objective Prompt Optimization for Affective Text Generation
Institut für Maschinelle Sprachverarbeitung, University of Stuttgart（斯图加特大学机器语言研究所）；Fundamentals of Natural Language Processing, University of Bamberg（班贝格大学自然语言处理基础研究所）
