Optimism, Expectation, or Sarcasm? Multi-Class Hope Speech Detection in Spanish and English

Hope is a complex and underexplored emotional state that plays a significant role in education, mental health, and social interaction. Unlike basic emotions, hope manifests in nuanced forms ranging from grounded optimism to exaggerated wishfulness or sarcasm, making it difficult for Natural Language Processing systems to detect accurately. This study introduces PolyHope V2, a multilingual, fine-grained hope-speech dataset comprising over 30,000 annotated tweets in English and Spanish. This resource distinguishes between four hope sub-types--Generalized, Realistic, Unrealistic, and Sarcastic--and enhances existing datasets by explicitly labeling sarcastic instances. We benchmark multiple pre-trained transformer models and compare them with large language models (LLMs) such as GPT-4 and Llama 3 under zero-shot and few-shot regimes. Through qualitative analysis and confusion matrices, we highlight systematic challenges in separating closely related hope subtypes. The dataset and results provide a robust foundation for future emotion recognition tasks that demand greater semantic and contextual sensitivity across languages. Keywords: Hope Speech Detection, Sarcasm Detection, Multilingual NLP, Emotion Recognition, Fine-grained Sentiment Analysis 1 Introduction Recent improvements in Natural Language Processing (NLP) have enhanced applications in sentiment analysis, mental health assessments, social media monitoring, and educational platforms [1-5]. Despite recent progress, a persistent challenge in emotion recognition lies in identifying subtle and complex emotions, particularly hope, which is often overlooked in standard emotion taxonomies [6].