Abstract--Noisy self-reported empathy scores challenge supervised learning for empathy regression. While many algorithms have been proposed for learning with noisy labels in textual classification problems, the regression counterpart is relatively under-explored. We propose UPLME, an uncertainty-aware probabilistic language modelling framework to capture label noise in empathy regression tasks. One of the novelties in UPLME is a probabilistic language model that predicts both empathy scores and heteroscedastic uncertainty, and is trained using Bayesian concepts with variational model ensembling. We further introduce two novel loss components: one penalises degenerate Uncertainty Quantification (UQ), and another enforces similarity between the input pairs on which empathy is being predicted. UPLME achieves state-of-the-art performance (Pearson Correlation Coefficient: 0.558 0.580 and 0.629 0.634) in terms of the performance reported in the literature on two public benchmarks with label noise. Through synthetic label noise injection, we demonstrate that UPLME is effective in distinguishing between noisy and clean samples based on the predicted uncertainty. UPLME further outperform (Calibration error: 0.571 0.376) a recent variational model ensembling-based UQ method designed for regression problems.

Social media platforms generate massive volumes of heterogeneous data, capturing user behaviors, textual content, temporal dynamics, and network structures. Analyzing such data is crucial for understanding phenomena such as opinion dynamics, community formation, and information diffusion. However, discovering insights from this complex landscape is exploratory, conceptually challenging, and requires expertise in social media mining and visualization. Existing automated approaches, though increasingly leveraging large language models (LLMs), remain largely confined to structured tabular data and cannot adequately address the heterogeneity of social media analysis. We present SIA (Social Insight Agents), an LLM agent system that links heterogeneous multi-modal data -- including raw inputs (e.g., text, network, and behavioral data), intermediate outputs, mined analytical results, and visualization artifacts -- through coordinated agent flows. Guided by a bottom-up taxonomy that connects insight types with suitable mining and visualization techniques, SIA enables agents to plan and execute coherent analysis strategies. To ensure multi-modal integration, it incorporates a data coordinator that unifies tabular, textual, and network data into a consistent flow. Its interactive interface provides a transparent workflow where users can trace, validate, and refine the agent's reasoning, supporting both adaptability and trustworthiness. Through expert-centered case studies and quantitative evaluation, we show that SIA effectively discovers diverse and meaningful insights from social media while supporting human-agent collaboration in complex analytical tasks.

In this digital world, people freely express their emotions using different social media platforms. As a result, modeling and integrating emotion-understanding models are vital for various human-computer interaction tasks such as decision-making, product and customer feedback analysis, political promotions, marketing research, and social media monitoring. As users express different emotions simultaneously in a single instance, annotating emotions in a multilabel setting such as the EthioEmo (Belay et al., 2025) dataset effectively captures this dynamic. Additionally, incorporating intensity, or the degree of emotion, is crucial, as emotions can significantly differ in their expressive strength and impact. This intensity is significant for assessing whether further action is necessary in decision-making processes, especially concerning negative emotions in applications such as healthcare and mental health studies. To enhance the EthioEmo dataset, we include annotations for the intensity of each labeled emotion. Furthermore, we evaluate various state-of-the-art encoder-only Pretrained Language Models (PLMs) and decoder-only Large Language Models (LLMs) to provide comprehensive benchmarking.

Large language models (LLMs) have revolutionised numerous fields, with LLM-as-a-service (LLMSaaS) having a strong generalisation ability that offers accessible solutions directly without the need for costly training. In contrast to the widely studied prompt engineering for task solving directly (in vivo), this paper explores its potential in in-vitro applications. These involve using LLM to generate labels to help the supervised training of mainstream models by (1) noisy label correction and (2) training data augmentation with LLM-generated labels. In this paper, we evaluate this approach in the emerging field of empathy computing -- automating the prediction of psychological questionnaire outcomes from inputs like text sequences. Specifically, crowdsourced datasets in this domain often suffer from noisy labels that misrepresent underlying empathy. By leveraging LLM-generated labels to train pre-trained language models (PLMs) like RoBERTa, we achieve statistically significant accuracy improvements over baselines, achieving a state-of-the-art Pearson correlation coefficient of 0.648 on NewsEmp benchmarks. In addition, we bring insightful discussions, including current challenges in empathy computing, data biases in training data and evaluation metric selection. Code and LLM-generated data are available at https://github.com/hasan-rakibul/LLMPathy (available once the paper is accepted).

This comprehensive study evaluates the performance of OpenAI's o1-preview large language model across a diverse array of complex reasoning tasks, spanning multiple domains, including computer science, mathematics, natural sciences, medicine, linguistics, and social sciences. Through rigorous testing, o1-preview demonstrated remarkable capabilities, often achieving human-level or superior performance in areas ranging from coding challenges to scientific reasoning and from language processing to creative problem-solving. Key findings include: -83.3% success rate in solving complex competitive programming problems, surpassing many human experts. -Superior ability in generating coherent and accurate radiology reports, outperforming other evaluated models. -100% accuracy in high school-level mathematical reasoning tasks, providing detailed step-by-step solutions. -Advanced natural language inference capabilities across general and specialized domains like medicine. -Impressive performance in chip design tasks, outperforming specialized models in areas such as EDA script generation and bug analysis. -Remarkable proficiency in anthropology and geology, demonstrating deep understanding and reasoning in these specialized fields. -Strong capabilities in quantitative investing. O1 has comprehensive financial knowledge and statistical modeling skills. -Effective performance in social media analysis, including sentiment analysis and emotion recognition. The model excelled particularly in tasks requiring intricate reasoning and knowledge integration across various fields. While some limitations were observed, including occasional errors on simpler problems and challenges with certain highly specialized concepts, the overall results indicate significant progress towards artificial general intelligence.

Natural language processing (NLP) is a field of study that combines computer science and linguistics to help machines understand human language. NLP has become an integral part of modern technology, powering everything from chatbots to voice assistants. But how exactly do NLP algorithms work? And why do they matter? At its core, NLP is about teaching machines to understand human language.

We review the state of research on empathy in natural language processing and identify the following issues: (1) empathy definitions are absent or abstract, which (2) leads to low construct validity and reproducibility. Moreover, (3) emotional empathy is overemphasized, skewing our focus to a narrow subset of simplified tasks. We believe these issues hinder research progress and argue that current directions will benefit from a clear conceptualization that includes operationalizing cognitive empathy components. Our main objectives are to provide insight and guidance on empathy conceptualization for NLP research objectives and to encourage researchers to pursue the overlooked opportunities in this area, highly relevant, e.g., for clinical and educational sectors.

Social media have the potential to provide timely information about emergency situations and sudden events. However, finding relevant information among millions of posts being posted every day can be difficult, and developing a data analysis project usually requires time and technical skills. This study presents an approach that provides flexible support for analyzing social media, particularly during emergencies. Different use cases in which social media analysis can be adopted are introduced, and the challenges of retrieving information from large sets of posts are discussed. The focus is on analyzing images and text contained in social media posts and a set of automatic data processing tools for filtering, classification, and geolocation of content with a human-in-the-loop approach to support the data analyst. Such support includes both feedback and suggestions to configure automated tools, and crowdsourcing to gather inputs from citizens. The results are validated by discussing three case studies developed within the Crowd4SDG H2020 European project.

The Ubiquitous nature of smartphones has significantly increased the use of social media platforms, such as Facebook, Twitter, TikTok, and LinkedIn, etc., among the public, government, and businesses. Facebook generated ~70 billion USD in 2019 in advertisement revenues alone, a ~27% increase from the previous year. Social media has also played a strong role in outbreaks of social protests responsible for political changes in different countries. As we can see from the above examples, social media plays a big role in business intelligence and international politics. In this paper, we present and discuss a high-level functional intelligence model (recipe) of Social Media Analysis (SMA). This model synthesizes the input data and uses operational intelligence to provide actionable recommendations. In addition, it also matches the synthesized function of the experiences and learning gained from the environment. The SMA model presented is independent of the application domain, and can be applied to different domains, such as Education, Healthcare and Government, etc. Finally, we also present some of the challenges faced by SMA and how the SMA model presented in this paper solves them.

Social media has become prevalent and important for social networking and opinion sharing in recent years [1]. By changing the way we perceive and interact with the world, social media has changed our lives profoundly [2], [3]. With millions of posts and replies uploaded every day on social media such as Facebook, Twitters and YouTube, it is an abundant and informative data source of public opinions; thus, it has attracted lots of attention from both academia and industry to understand people and society [4]-[6]. Most previous text mining-based social media analysis focused on Twitter and Facebook [7]. YouTube, generally considered as a video platform, the values of its text comments below videos have long been underestimated. Being the second most popular website in the world [8] and having 1.9 billion active users [9], YouTube is an attractive source of research in social media analysis with immense potentials. Recent developments in autonomous vehicle technology have helped bring self-driving vehicles to the forefront of public interest [10].