This paper faces the problem of the limited availability of datasets for Aspect-Based Sentiment Analysis (ABSA) in the Cultural Heritage domain. Currently, the main datasets for ABSA are product or restaurant reviews. We expand this to book reviews. Our methodology employs an LLM to maintain domain relevance while preserving the linguistic authenticity and natural variations found in genuine reviews. Entity types are annotated through the tool Text2AMR2FRED and evaluated manually. Additionally, we finetuned Llama 3.1 8B as a baseline model that not only performs ABSA, but also performs Entity Typing (ET) with a set of classes from DOLCE foundational ontology, enabling precise categorization of target aspects within book reviews. We present three key contributions as a step forward expanding ABSA: 1) a semi-synthetic set of book reviews, 2) an evaluation of Llama-3-1-Instruct 8B on the ABSA task, and 3) a fine-tuned version of Llama-3-1-Instruct 8B for ABSA.

The development of artificial intelligence systems capable of understanding and reasoning about complex real-world scenarios is a significant challenge. In this work we present a novel approach to enhance and exploit LLM reactive capability to address complex problems and interpret deeply contextual real-world meaning. We introduce a method and a tool for creating a multimodal, knowledge-augmented formal representation of meaning that combines the strengths of large language models with structured semantic representations. Our method begins with an image input, utilizing state-of-the-art large language models to generate a natural language description. This description is then transformed into an Meaning Representation (AMR) graph, which is formalized and enriched with logical design patterns, and layered semantics derived from linguistic and factual knowledge bases. The resulting graph is then fed back into the LLM to be extended with implicit knowledge activated by complex heuristic learning, including semantic implicatures, moral values, embodied cognition, and metaphorical representations. By bridging the gap between unstructured language models and formal semantic structures, our method opens new avenues for tackling intricate problems in natural language understanding and reasoning. • Neurosymbolic approach combining Large Language Models (LLMs) and knowledge graphs. • Extended Knowledge Graphs for implicit knowledge in multiple semantic dimensions. • 11 heuristics to enrich formal representations of meaning from multimodal inputs. • Three-tiered evaluation: logical validation, ontology alignment, human assessment.

Abstract Values, as intended in ethics, determine the shape and validity of moral and social norms, grounding our everyday individual and community behavior on commonsense knowledge. The attempt to untangle human moral and social value-oriented structure of relations requires investigating both the dimension of subjective human perception of the world, and socio-cultural dynamics and multi-agent social interactions. Formalising latent moral content in human interaction is an appealing perspective that would enable a deeper understanding of both social dynamics and individual cognitive and behavioral dimension. To formalize this broad knowledge area, in the context of ValueNet, a modular ontology representing and operationalising moral and social values, we present two modules aiming at representing two main informal theories in literature: (i) the Basic Human Values theory by Shalom Schwartz and (ii) the Moral Foundations Theory by Graham and Haidt. ValueNet is based on reusable Ontology Design Patterns, is aligned to the DOLCE foundational ontology, and is a component of the Framester factual-linguistic knowledge graph.