Abstract The exponential surge in online health information, coupled with its increasing use by non-experts, highlights the pressing need for advanced Health Information Retrieval (HIR) models that consider not only topical relevance but also the factual accuracy of the retrieved information, given the potential risks associated with health misinformation. To this aim, this paper introduces a solution driven by Retrieval-Augmented Generation (RAG), which leverages the capabilities of generative Large Language Models (LLMs) to enhance the retrieval of health-related documents grounded in scientific evidence. In particular, we propose a three-stage model: in the first stage, the user’s query is employed to retrieve topically relevant passages with associated references from a knowledge base constituted by scientific literature. In the second stage, these passages, alongside the initial query, are processed by LLMs to generate a contextually relevant rich text (GenText). In the last stage, the documents to be retrieved are evaluated and ranked both from the point of view of topical relevance and factual accuracy by means of their comparison with GenText, either through stance detection or semantic similarity. In addition to calculating factual accuracy, GenText can offer a layer of explainability for it, aiding users in understanding the reasoning behind the retrieval. Experimental evaluation of our model on benchmark datasets and against baseline models demonstrates its effectiveness in enhancing the retrieval of both topically relevant and factually accurate health information, thus presenting a significant step forward in the health misinformation mitigation problem.

Research aimed at finding solutions to the problem of the diffusion of distinct forms of non-genuine information online across multiple domains has attracted growing interest in recent years, from opinion spam to fake news detection. Currently, partly due to the COVID-19 virus outbreak and the subsequent proliferation of unfounded claims and highly biased content, attention has focused on developing solutions that can automatically assess the genuineness of health information. Most of these approaches, applied both to Web pages and social media content, rely primarily on the use of handcrafted features in conjunction with Machine Learning. In this article, instead, we propose a health misinformation detection model that exploits as features the embedded representations of some structural and content characteristics of Web pages, which are obtained using an embedding model pre-trained on medical data. Such features are employed within a deep learning classification model, which categorizes genuine health information versus health misinformation. The purpose of this article is therefore to evaluate the effectiveness of the proposed model, namely Vec4Cred, with respect to the problem considered. This model represents an evolution of a previous one, with respect to which new features and architectural choices have been considered and illustrated in this work.

In this paper, we designed a knowledge supporting software system in which sentences and keywords are extracted from large scale document database.This system consists of semantic representation scheme for natural language processing of the document database.Documents originally in a form of PDF are broken into triple-store data after pre-processing.The semantic representation is a hyper-graph which consists of collections of binary relations of 'triples'.According to a certain rule based on user's interests, the system identify sentences and words of interests.The relationship of those extracted sentences is visualized in the form of network graph.A user can introduce new rules to extract additional Knowledge from the Database or paper.For practical example, we choose a set of research papers related IoT for the case study purpose.Applying several rules concerning authors' indicated keywords as well as the system's specified discourse words, significant knowledge are extracted from the papers.