Explainable online health information truthfulness in Consumer Health Search.

Introduction: People are today increasingly relying on health information they find online to make decisions that may impact both their physical and mental wellbeing. Therefore, there is a growing need for systems that can assess the truthfulness of such health information. Most of the current literature solutions use machine learning or knowledge-based approaches treating the problem as a binary classification task, discriminating between correct information and misinformation. Such solutions present several problems with regard to user decision making, among which: (i) the binary classification task provides users with just two predetermined possibilities with respect to the truthfulness of the information, which users should take for granted; indeed, (ii) the processes by which the results were obtained are often opaque and the results themselves have little or no interpretation. Methods: To address these issues, we approach the problem as an ad hoc retrieval task rather than a classification task, with reference, in particular, to the Consumer Health Search task. To do this, a previously proposed Information Retrieval model, which considers information truthfulness as a dimension of relevance, is used to obtain a ranked list of both topically-relevant and truthful documents. The novelty of this work concerns the extension of such a model with a solution for the explainability of the results obtained, by relying on a knowledge base consisting of scientific evidence in the form of medical journal articles. Results and discussion: We evaluate the proposed solution both quantitatively, as a standard classification task, and qualitatively, through a user study to examine the "explained" ranked list of documents. The results obtained illustrate the solution's effectiveness and usefulness in making the retrieved results more interpretable by Consumer Health Searchers, both with respect to topical relevance and truthfulness.

Effective matching of patients to clinical trials using entity extraction and neural re-ranking.

INTRODUCTION: Clinical trials (CTs) often fail due to inadequate patient recruitment. Finding eligible patients involves comparing the patient's information with the CT eligibility criteria. Automated patient matching offers the promise of improving the process, yet the main difficulties of CT retrieval lie in the semantic complexity of matching unstructured patient descriptions with semi-structured, multi-field CT documents and in capturing the meaning of negation coming from the eligibility criteria. OBJECTIVES: This paper tackles the challenges of CT retrieval by presenting an approach that addresses the patient-to-trials paradigm. Our approach involves two key components in a pipeline-based model: (i) a data enrichment technique for enhancing both queries and documents during the first retrieval stage, and (ii) a novel re-ranking schema that uses a Transformer network in a setup adapted to this task by leveraging the structure of the CT documents. METHODS: We use named entity recognition and negation detection in both patient description and the eligibility section of CTs. We further classify patient descriptions and CT eligibility criteria into current, past, and family medical conditions. This extracted information is used to boost the importance of disease and drug mentions in both query and index for lexical retrieval. Furthermore, we propose a two-step training schema for the Transformer network used to re-rank the results from the lexical retrieval. The first step focuses on matching patient information with the descriptive sections of trials, while the second step aims to determine eligibility by matching patient information with the criteria section. RESULTS: Our findings indicate that the inclusion criteria section of the CT has a great influence on the relevance score in lexical models, and that the enrichment techniques for queries and documents improve the retrieval of relevant trials. The re-ranking strategy, based on our training schema, consistently enhances CT retrieval and shows improved performance by 15% in terms of precision at retrieving eligible trials. CONCLUSION: The results of our experiments suggest the benefit of making use of extracted entities. Moreover, our proposed re-ranking schema shows promising effectiveness compared to larger neural models, even with limited training data. These findings offer valuable insights for improving methods for retrieval of clinical documents.

Vec4Cred: a model for health misinformation detection in web pages.

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.

Assessing vulnerability to psychological distress during the COVID-19 pandemic through the analysis of microblogging content.

In recent years we have witnessed a growing interest in the analysis of social media data under different perspectives, since these online platforms have become the preferred tool for generating and sharing content across different users organized into virtual communities, based on their common interests, needs, and perceptions. In the current study, by considering a collection of social textual contents related to COVID-19 gathered on the Twitter microblogging platform in the period between August and December 2020, we aimed at evaluating the possible effects of some critical factors related to the pandemic on the mental well-being of the population. In particular, we aimed at investigating potential lexicon identifiers of vulnerability to psychological distress in digital social interactions with respect to distinct COVID-related scenarios, which could be "at risk" from a psychological discomfort point of view. Such scenarios have been associated with peculiar topics discussed on Twitter. For this purpose, two approaches based on a "top-down" and a "bottom-up" strategy were adopted. In the top-down approach, three potential scenarios were initially selected by medical experts, and associated with topics extracted from the Twitter dataset in a hybrid unsupervised-supervised way. On the other hand, in the bottom-up approach, three topics were extracted in a totally unsupervised way capitalizing on a Twitter dataset filtered according to the presence of keywords related to vulnerability to psychological distress, and associated with at-risk scenarios. The identification of such scenarios with both approaches made it possible to capture and analyze the potential psychological vulnerability in critical situations.

Echo chamber detection and analysis: A topology- and content-based approach in the COVID-19 scenario.

Social media allow to fulfill perceived social needs such as connecting with friends or other individuals with similar interests into virtual communities; they have also become essential as news sources, microblogging platforms, in particular, in a variety of contexts including that of health. However, due to the homophily property and selective exposure to information, social media have the tendency to create distinct groups of individuals whose ideas are highly polarized around certain topics. In these groups, a.k.a. echo chambers, people only "hear their own voice," and divergent visions are no longer taken into account. This article focuses on the study of the echo chamber phenomenon in the context of the COVID-19 pandemic, by considering both the relationships connecting individuals and semantic aspects related to the content they share over Twitter. To this aim, we propose an approach based on the application of a community detection strategy to distinct topology- and content-aware representations of the COVID-19 conversation graph. Then, we assess and analyze the controversy and homogeneity among the different polarized groups obtained. The evaluations of the approach are carried out on a dataset of tweets related to COVID-19 collected between January and March 2020.

Surveilling COVID-19 Emotional Contagion on Twitter by Sentiment Analysis.

BACKGROUND: The fight against the COVID-19 pandemic seems to encompass a social media debate, possibly resulting in emotional contagion and the need for novel surveillance approaches. In the current study, we aimed to examine the flow and content of tweets, exploring the role of COVID-19 key events on the popular Twitter platform. METHODS: Using representative freely available data, we performed a focused, social media-based analysis to capture COVID-19 discussions on Twitter, considering sentiment and longitudinal trends between January 19 and March 3, 2020. Different populations of users were considered. Core discussions were explored measuring tweets' sentiment, by both computing a polarity compound score with 95% Confidence Interval and using a transformer-based model, pretrained on a large corpus of COVID-19-related Tweets. Context-dependent meaning and emotion-specific features were considered. RESULTS: We gathered 3,308,476 tweets written in English. Since the first World Health Organization report (January 21), negative sentiment proportion of tweets gradually increased as expected, with amplifications following key events. Sentiment scores were increasingly negative among most active users. Tweets content and flow revealed an ongoing scenario in which the global emergency seems difficult to be emotionally managed, as shown by sentiment trajectories. CONCLUSIONS: Integrating social media like Twitter as essential surveillance tools in the management of the pandemic and its waves might actually represent a novel preventive approach to hinder emotional contagion, disseminating reliable information and nurturing trust. There is the need to monitor and sustain healthy behaviors as well as community supports also via social media-based preventive interventions.

Detecting Binge Drinking and Alcohol-Related Risky Behaviours from Twitter's Users: An Exploratory Content- and Topology-Based Analysis.

Binge Drinking (BD) is a common risky behaviour that people hardly report to healthcare professionals, although it is not uncommon to find, instead, personal communications related to alcohol-related behaviors on social media. By following a data-driven approach focusing on User-Generated Content, we aimed to detect potential binge drinkers through the investigation of their language and shared topics. First, we gathered Twitter threads quoting BD and alcohol-related behaviours, by considering unequivocal keywords, identified by experts, from previous evidence on BD. Subsequently, a random sample of the gathered tweets was manually labelled, and two supervised learning classifiers were trained on both linguistic and metadata features, to classify tweets of genuine unique users with respect to media, bot, and commercial accounts. Based on this classification, we observed that approximately 55% of the 1 million alcohol-related collected tweets was automatically identified as belonging to non-genuine users. A third classifier was then trained on a subset of manually labelled tweets among those previously identified as belonging to genuine accounts, to automatically identify potential binge drinkers based only on linguistic features. On average, users classified as binge drinkers were quite similar to the standard genuine Twitter users in our sample. Nonetheless, the analysis of social media contents of genuine users reporting risky behaviours remains a promising source for informed preventive programs.

Bee Swarm Optimization for Medical Web Information Foraging.

The present work is related to Web intelligence and more precisely to medical information foraging. We present here a novel approach based on agents technology for information foraging. An architecture is proposed, in which we distinguish two important phases. The first one is a learning process for localizing the most relevant pages that might interest the user. This is performed on a fixed instance of the Web. The second takes into account the openness and the dynamicity of the Web. It consists on an incremental learning starting from the result of the first phase and reshaping the outcomes taking into account the changes that undergoes the Web. The whole system offers a tool to help the user undertaking information foraging. We implemented the system using a group of cooperative reactive agents and more precisely a colony of artificial bees. In order to validate our proposal, experiments were conducted on MedlinePlus, a benchmark dedicated for research in the domain of Health. The results are promising either for those related to Web regularities and for the response time, which is very short and hence complies the real time constraint.

A Novel Framework for Medical Web Information Foraging Using Hybrid ACO and Tabu Search.

We present in this paper a novel approach based on multi-agent technology for Web information foraging. We proposed for this purpose an architecture in which we distinguish two important phases. The first one is a learning process for localizing the most relevant pages that might interest the user. This is performed on a fixed instance of the Web. The second takes into account the openness and dynamicity of the Web. It consists on an incremental learning starting from the result of the first phase and reshaping the outcomes taking into account the changes that undergoes the Web. The system was implemented using a colony of artificial ants hybridized with tabu search in order to achieve more effectiveness and efficiency. To validate our proposal, experiments were conducted on MedlinePlus, a real website dedicated for research in the domain of Health in contrast to other previous works where experiments were performed on web logs datasets. The main results are promising either for those related to strong Web regularities and for the response time, which is very short and hence complies the real time constraint.