RESUMEN
Automatic eligibility criteria parsing in clinical trials is crucial for cohort recruitment leading to data validity and trial completion. Recent years have witnessed an explosion of powerful machine learning (ML) and natural language processing (NLP) models that can streamline the patient accrual process. In this PRISMA-based scoping review, we comprehensively evaluate existing literature on the application of ML/NLP models for parsing clinical trial eligibility criteria. The review covers 9160 papers published between 2000 and 2024, with 88 publications subjected to data charting along 17 dimensions. Our review indicates insufficient use of state-of-the-art artificial intelligence (AI) models in the analysis of clinical protocols.
RESUMEN
Recent research revealed that several psycho-cognitive processes, such as insensitivity to positive and negative feedback, cognitive rigidity, pessimistic judgment bias, and anxiety, are involved in susceptibility to fake news. All of these processes have been previously associated with depressive disorder and are sensitive to serotoninergic manipulations. In the current study, a link between chronic treatment with the selective serotonin reuptake inhibitor (SSRI) sertraline and susceptibility to true and fake news was examined. Herein, a sample of 1162 participants was recruited via Prolific Academic for an online study. Half of the sample reported taking sertraline (Zoloft) for at least 8 weeks (sertraline group), and the other half confirmed not taking any psychiatric medication (control group). The sertraline group was further divided according to their daily dosage (50, 100, 150, and 200 mg/day). All participants completed a susceptibility to misinformation scale, wherein they were asked to determine the veracity of the presented true and fake news and their willingness to behaviorally engage with the news. The results were compared between those of the sertraline groups and the control group. The results showed that sertraline groups did not differ significantly in the assessment of the truthfulness of information or their ability to discern the truth. However, those taking sertraline appeared to have a significantly increased likelihood of behavioral engagement with the information, and this effect was observed for both true and fake news. The research presented here represents the initial endeavor to comprehend the neurochemical foundation of the susceptibility to misinformation. The association between sertraline treatment and increased behavioral engagement with information observed in this study can be explained in light of previous studies showing positive correlations between serotonin (5-HT) system activity and the inclination to engage in social behaviors. It can also be attributed to the anxiolytic effects of sertraline treatment, which mitigate the fear of social judgment. The heightened behavioral engagement with information in people taking sertraline may, as part of a general phenomenon, also shape their interactions with fake news. Future longitudinal studies should reveal the specificity and exact causality of these interactions.
Asunto(s)
Ansiolíticos , Sertralina , Humanos , Sertralina/farmacología , Sertralina/uso terapéutico , Informe de Investigación , Inhibidores Selectivos de la Recaptación de Serotonina/efectos adversos , Trastornos de Ansiedad/tratamiento farmacológicoRESUMEN
Research suggests that minority-group members sometimes are more susceptible to misinformation. Two complementary studies examined the influence of perceived minority status on susceptibility to misinformation and conspiracy beliefs. In study 1 (n = 2140), the perception of belonging to a minority group, rather than factually belonging to it, was most consistently related with an increased susceptibility to COVID-19 misinformation across national samples from the USA, the UK, Germany and Poland. Specifically, perceiving that one belongs to a gender minority group particularly predicted susceptibility to misinformation when participants factually did not belong to it. In pre-registered study 2 (n = 1823), an experiment aiming to manipulate the minority perceptions of men failed to influence conspiracy beliefs in the predicted direction. However, pre-registered correlational analyses showed that men who view themselves as a gender minority were more prone to gender conspiracy beliefs and exhibited a heightened conspiracy mentality. This effect was correlationally mediated by increased feelings of system identity threat, collective narcissism, group relative deprivation and actively open-minded thinking. Especially, the perception of being a minority in terms of power and influence (as compared to numerically) was linked to these outcomes. We discuss limitations and practical implications for countering misinformation.
RESUMEN
Background: The contemporary media landscape is saturated with the ubiquitous presence of misinformation. One can point to several factors that amplify the spread and dissemination of false information, such as blurring the line between expert and layman's opinions, economic incentives promoting the publication of sensational information, the zero cost of sharing false information, and many more. In this study, we investigate some of the mechanisms of fake news dissemination that have eluded scientific scrutiny: the evaluation of veracity and behavioral engagement with information in light of its factual truthfulness (either true or false), cognitive utility (either enforcing or questioning participants' beliefs), and presentation style (either sober or populistic). Results: Two main results emerge from our experiment. We find that the evaluation of veracity is mostly related to the objective truthfulness of a news item. However, the probability of engagement is more related to the congruence of the information with the participants' preconceived beliefs than to objective truthfulness or information presentation style. Conclusion: We conclude a common notion that the spread of fake news can be limited by fact-checking and educating people might not be entirely true, as people will share fake information as long as it reduces the entropy of their mental models of the world. We also find support for the Trojan Horse hypothesis of fake news dissemination.
RESUMEN
Fighting medical disinformation in the era of the pandemic is an increasingly important problem. Today, automatic systems for assessing the credibility of medical information do not offer sufficient precision, so human supervision and the involvement of medical expert annotators are required. Our work aims to optimize the utilization of medical experts' time. We also equip them with tools for semi-automatic initial verification of the credibility of the annotated content. We introduce a general framework for filtering medical statements that do not require manual evaluation by medical experts, thus focusing annotation efforts on non-credible medical statements. Our framework is based on the construction of filtering classifiers adapted to narrow thematic categories. This allows medical experts to fact-check and identify over two times more non-credible medical statements in a given time interval without applying any changes to the annotation flow. We verify our results across a broad spectrum of medical topic areas. We perform quantitative, as well as exploratory analysis on our output data. We also point out how those filtering classifiers can be modified to provide experts with different types of feedback without any loss of performance.
RESUMEN
Introduction: The rise of social media users and the explosive growth in misinformation shared across social media platforms have become a serious threat to democratic discourse and public health. The mentioned implications have increased the demand for misinformation detection and intervention. To contribute to this challenge, we are presenting a systematic scoping review of psychological interventions countering misinformation in social media. The review was conducted to (i) identify and map evidence on psychological interventions countering misinformation, (ii) compare the viability of the interventions on social media, and (iii) provide guidelines for the development of effective interventions. Methods: A systematic search in three bibliographic databases (PubMed, Embase, and Scopus) and additional searches in Google Scholar and reference lists were conducted. Results: 3,561 records were identified, 75 of which met the eligibility criteria for the inclusion in the final review. The psychological interventions identified during the review can be classified into three categories distinguished by Kozyreva et al.: Boosting, Technocognition, and Nudging, and then into 15 types within these. Most of the studied interventions were not implemented and tested in a real social media environment but under strictly controlled settings or online crowdsourcing platforms. The presented feasibility assessment of implementation insights expressed qualitatively and with numerical scoring could guide the development of future interventions that can be successfully implemented on social media platforms. Discussion: The review provides the basis for further research on psychological interventions counteracting misinformation. Future research on interventions should aim to combine effective Technocognition and Nudging in the user experience of online services. Systematic review registration: [https://figshare.com/], identifier [https://doi.org/10.6084/m9.figshare.14649432.v2].
RESUMEN
BACKGROUND: The spread of false medical information on the web is rapidly accelerating. Establishing the credibility of web-based medical information has become a pressing necessity. Machine learning offers a solution that, when properly deployed, can be an effective tool in fighting medical misinformation on the web. OBJECTIVE: The aim of this study is to present a comprehensive framework for designing and curating machine learning training data sets for web-based medical information credibility assessment. We show how to construct the annotation process. Our main objective is to support researchers from the medical and computer science communities. We offer guidelines on the preparation of data sets for machine learning models that can fight medical misinformation. METHODS: We begin by providing the annotation protocol for medical experts involved in medical sentence credibility evaluation. The protocol is based on a qualitative study of our experimental data. To address the problem of insufficient initial labels, we propose a preprocessing pipeline for the batch of sentences to be assessed. It consists of representation learning, clustering, and reranking. We call this process active annotation. RESULTS: We collected more than 10,000 annotations of statements related to selected medical subjects (psychiatry, cholesterol, autism, antibiotics, vaccines, steroids, birth methods, and food allergy testing) for less than US $7000 by employing 9 highly qualified annotators (certified medical professionals), and we release this data set to the general public. We developed an active annotation framework for more efficient annotation of noncredible medical statements. The application of qualitative analysis resulted in a better annotation protocol for our future efforts in data set creation. CONCLUSIONS: The results of the qualitative analysis support our claims of the efficacy of the presented method.
RESUMEN
We claim that networks are created according to the priority attachment mechanism. We introduce a simple model, which uses the priority attachment to generate both synthetic and close to empirical networks. Priority attachment is a mechanism, which generalizes previously proposed mechanisms, such as small world creation or preferential attachment, but we also observe its presence in a range of real-world networks. In this paper, we show that by using priority attachment we can generate networks of very diverse topologies, as well as re-create empirical ones. An additional advantage of the priority attachment mechanism is an easy interpretation of the latent processes of network formation. We substantiate our claims by performing numerical experiments on both synthetic and empirical networks. The two main contributions of the paper are: the development of the priority attachment mechanism, and the design of Priority Rank: a simple network generative model based on the priority attachment mechanism.
RESUMEN
Graph energy is the energy of the matrix representation of the graph, where the energy of a matrix is the sum of singular values of the matrix. Depending on the definition of a matrix, one can contemplate graph energy, Randic energy, Laplacian energy, distance energy, and many others. Although theoretical properties of various graph energies have been investigated in the past in the areas of mathematics, chemistry, physics, or graph theory, these explorations have been limited to relatively small graphs representing chemical compounds or theoretical graph classes with strictly defined properties. In this paper we investigate the usefulness of the concept of graph energy in the context of large, complex networks. We show that when graph energies are applied to local egocentric networks, the values of these energies correlate strongly with vertex centrality measures. In particular, for some generative network models graph energies tend to correlate strongly with the betweenness and the eigencentrality of vertices. As the exact computation of these centrality measures is expensive and requires global processing of a network, our research opens the possibility of devising efficient algorithms for the estimation of these centrality measures based only on local information.
RESUMEN
Many collections of numbers do not have a uniform distribution of the leading digit, but conform to a very particular pattern known as Benford's distribution. This distribution has been found in numerous areas such as accounting data, voting registers, census data, and even in natural phenomena. Recently it has been reported that Benford's law applies to online social networks. Here we introduce a set of rigorous tests for adherence to Benford's law and apply it to verification of this claim, extending the scope of the experiment to various complex networks and to artificial networks created by several popular generative models. Our findings are that neither for real nor for artificial networks there is sufficient evidence for common conformity of network structural properties with Benford's distribution. We find very weak evidence suggesting that three measures, degree centrality, betweenness centrality and local clustering coefficient, could adhere to Benford's law for scalefree networks but only for very narrow range of their parameters.