Multiple studies have investigated bibliometric factors predictive of the citation count a research article will receive. In this article, we go beyond bibliometric data by using a range of machine learning techniques to find patterns predictive of citation count using both article content and available metadata. As the input collection, we use the CORD-19 corpus containing research articles-mostly from biology and medicine-applicable to the COVID-19 crisis. Our study employs a combination of state-of-the-art machine learning techniques for text understanding, including embeddings-based language model BERT, several systems for detection and semantic expansion of entities: ConceptNet, Pubtator and ScispaCy. To interpret the resulting models, we use several explanation algorithms: random forest feature importance, LIME, and Shapley values. We compare the performance and comprehensibility of models obtained by "black-box" machine learning algorithms (neural networks and random forests) with models built with rule learning (CORELS, CBA), which are intrinsically explainable. Multiple rules were discovered, which referred to biomedical entities of potential interest. Of the rules with the highest lift measure, several rules pointed to dipeptidyl peptidase4 (DPP4), a known MERS-CoV receptor and a critical determinant of camel to human transmission of the camel coronavirus (MERS-CoV). Some other interesting patterns related to the type of animal investigated were found. Articles referring to bats and camels tend to draw citations, while articles referring to most other animal species related to coronavirus are lowly cited. Bat coronavirus is the only other virus from a non-human species in the betaB clade along with the SARS-CoV and SARS-CoV-2 viruses. MERS-CoV is in a sister betaC clade, also close to human SARS coronaviruses. Thus both species linked to high citation counts harbor coronaviruses which are more phylogenetically similar to human SARS viruses. On the other hand, feline (FIPV, FCOV) and canine coronaviruses (CCOV) are in the alpha coronavirus clade and more distant from the betaB clade with human SARS viruses. Other results include detection of apparent citation bias favouring authors with western sounding names. Equal performance of TF-IDF weights and binary word incidence matrix was observed, with the latter resulting in better interpretability. The best predictive performance was obtained with a "black-box" method-neural network. The rule-based models led to most insights, especially when coupled with text representation using semantic entity detection methods. Follow-up work should focus on the analysis of citation patterns in the context of phylogenetic trees, as well on patterns referring to DPP4, which is currently considered as a SARS-Cov-2 therapeutic target.

• Publication type
• Journal Article MeSH

Automated sentiment analysis is becoming increasingly recognized due to the growing importance of social media and e-commerce platform review websites. Deep neural networks outperform traditional lexicon-based and machine learning methods by effectively exploiting contextual word embeddings to generate dense document representation. However, this representation model is not fully adequate to capture topical semantics and the sentiment polarity of words. To overcome these problems, a novel sentiment analysis model is proposed that utilizes richer document representations of word-emotion associations and topic models, which is the main computational novelty of this study. The sentiment analysis model integrates word embeddings with lexicon-based sentiment and emotion indicators, including negations and emoticons, and to further improve its performance, a topic modeling component is utilized together with a bag-of-words model based on a supervised term weighting scheme. The effectiveness of the proposed model is evaluated using large datasets of Amazon product reviews and hotel reviews. Experimental results prove that the proposed document representation is valid for the sentiment analysis of product and hotel reviews, irrespective of their class imbalance. The results also show that the proposed model improves on existing machine learning methods.

• MeSH
• Algorithms * MeSH
• Emotions MeSH
• Humans MeSH
• Neural Networks, Computer * MeSH
• Semantics MeSH
• Machine Learning MeSH
• Check Tag
• Humans MeSH
• Publication type
• Journal Article MeSH

OBJECTIVE: The aim of the present study was to investigate if prospective memory (PM) is impaired in idiopathic rapid eye movement (REM) sleep behavior disorder (iRBD). RBD is a parasomnia characterized by dream enactment and by REM sleep without muscle atonia. iRBD is considered as the initial stage of neurodegeneration with pathological storage of alpha-synuclein. METHOD: Sixty iRBD patients with polysomnography-confirmed RBD without parkinsonism and dementia and 30 demographically matched normal controls (NC) were enrolled in the present study. Clinical assessment included Movement Disorders Society-Unified Parkinson's Disease Rating Scale (MDS-UPDRS), dopamine transporter single-photon emission computed tomography (DaT-SPECT) for imaging synapses of dopaminergic neurons in the striatum and a neuropsychological battery with embedded time-based and event-based PM measures. RESULTS: iRBD differed significantly from NC in event-based PM, a number of event-based failures to recall intention and total PM performance (all p < .001) but did not differ in time-based PM and recognition. PM did not contribute to impairment of instrumental activities of daily living in iRBD. Despite being preserved in iRBD in comparison to NC, time-based PM correlated significantly with dopaminergic neuronal loss measured by DaT-SPECT. CONCLUSIONS: We show evidence for a differential pattern of PM impairment in iRBD with severe impairment of event-based and concurrent preservation of time-based PM. We theorize that event-based PM impairment in iRBD is caused by severe impairment of retention and recognition mechanisms in episodic memory whereas time-based PM seems to be affected by reduced striatal dopaminergic synapses.

• MeSH
• Activities of Daily Living psychology   MeSH
• Memory, Episodic * MeSH
• Tomography, Emission-Computed, Single-Photon methods   MeSH
• Middle Aged MeSH
• Humans MeSH
• Neuropsychological Tests MeSH
• Polysomnography methods   MeSH
• REM Sleep Behavior Disorder diagnostic imaging   epidemiology   psychology   MeSH
• Memory Disorders diagnostic imaging   epidemiology   psychology   MeSH
• Aged MeSH
• Check Tag
• Middle Aged MeSH
• Humans MeSH
• Male MeSH
• Aged MeSH
• Female MeSH
• Publication type
• Journal Article MeSH
• Research Support, Non-U.S. Gov't MeSH

Na Masarykově univerzitě v současné době studuje 450 studentů se specifickými nároky (stav ke 31. 1. 2013), což je nejvíce mezi veřejnými vysokými školami v ČR. Jedná se převážně o studenty s postižením pohybovým, zrakovým, sluchovým ale i další. Stejně jako ostatní studenti mají právo, ač je otázka zda je vhodné takto slovo právo v takovéto souvislosti použít, na plnohodnotné zapojení do všech aktivit, které se studiem souvisejí, tzn. také do aktivit v oblasti tělesné výchovy a sportu. Tato práva vycházejí nejen z všeobecné legislativy, ale jsou v rámci Masarykovy univerzity ukotvena i v interních dokumentech (např. Směrnice o studiu osob se specifickými nároky – Směrnice č. 04/03). Značnou část úkolů, které s naplňováním těchto práv souvisí (obecně se hovoří o zpřístupnění studia), v praxi zajišťuje celouniverzitní pracoviště – Středisko pro pomoc studentům se specifickými nároky MU, Teiresiás. V oblasti tělesné výchovy a sportu se jedná (vždy dle potřeby) jednak o zajištění podmínek pro zpřístupnění standardní výuky tělesné výchovy a standardně nabízených sportovních aktivit a dále o vytváření vhodných alternativ, není-li zpřístupnění standardní nabídky z hlediska technického, metodologického aj. vhodné. V posledních letech se na Masarykově univerzitě aktivně zapojuje do sportovní činnosti (ať již standardní nebo alternativní) v průměru 37 řádných studentů se specifickými nároky za semestr, z toho někteří si zapíší více předmětů tělesné výchovy v jednom semestru. Zajištění přístupnosti znamená v praxi vyřešit řadu překážek na straně personální, na straně materiálního vybavení, dále přístupnosti budov a jejich částí, ale také např. v oblasti vhodné studijní podpory (přístupnost didaktických a studijních materiálů). Vedlo toho je někdy nezbytná také intervence v oblasti motivace studentů se specifickými nároky. Veškeré tyto aktivity se neobejdou bez odpovídající spolupráce, která je interně nezbytná především s Centrem univerzitního sportu Fakulty sportovních studií Masarykovy univerzity a externě pak s dalšími státními i nestátními institucemi.

As of January 31, 2013, there are 450 special needs students currently studying at Masaryk University. This is the largest number of students with special needs among all Czech universities. These are students with visual, hearing or mobility impairment or other disabilities. As well as others, these students have the right (though the use of the word in this context is disputable) to fully participate in all activities pertaining to their studies, which include Physical Education and sports activities. These rights are not only contained in the general legislature, but they are also embedded in Masaryk University’s internal documents (e. g. Rector’s Directive on the Studies of Persons with Special Needs – Rector’s Directive No. 04/03). A substantial part of the tasks connected with fulfilling these rights (and therefore ensuring accessibility of studies) is provided by Teiresias – the Support Centre for Students with Special Needs at Masaryk University. In the area of Physical Education and sports, this involves providing the conditions for accessibility of standard Physical Education and sports activities and creating alternative solutions if the former proves unsuitable for any reason (technical, methodological etc.). On the average, 37 special needs students a semester have been participating in sports activities (standard or alternative) in recent years; with some of them taking more than one Physical Education course in a semester. Providing accessibility encompasses a number of obstacles; there are personnel issues, issues of material and equipment, accessibility of university buildings or suitable didactic and study materials. Sometimes also intervention into the motivation of special needs students is necessary. The activities of Teiresias are based on internal cooperation with the University Sports Centre of the Faculty of Sports, Masaryk University, and external cooperation with both governmental and non-governmental institutions.

• MeSH
• Architectural Accessibility MeSH
• Humans MeSH
• Local Government MeSH
• Motivation MeSH
• Organization and Administration MeSH
• Motor Activity MeSH
• Persons with Disabilities MeSH
• Sports for Persons with Disabilities * MeSH
• Students MeSH
• Physical Education and Training * organization & administration   MeSH
• Universities * organization & administration   MeSH
• Check Tag
• Humans MeSH

• MeSH
• Philosophy MeSH
• Linguistics MeSH

• Conspectus
• Věda. Všeobecnosti. Základy vědy a kultury. Vědecká práce
• NML Fields
• lingvistika, lékařská terminologie
• humanitní vědy a umění

• MeSH
• Dementia therapy   MeSH
• Mental Disorders therapy   MeSH
• Kinesiology, Applied MeSH
• Psychiatry MeSH
• Schizophrenia therapy   MeSH
• Exercise Movement Techniques MeSH
• Dependency, Psychological therapy   MeSH

• Conspectus
• Psychiatrie
• NML Fields
• psychiatrie
• terapie
• NML Publication type
• učebnice vysokých škol