The normalized TF is calculated by dividing the frequency of the term in the document by the frequency of the most frequent term in a document.
A wordcloud (Fig. 2) was generated using text analysis software (Voyant Tools v. 1.0), which presents more frequent terms in a larger font size.
In the following we will either refer to a topic by its ID (0 99) assigned by the topic modelling algorithm or labels that we assigned on inspection of the most frequent terms in a topic.
In this regard, the contribution of the term provides higher ranking to those terms that appear in few documents, not considering very rare or very frequent terms in the collection, as shown in Equation 11. tc t j = ∑ x = 1 D ∑ y = 1 D f d x, t j × idf t j × f d x, t j × idf t j (11).
According to the database (http://archive.geneontol ogy.org/latest-termdb/go_daily-termdb.rdf-xml.gz), there are three GO terms (i.e. Cellular component, Biological process and Molecular function) in the first level, and 60 terms in the second level, of which 11 most frequent terms in training data were used to build 12 binary classifiers (one for 'other' class) to assign the most relevant terms.
Clinical governance is one of the most frequent terms encountered in health care management, in both the national health services and private healthcare systems.
With improvements in immunosuppressive regimens that prolong patient and graft survival, neoplastic disease has developed into a frequent long-term complication in kidney recipients.
19 A frequent long-term complication in patients exposed to SM is delayed neuropathic symptoms, which are underrepresented in most previous studies.
These filtered terms are called as semantic similar frequent terms available in the document collection using the method ComputeSemanticSimilar(T i ).
In particular, we analyze the most engaged SBBD authors, the number of distinct authors, institutions, and published papers, and the evolution of some of the most frequent terms presented in the titles of the papers.
