… documents—the representations of documents we use, the selected classification algorithms,
and the description of the corpora… of documents and the two corpora employed in this work, …

… consists in the classification of the two corpora presented in Section 3.1 … documents
represented as bags-of-concepts. First, it is necessary to obtain the BoC representation of documents…

… For the classification of the corpora we used several algorithms in order to observe which
one performs the best for each corpus: Linear Support Vector Machines [17], Random Forest […

… news articles published at different dates shows the power of the proposed method on
comparing sets of documents… and is thus not scalable to large corpora. Our proposed CDA is fully …

… news corpora with sentiment annotation on three levels of granularity: sentence, paragraph
and document … The corpora contain more than 250,000 documents with political, business, …

… For different corpora, the best model is related to the number of topics. Perplexity value can
… 18 and 20, when using LSTM networks for news classification, the “word-document” matrix …

… with a collection of 487,000 news stories. Each news story was manually classified into four
… , we also provide training corpora of 2 000, 5 000 and 10 000 documents.The development …

… News Classification. In this experiment, we evaluate NewsEmbed in the setting of document
classification. … These include several semantic textual similarity corpora in the news domain, …

… document classification. In order to increase the variety of feature sets for classification,
we transform a document using three document representation methods: term frequency–inverse …

… corpora mainly extracted from news websites. These corpora are used to train and test
classification … Arabic corpus for text classification whose documents are automatically increasing. …