@InProceedings{CarvalhoBorg:2021:CoStTe,
               author = "Carvalho, Hevelyn Sthefany Lima de and Borges, Vinicius Ruela 
                         Pereira",
          affiliation = "{University of Bras{\'{\i}}lia} and {University of 
                         Bras{\'{\i}}lia}",
                title = "A Comparative Study of Text Document Representation Approaches 
                         Using Point Placement-based Visualizations",
            booktitle = "Proceedings...",
                 year = "2021",
               editor = "Paiva, Afonso and Menotti, David and Baranoski, Gladimir V. G. and 
                         Proen{\c{c}}a, Hugo Pedro and Junior, Antonio Lopes Apolinario 
                         and Papa, Jo{\~a}o Paulo and Pagliosa, Paulo and dos Santos, 
                         Thiago Oliveira and e S{\'a}, Asla Medeiros and da Silveira, 
                         Thiago Lopes Trugillo and Brazil, Emilio Vital and Ponti, Moacir 
                         A. and Fernandes, Leandro A. F. and Avila, Sandra",
         organization = "Conference on Graphics, Patterns and Images, 34. (SIBGRAPI)",
            publisher = "Sociedade Brasileira de Computa{\c{c}}{\~a}o",
              address = "Porto Alegre",
             keywords = "visualization, word-embedding, feature extraction, text, 
                         multidimensional scaling.",
             abstract = "In natural language processing, text representation plays an 
                         important role which can affect the performance of language models 
                         and machine learning algorithms. Basic vector space models, such 
                         as the term frequency-inverse document frequency, became popular 
                         approaches to represent text documents. In the last years, 
                         approaches based on word embeddings have been proposed to preserve 
                         the meaning and semantic relations of words, phrases and texts. In 
                         this paper, we focus on studying the influences of different text 
                         representations to the quality of layouts generated by 
                         state-of-art visualizations based on point placement. For that 
                         purpose, a visualization-assisted approach is proposed to support 
                         users when exploring such representations in classification tasks. 
                         Experimental results using two public labeled corpora were 
                         conducted to assess the quality of the layouts and to discuss 
                         possible relations to the classification performances. The results 
                         are promising, indicating that the proposed approach can guide 
                         users to understand the relevant patterns of a corpus in each 
                         representation.",
  conference-location = "Gramado, RS, Brazil (virtual)",
      conference-year = "18-22 Oct. 2021",
             language = "en",
                  ibi = "8JMKD3MGPEW34M/45E54GS",
                  url = "http://urlib.net/ibi/8JMKD3MGPEW34M/45E54GS",
           targetfile = "WUW-9.pdf",
        urlaccessdate = "2024, May 06"
}