@InProceedings{HirotaSantRaddThak:2016:MiSDSk,
               author = "Hirota, Vitor Makiyama and Santos, Rafael Duarte Coelho dos and 
                         Raddick, Jordan and Thakar, Ani",
          affiliation = "{Instituto Nacional de Pesquisas Espaciais (INPE)} and {Instituto 
                         Nacional de Pesquisas Espaciais (INPE)} and {Johns Hopkins 
                         University} and {Johns Hopkins University}",
                title = "Mining the SDSS Skyserver SQL queries log",
            booktitle = "Proceedings...",
                 year = "2016",
               editor = "Broome, Barbara D. and Hanratty, Timothy P. and Hall, David L. and 
                         Llinas, James",
         organization = "Next-Generation Analyst, 4.",
            publisher = "SPIE",
                 note = "Proceedings of the SPIE, v.9851",
             abstract = "SkyServer, the Internet portal for the Sloan Digital Sky Survey 
                         (SDSS) astronomic catalog, provides a set of tools that allows 
                         data access for astronomers and scientific education. One of 
                         SkyServer data access interfaces allows users to enter ad-hoc SQL 
                         statements to query the catalog. SkyServer also presents some 
                         template queries that can be used as basis for more complex 
                         queries. This interface has logged over 330 million queries 
                         submitted since 2001. It is expected that analysis of this data 
                         can be used to investigate usage patterns, identify potential new 
                         classes of queries, find similar queries, etc. and to shed some 
                         light on how users interact with the Sloan Digital Sky Survey data 
                         and how scientists have adopted the new paradigm of e-Science, 
                         which could in turn lead to enhancements on the user interfaces 
                         and experience in general. In this paper we review some approaches 
                         to SQL query mining, apply the traditional techniques used in the 
                         literature and present lessons learned, namely, that the general 
                         text mining approach for feature extraction and clustering does 
                         not seem to be adequate for this type of data, and, most 
                         importantly, we find that this type of analysis can result in very 
                         different queries being clustered together. © (2016) COPYRIGHT 
                         Society of Photo-Optical Instrumentation Engineers (SPIE). 
                         Downloading of the abstract is permitted for personal use only.",
  conference-location = "Baltimore, Maryland",
      conference-year = "17 Apr.",
                  doi = "10.1117/12.2224237",
                  url = "http://dx.doi.org/10.1117/12.2224237",
             language = "en",
           targetfile = "hirota_mining.pdf",
        urlaccessdate = "28 abr. 2024"
}