Search (3 results, page 1 of 1)

  • × author_ss:"Xu, L."
  1. Wei, M.; Xu, L.: Boolean mapping algorithms across heterogeneous information sources (1998) 0.00 
    0.0024318986 = product of:
  0.004863797 = sum of:
    0.004863797 = product of:
      0.009727594 = sum of:
        0.009727594 = weight(_text_:a in 3293) [ClassicSimilarity], result of:
          0.009727594 = score(doc=3293,freq=8.0), product of:
            0.04772363 = queryWeight, product of:
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.041389145 = queryNorm
            0.20383182 = fieldWeight in 3293, product of:
              2.828427 = tf(freq=8.0), with freq of:
                8.0 = termFreq=8.0
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.0625 = fieldNorm(doc=3293)
      0.5 = coord(1/2)
  0.5 = coord(1/2)
    Abstract
    Notes the difficulties of searching over heterogeneous information sources where query languages are not unifrom. Presents a model where Boolean queries are composed in one rich front end language. For each query and target source, the query is transformed into a subsuming query that can be supported by the source but may return extra documents. The results are then processed by a filter query to yield the correct results
    Type
    a
  2. Xu, L.; Qiu, J.: Unsupervised multi-class sentiment classification approach (2019) 0.00 
    0.002149515 = product of:
  0.00429903 = sum of:
    0.00429903 = product of:
      0.00859806 = sum of:
        0.00859806 = weight(_text_:a in 5003) [ClassicSimilarity], result of:
          0.00859806 = score(doc=5003,freq=16.0), product of:
            0.04772363 = queryWeight, product of:
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.041389145 = queryNorm
            0.18016359 = fieldWeight in 5003, product of:
              4.0 = tf(freq=16.0), with freq of:
                16.0 = termFreq=16.0
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.0390625 = fieldNorm(doc=5003)
      0.5 = coord(1/2)
  0.5 = coord(1/2)
    Abstract
    Real-time and accurate multi-class sentiment classification serves as a tool to gauge public user experiences and provide a decision-making basis for timely analysis. In the field of sentiment classification, there is an urgent need for an accurate and efficient multi-class sentiment classification method. With the aim to overcome the drawbacks of the existing methods, we propose a novel, unsupervised multi-class sentiment classification method called Gaussian mixture model of multi-class sentiment classification (GMSC). Based on the Gaussian mixture model (GMM), the GMSC consists of the following essential phases: first, combining a dictionary with microblog texts to calculate and construct the feature matrix of sentiment for each sample; second, introducing a dimension reduction method to avoid the in-fluence of a sparse feature matrix on the results; third, modeling the multi-class sentiment classification procedure based on GMM; and lastly, computing the probability distribution of different categories of sentiment by using GMM to partition sentiments in microblogs into distinct components and classify them via a Gaussian process regression. The results indicate the GMSC approach's accuracy is better and manual tagging time is reduced when compared to semi-supervised and unsupervised sentiment classification methods within the same parameters.
    Type
    a
  3. Xu, L.: Research synthesis methods and library and information science : shared problems, limited diffusion (2016) 0.00 
    0.0020106873 = product of:
  0.0040213745 = sum of:
    0.0040213745 = product of:
      0.008042749 = sum of:
        0.008042749 = weight(_text_:a in 3057) [ClassicSimilarity], result of:
          0.008042749 = score(doc=3057,freq=14.0), product of:
            0.04772363 = queryWeight, product of:
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.041389145 = queryNorm
            0.1685276 = fieldWeight in 3057, product of:
              3.7416575 = tf(freq=14.0), with freq of:
                14.0 = termFreq=14.0
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.0390625 = fieldNorm(doc=3057)
      0.5 = coord(1/2)
  0.5 = coord(1/2)
    Abstract
    Interests of researchers who engage with research synthesis methods (RSM) intersect with library and information science (LIS) research and practice. This intersection is described by a summary of conceptualizations of research synthesis in a diverse set of research fields and in the context of Swanson's (1986) discussion of undiscovered public knowledge. Through a selective literature review, research topics that intersect with LIS and RSM are outlined. Topics identified include open access, information retrieval, bias and research information ethics, referencing practices, citation patterns, and data science. Subsequently, bibliometrics and topic modeling are used to present a systematic overview of the visibility of RSM in LIS. This analysis indicates that RSM became visible in LIS in the 1980s. Overall, LIS research has drawn substantially from general and internal medicine, the field's own literature, and business; and is drawn on by health and medical sciences, computing, and business. Through this analytical overview, it is confirmed that research synthesis is more visible in the health and medical literature in LIS; but suggests that, LIS, as a meta-science, has the potential to make substantive contributions to a broader variety of fields in the context of topics related to research synthesis methods.
    Type
    a

Authors

Years

Languages