Search (4 results, page 1 of 1)

0.038023844 = product of:
  0.114071526 = sum of:
    0.114071526 = sum of:
      0.08220865 = weight(_text_:networks in 2743) [ClassicSimilarity], result of:
        0.08220865 = score(doc=2743,freq=4.0), product of:
          0.22247115 = queryWeight, product of:
            4.72992 = idf(docFreq=1060, maxDocs=44218)
            0.047034867 = queryNorm
          0.369525 = fieldWeight in 2743, product of:
            2.0 = tf(freq=4.0), with freq of:
              4.0 = termFreq=4.0
            4.72992 = idf(docFreq=1060, maxDocs=44218)
            0.0390625 = fieldNorm(doc=2743)
      0.031862877 = weight(_text_:22 in 2743) [ClassicSimilarity], result of:
        0.031862877 = score(doc=2743,freq=2.0), product of:
          0.1647081 = queryWeight, product of:
            3.5018296 = idf(docFreq=3622, maxDocs=44218)
            0.047034867 = queryNorm
          0.19345059 = fieldWeight in 2743, product of:
            1.4142135 = tf(freq=2.0), with freq of:
              2.0 = termFreq=2.0
            3.5018296 = idf(docFreq=3622, maxDocs=44218)
            0.0390625 = fieldNorm(doc=2743)
  0.33333334 = coord(1/3)

Abstract

In this article, we performed a comparative study to investigate the performance of methods for detecting emerging research fronts. Three types of citation network, co-citation, bibliographic coupling, and direct citation, were tested in three research domains, gallium nitride (GaN), complex network (CNW), and carbon nanotube (CNT). Three types of citation network were constructed for each research domain, and the papers in those domains were divided into clusters to detect the research front. We evaluated the performance of each type of citation network in detecting a research front by using the following measures of papers in the cluster: visibility, measured by normalized cluster size, speed, measured by average publication year, and topological relevance, measured by density. Direct citation, which could detect large and young emerging clusters earlier, shows the best performance in detecting a research front, and co-citation shows the worst. Additionally, in direct citation networks, the clustering coefficient was the largest, which suggests that the content similarity of papers connected by direct citations is the greatest and that direct citation networks have the least risk of missing emerging research domains because core papers are included in the largest component.

Date

22. 3.2009 17:52:50

0.020136926 = product of:
  0.060410775 = sum of:
    0.060410775 = product of:
      0.12082155 = sum of:
        0.12082155 = weight(_text_:networks in 286) [ClassicSimilarity], result of:
          0.12082155 = score(doc=286,freq=6.0), product of:
            0.22247115 = queryWeight, product of:
              4.72992 = idf(docFreq=1060, maxDocs=44218)
              0.047034867 = queryNorm
            0.5430886 = fieldWeight in 286, product of:
              2.4494898 = tf(freq=6.0), with freq of:
                6.0 = termFreq=6.0
              4.72992 = idf(docFreq=1060, maxDocs=44218)
              0.046875 = fieldNorm(doc=286)
      0.5 = coord(1/2)
  0.33333334 = coord(1/3)

Abstract

In this article, we investigated the factors determining the capability of academic articles to be cited in the future using a topological analysis of citation networks. The basic idea is that articles that will have many citations were in a "similar" position topologically in the past. To validate this hypothesis, we investigated the correlation between future times cited and three measures of centrality: clustering centrality, closeness centrality, and betweenness centrality. We also analyzed the effect of aging as well as of self-correlation of times cited. Case studies were performed in the two following recent representative innovations: Gallium Nitride and Complex Networks. The results suggest that times cited is the main factor in explaining the near future times cited, and betweenness centrality is correlated with the distant future times cited. The effect of topological position on the capability to be cited is influenced by the migrating phenomenon in which the activated center of research shifts from an existing domain to a new emerging domain.

0.020136926 = product of:
  0.060410775 = sum of:
    0.060410775 = product of:
      0.12082155 = sum of:
        0.12082155 = weight(_text_:networks in 4964) [ClassicSimilarity], result of:
          0.12082155 = score(doc=4964,freq=6.0), product of:
            0.22247115 = queryWeight, product of:
              4.72992 = idf(docFreq=1060, maxDocs=44218)
              0.047034867 = queryNorm
            0.5430886 = fieldWeight in 4964, product of:
              2.4494898 = tf(freq=6.0), with freq of:
                6.0 = termFreq=6.0
              4.72992 = idf(docFreq=1060, maxDocs=44218)
              0.046875 = fieldNorm(doc=4964)
      0.5 = coord(1/2)
  0.33333334 = coord(1/3)

Abstract

In this article, we build models to predict the existence of citations among papers by formulating link prediction for 5 large-scale datasets of citation networks. The supervised machine-learning model is applied with 11 features. As a result, our learner performs very well, with the F1 values of between 0.74 and 0.82. Three features in particular, link-based Jaccard coefficient difference in betweenness centrality, and cosine similarity of term frequency-inverse document frequency vectors, largely affect the predictions of citations. The results also indicate that different models are required for different types of research areas-research fields with a single issue or research fields with multiple issues. In the case of research fields with multiple issues, there are barriers among research fields because our results indicate that papers tend to be cited in each research field locally. Therefore, one must consider the typology of targeted research areas when building models for link prediction in citation networks.

0.011626059 = product of:
  0.034878176 = sum of:
    0.034878176 = product of:
      0.06975635 = sum of:
        0.06975635 = weight(_text_:networks in 77) [ClassicSimilarity], result of:
          0.06975635 = score(doc=77,freq=2.0), product of:
            0.22247115 = queryWeight, product of:
              4.72992 = idf(docFreq=1060, maxDocs=44218)
              0.047034867 = queryNorm
            0.31355235 = fieldWeight in 77, product of:
              1.4142135 = tf(freq=2.0), with freq of:
                2.0 = termFreq=2.0
              4.72992 = idf(docFreq=1060, maxDocs=44218)
              0.046875 = fieldNorm(doc=77)
      0.5 = coord(1/2)
  0.33333334 = coord(1/3)