Authors:Xinhai Liu, Wolfgang Glänzel, and Bart De Moor
, creative and business. Consequently, the combination of textual data and citation data is thought as a promising method to deal with scientific publication. Some hybrid clustering has been carried out, such as Janssens et al. ( 2006a , b ) put forward a
Authors:Xinhai Liu, Wolfgang Glänzel, and Bart De Moor
and by which venues, extract “hot topics” and predict trends. Hybrid clustering refers to the clustering of the same class of entities with multi-view representations, either from various information sources or from different feature generators (we
Authors:Ji-ping Gao, Kun Ding, Li Teng, and Jie Pang
subsequent technology. It can't reveal the exact interaction between science and technology.
Here the paper aims to deploy a method called hybrid documents co-citation analysis (HDCCA) to overcome the above weakness. And in the whole paper, we first
the growth stage following the initial stage of its introduction, and technologies which have only recently entered into its growth stage are particularly helpful in facilitating measurements. In the case of the US market, the case of hybrid
Authors:Frizo Janssens, Wolfgang Glänzel, and Bart De Moor
Previous studies have shown that hybrid clustering methods that incorporate textual content and bibliometric information can
outperform clustering methods that use only one of these components. In this paper we apply a hybrid clustering method based
on Fisher’s inverse chisquare to integrate full-text with citations and to provide a mapping of the field of information science.
We quantitatively and qualitatively asses the added value of such an integrated analysis and we investigate whether the clustering
outcome is a better representation of the field by comparing with a text-only clustering and with another hybrid method based
on linear combination of distance matrices. Our data set consists of almost 1000 articles and notes published in the period
2002–2004 in 5 representative journals. The optimal number of clusters for the field is 5, determined by using a combination
of distance-based and stability-based methods. Term networks present the cognitive structure of the field and are complemented
by the most representative publications. Three large traditional sub-disciplines, particularly, information retrieval, bibliometrics/scientometrics,
and more social aspects, and two smaller clusters about patent analysis and webometrics, can be distinguished.
Authors:Patricia Laurens, Michel Zitt, and Elise Bassecoulard
In advanced methods of delineation and mapping of scientific fields, hybrid methods open a promising path to the capitalisation
of advantages of approaches based on words and citations. One way to validate the hybrid approaches is to work in cooperation
with experts of the fields under scrutiny. We report here an experiment in the field of genomics, where a corpus of documents
has been built by a hybrid citation-lexical method, and then clustered into research themes. Experts of the field were associated
in the various stages of the process: lexical queries for building the initial set of documents, the seed; citation-based
extension aiming at reducing silence; final clustering to identify noise and allow discussion on border areas. The analysis
of experts’ advices show a high level of validation of the process, which combines a high-precision and low-recall seed, obtained
by journal and lexical queries, and a citation-based extension enhancing the recall. This findings on the genomics field suggest
that hybrid methods can efficiently retrieve a corpus of relevant literature, even in complex and emerging fields.
Authors:Martin Meyer, Tatiana Siniläinen, and Jan Utecht
This paper presents work directed at capturing the entrepreneurial and collaborative activity of university researchers. The Triple Helix points to the emergence of the entrepreneurial university as well as to an increasing overlay of activities in universities, industry and government. This study explores ways in which patent-based metrics could be utilized in a Triple Helix context, and how hybrid indicators could be developed by combining patent with survey data. More specifically, it aims to develop indicators that connect technological inventiveness of university researchers to both funding organizations and users, as well as to entrepreneurial activities by academics. The paper develops a simplified model of the innovation process to benchmark the relevance of the indicators to the Triple Helix. An analysis of Finnish academic patents illustrates that patent data can already provide useful indicators but, on its own, cannot provide information about how academic patents are interconnected with government or industry through funding or utilization links. An exclusive analysis of patents can point to patent concentrations on certain universities, to inventors and assignees, or to potential gaps in translating applied science into industrial technology. However, the patent data had to be combined with an inventor survey in order to relate academic patents more to their Triple Helix environment. The survey indicated that most patented academic inventions are connected to (often publicly funded) scientific research by the inventors and tend to be utilized in large firms rather than in start-up companies founded by academic entrepreneurs.
some of these limitations. The advantage of the combination of text-based methods with citation-based techniques have soon been recognised (cf. Braam et al. 1991a , b ; Zitt and Bassecoulard 1994 ). The superiority of such hybrid methods over text
Analysis of research foci
An analysis of terms such as keywords can help us identify hot topics of pervasive and ubiquitous computing research. Figure 10 shows a hybrid network of keywords and noun phrases with 241 nodes and 988 links. Keywords
is discussed in “ The literature overview ” section. A hybrid approach is proposed in “ A hybrid model ” section. An empirical research is conducted in “ An empirical research ” section. Conclusions are in the last section.