Homepage | Publications | Software | Courseware; indicators | Animation | Geo | Search website (Google) |
Program Combine2.EXE for Mapping Heterogeneous Network Analysis
(Co-word, Co-authorship, and Cited Journals Analysis combined)
This program enables the user to generate a representation of the co-words, coauthorship relations, and journals cited in a document set. Input is a set saved using ISI’s Web of Science, and output is, among others, a file cosine.dat in Pajek format. (Note that this program is different (but derived) from combine.exe available at http://www.leydesdorff.net/software/animation . This latter program uses co-words, co-authors, and journal titles in the document set.)
The input file has to be saved in the tagged format from the Science Citation Index (Social Sciences Citation Index, Arts & Humanities Citation Index) at the Web-of-Science. The default filename “savedrecs.txt” should not be used, but “data.txt” instead. The program is based on DOS-legacy software. It runs in a MS-Dos Command Box under Windows. The programs and the input files have to be contained in the same folder. The output files are written into this directory. Please, note that existing files from a previous run are overwritten by the program. (The user is advised to save output elsewhere if one wishes to continue with these materials.)
The routine creates the asymmetrical occurrence matrix (matrix.dbf which can be read in excel or spss), the symmetrical affiliations (co-occurrence) matrix (coocc.dbf, coocc.dat) and the cosine-normalized output (cosine.dbf, cosine.dat) based on the asymmetrical occurrence matrix. Words which occur only once in the input file are not included. If stopword.txt is made available in the same directory, these words are also excluded. A possible stopword list of 429 words in English is available here. (Originally from http://www.lextek.com/manuals/onix/stopwords1.html. This file has to be renamed “stopword.txt”.) The variable labels are also available in words.dbf; the order is; (1) title words; (2) author names; (3) journal names. The file partition.clu contains the three types of variables in the format of a partition file of Pajek.
The labels in the output files (cosine.dat and coocc.dat) can be edited (using an ASCII editor such as NotePad or WordPad) before feeding the files into Pajek. A series of these matrices can be used for animations (in the dynamic version of Visone, SVG2Pajek or SoNIA) after saving these in Pajek. The necessary steps in between are further explained in this manual.
See for examples: