Paper journal coupling analysis

Paper journal coupling clustering finds groups of paper journals that tend to cite the same reference journals. The clustering is accomplished by building a cooccurrence matrix of paper journals relative to reference journals. Cooccurrence counts are calculated using the overlap function. Similarities based on these cooccurrence counts are used as proximities in the clustering routine. Such clustering tends to identify the groups of paper journals that have papers that tend to use base knowledge from the same reference journals.

Loading the paper to paper journal matrix

• Prior to journal cocitation clustering, it is necessary to load the paper to paper journal matrix from the database. To do this, on the TFGUI window select Journals > load paper to paper journal matrix. In the MATLAB command window, a few processing messges will appear, and a final message finished loading paper to paper journal matrix.

Loading the paper journal to reference journal matrix.

• After loading the paper to paper journal matrix, it is necesary to load the paper to reference journal matrix. Instructions for doing this are at the journal cocitation analysis page.

Calculating the paper journal to reference journal matrix.

With both the paper to paper journal matrix loaded, and the paper to reference journal matrix loaded, to produce the paper journal to reference journal matrix, on the TFGUI window, select Journals > Load paper journal to reference journal matrix. After calculating and storing the matrix, the message done generating paper journal to reference journal matrix will appear in the MATLAB command window.

Journal coupling clustering

• The paper journal to reference journal matrix must be loaded into DIVA before journal coupling clustering can be performed. See the previous paragraph.
• In the TFGUI window, go to the Journals menu and select cluster paper journals by reference journals. The cooccur_gui will appear. The primary entity will be paper journal and the secondary entity will be reference journal. This means that paper journals will be clustered on cooccurrence in reference journals.
• Coocurrence of paper journals should be performed using the overlap function. Make sure the use overlap toggle button on the cooccur_gui window is selected.
• If the number of paper journals to cluster is greater than the number of clusters specified in coocur_gui, then DIVA will produce the number of clusters specified. Otherwise DIVA will produce clusters down to individual paper journals, whatever that number is.
• It is normally best to cluster down to individual paper journals, with the number of paper journals between 50 to 200 depending on the size of the dataset. A good rule of thumb is to use 50 paper journals per 500 papers in the dataset.
• In journal coupling clustering the occurrence threshold corresponds to the minimum number of papers associated with a paper journal. Paper journals with more papers than the occurrence threshold are retained.
• You should experiment with the occurence threshold to get close to the desired number of retained paper journals.
• Set the occurence threshold, click on Execute. An overwrite dialog will appear, click OK on this, then a dialog will appear telling the number of items (paper journals) that will be clustered, and asking whether to continue.
• If the number of items is too few, click NO and go back and reduce the coocurrence threshold, if too few, click NO and increase the threashold. If the number of items that will be clustered is close to the desired number, then click Yes and clustering will proceed.
• Clustering will proceed quickly, but simulated annealing to seriate the dendrogram may take very long if many items are to be clustered.

Go to Make RF to paper journal crossmap