In the previous posts, we used clustering algorithms such as Yifan Hu to give shape to the communities (fig. 1). We also used centrality measures to identify the important actors in the network.

Communities

Figure 1. Communities in the network.

Those were all generated using Gephi’s algorithm.

Sometiemes we might need to highlight selected nodes or display only specific clusters during our analysis and research. In this post, we will find an efficient way to filter nodes that we want to highlight, and in the next post we will partition the network into different sections.

Step 1: Filter nodes

Let’s continue with the Yifan Hu layout.

  • Make a copy of the yifanhu.gephi file, and rename the copy blackmountain.gephi.
  • Open Gephi and select blackmountain.gephi.

We will filter the poets associated with the Black Mountain School in Donald Allen’s New American Poetry: 1945-1960. You can see the network graph for poets from different schools in Allen’s anthology in the Networking the New American Poetry project.

Basically, we want to color the poet nodes; however, it’s really difficult to find the small nodes, so we will use Gephi’s filter functionality.

  • Go to the Data Laboratory tab, and click on the Label button so that the poet and journal names are sorted alphabetically (fig. 2).
  • On the bottom right, click Add column and name that column to Black Mountain.
  • Next, you can either scroll through the names in the Label column or use Cmd + F (Ctrl + F on Windows) to search for the 11 names below. For each poet, right click on the poet name, select Edit Node. It will bring up the Attributes dialog box. In the last row, replace **<null value>** with bm. The value bm will appear in the column Black Mountain for that poet.
  • Poets associated with the Black Mountain School. Charles Olson, Denise Levertov, Edward Dorn, Joel Oppenheimer, Jonathan Williams, Larry Eigner, Paul Blackburn, Paul Carroll, Robert Duncan, and Robert Creeley.
  • Save the file: File > Save.

Tab the poets with label bm

Figure 2. Tag the 11 Black Mountain poets in the Data Laboratory with the label bm.

Step 2: Color the nodes

We will color these nodes tagged bm.

  • Go to the Overview section.
  • First change all nodes color to gray: Nodes > Color (palette icon) > Unique > Apply.
  • Apply red color to our filtered nodes (fig. 3): Nodes > Color (palette icon) > Partition > Choose an attribute > Black Mountain. Click the bm label to select it, and right click the label again to pop up the Choose a Color dialog box. In the color wheel settings, change Hex: E10000 > Ok.
  • Click Apply in the Nodes panel to color the nodes.
  • Let’s make sure that in the More Settings option below the network graph (fig. 3), we have Edges tab > Edge Color: Source. This will color only the nodes and their edges, not the neighbor nodes.
  • Save the file: File > Save.

Color the filtered nodes

Figure 3. Color the filtered nodes.

Step 3: Export the image

  • Go to the Export option at the bottom left of the screen, click on SVG/PDF/PNG. Change image settings: Click on Options In this dialog box, change Width 6400 > Height 3600 > Ok. Save the image in the begin folder: Save In > gephi-intro folder > begin folder > Files of Type: PNG files > File Name: blackmountain.png. Click Save.
  • Save the file: File > Save.

The result looks like this (fig. 4). We can see that Black Mountain poets published frequently in the Origin journal, that’s why the edges connecting the poets with this journal are thick. Furthermore, they also published, though in low frequency, in many other journals in the network. T his is an important observation because it brings into view the venues where these Black Mountain poets co-appeared—Allen, for example, grouped these poets together because they were publishing together in Origin and the Black Mountain Review only. Go back to the Overview section, and hover over the journal nodes. Now it’s much easier to see the connections of these Black Mountain poets to different journals in the network.

Black mountain poets

Figure 4. Poets associated with the Black Mountain school.