Figures & data
Figure 1. Architecture of the proposed collaborative training model Text GCN-SW-KNN by cooperating ML-KNN and text GCN-SW, where the first two tiers show the working mechanism of Text GCN-SW
![Figure 1. Architecture of the proposed collaborative training model Text GCN-SW-KNN by cooperating ML-KNN and text GCN-SW, where the first two tiers show the working mechanism of Text GCN-SW](/cms/asset/5c0281bc-1068-4240-8301-9b7e2a25bb16/tbed_a_1877434_f0001_c.jpg)
Figure 2. Exemplary shortest path between feature words and theme within SWEET and WordNet. (a) Feature word A is included in SWEET; (b) Feature word is not included in SWEET but in WordNet; (c) Feature word A and alternative word B are two subclasses away; (d) Feature word A and Theme T are two subclasses away
![Figure 2. Exemplary shortest path between feature words and theme within SWEET and WordNet. (a) Feature word A is included in SWEET; (b) Feature word A is not included in SWEET but in WordNet; (c) Feature word A and alternative word B are two subclasses away; (d) Feature word A and Theme T are two subclasses away](/cms/asset/35ff1b7b-0b7b-472d-bcf6-d16cde28d6a7/tbed_a_1877434_f0002_c.jpg)
Table 1. Co-training algorithm based on Text GCN-SW and ML-KNN
Figure 3. An exemplary WMS metadata document in XML format, including URL, title, abstract and keyword, etc
![Figure 3. An exemplary WMS metadata document in XML format, including URL, title, abstract and keyword, etc](/cms/asset/4c4f7a03-193c-41f6-a8d7-11dbe56447f6/tbed_a_1877434_f0003_c.jpg)
Figure 4. Frequency histogram of the number of labels for each WMS and each layer on the selected 501 samples
![Figure 4. Frequency histogram of the number of labels for each WMS and each layer on the selected 501 samples](/cms/asset/83172f49-0c57-410f-abf8-746efbb9c7fd/tbed_a_1877434_f0004_c.jpg)
Figure 5. Performance comparison of text GCN-SW-KNN and eight baselines for both service-level and layer-level classification, respectively. (a) is the result for WMS and (b) is for WMS layer
![Figure 5. Performance comparison of text GCN-SW-KNN and eight baselines for both service-level and layer-level classification, respectively. (a) is the result for WMS and (b) is for WMS layer](/cms/asset/b53f5f97-617a-472b-8841-dff8d2ca15c1/tbed_a_1877434_f0005_c.jpg)
Figure 6. Stability of F1-score in repeating experiments for Text GCN and Text GCN-SW. (a) is the result for WMS and (b) is for WMS layer
![Figure 6. Stability of F1-score in repeating experiments for Text GCN and Text GCN-SW. (a) is the result for WMS and (b) is for WMS layer](/cms/asset/68e4cbb8-ee75-4752-8447-b9f0b5089b10/tbed_a_1877434_f0006_c.jpg)
Figure 7. Accuracy and F1 for Text GCN, Text GCN-SW, ML-KNN and LSTM with different proportions of the training data: (a) is for WMS and (b) is for WMS layer
![Figure 7. Accuracy and F1 for Text GCN, Text GCN-SW, ML-KNN and LSTM with different proportions of the training data: (a) is for WMS and (b) is for WMS layer](/cms/asset/16329724-8d32-4fbe-8805-0ef274eb0b49/tbed_a_1877434_f0007_c.jpg)
Table A1. Performance metrics of text GCN-SW-KNN and eight baselines for WMS service-level classification
Table A2. Performance metrics of text GCN-SW-KNN and eight baselines for WMS layer-level classification
Data availability statement
The code and data that support the findings of this study are openly available in GitHub at https://github.com/ZPGuiGroupWhu/Text-based-WMS-Application-Theme-Classification/tree/master.