The dataset used in the experiments was the BioMed Central open-access corpus (BioMed), which can be downloaded at http://www.biomedcentral.com/about/datamining. From the BioMed corpus, 110,369 articles between Jan. 2012 to Jun. 2012 are downloaded. Each BioMed file is a well-formatted XML document, and contains various tags, such as <title>, <bdy>, <issn>, and so on. But there are many articles contain only XML tags and abstracts, so those files of less than 4KB are removed in the pre-processing phase. Then the remaining files are divided into different ‘topics’ according to their journal names and the title, abstract and plain texts are extracted. Finally, the top 10 topics with paper numbers from 1966 to 5022 are selected as the test corpus. The detailed information of these 10 topics are listed in Table 1. In our experiments, to evaluate the performance of the different approaches across different dataset sizes, we randomly select 5 sub-datasets with scales of 400, 500, 600, 700 and 800 on each topic for comparison. And for each scale we randomly select 5 times computation to perform average to avoid accidental results.

Before beginning the clustering process, all journal-name-related information were eliminated from target texts. After clustering, this information was used to evaluate the clustering performance of each algorithm. According to the list in the website: http://norm.al/2009/04/14/list-of-english-stop-words/, the stop words are removed. Then each document is represented by a set of tow-tuples and the whole dataset should have the form indicated as follows:where N is the document number in the dataset, M^j is the term feature (unique words or phrases) number in the jth document, d_i = {<f_i¹, n_i¹>, <f_i², n_i²>,…<f_i^Mi, n_i^Mi>} indicates the ith document, and f_i^k and n_i^k represent the kth term in ith document and its normalized frequency, respectively. Hereinto, the normalized frequency is computed bywhere Count^k_i is the kth term count number in the jth document.

Based on the state-of-the-art unsupervised Affinity Propagation clustering algorithm [19], SSAP method is proposed as means of addressing the complexity problems posed by full text clustering of biomedical publications. In conventional vector space model (VSM) based methods, each document is represented in the feature space constructed by all the unique word or phrase of all the documents. Therefore, the similarities between different document pairs could be computed according to any similarity measurements under the same constructed space. However, this space is high-dimensional and the document representation is serious sparse. To avoid the large dimensions and sparse matrix computation, in the proposed method each document is represented in a tiny sub-space of VSM when computing the similarity between it and another one. The sub-space is spanned by only the features of the related document and its counterpart, which is much smaller than the original vector space. If the dataset includes thousands of words or phrases, the subspace restriction will reduce computational complexity significantly. In the method, the classical similarity measurement in text clustering, namely, Cosine Coefficient similarity is used. To achieve even better performance, a semi-supervision strategy that makes use of known information is introduced. The detailed steps of the SSAP method are as follows:

a. Initialization of dataset: Initializing dataset D = {d₁, d₂,...,d_N} be a superset of N (N>0) elements, where each element consists of a sequence of two-tuples;

b. Seed Construction: Add a small number of initially labeled objects in two-tuple sets to the dataset D, and get a new dataset D′ containing N′ elements (N′≥N).

c. Similarity Computation: Compute the similarities among objects in D′ using the Cosine Coefficient similarity metric:where S(i,j) is the similarity between the ith document and the jth document elements in D′, and |d| represents the unique terms' count number in document d, respectively.

d. Self-Similarity Computation: Compute the self- similarities s(l, l) of each object in D′ using: where , , and i≠j.

e. Initialization of availability matrix: a(i, j) = 0, (i, j  = 1, 2,⋯..., N′).

f. Message Matrix Computation: Compute the message matrices using:

g. Exemplar Selection: Add the two message matrices and search for the exemplar of each object i, defined as the maximizer of r(i, j)+a(i, j).

h. Updating Messages, using:

i. Iterating from Step f to h for a fixed number of iterations or until the exemplar selection remains constant for some number of iterations.

j. Merging Small Clusters with the same labels into larger clusters to produce clustering output.

SSAP is proposed based on Affinity Propagation (AP) method, which was proposed by Frey and Dueck in Science in 2007 [19] and was considered a convinced clustering algorithm in different applications. To investigate the semi-supervised learning performance of SSAP, AP is set as a comparison method in the experiments. K-means was firstly proposed by MacQueen [28] and was recognized as one of the top 10 algorithms in data mining [29]. Especially, it has proven that K-means is a simple but very reliable method in document clustering [30], [31]. Therefore, it is also used as a baseline for comparison.

To evaluate the performance of the three clustering methods—k-means, Affinity Propagation and SSAP, their respective values for F-measure, entropy, and CPU execution time are compared. For information retrieval, entity recognition, and information extraction in particular, F-measure is the most commonly used evaluation measurement. The global F-measure for the entire clustering result is defined as:where N is the total number of documents in the dataset, N_hg is the number of objects of class h in cluster g, N_g is the number of objects of cluster g, and N_h is the number of objects of class h.

In contrast to F-measure, entropy provides a measure of the homogeneity or purity of a cluster. The total entropy for a set of clusters is calculated as:where G is the total number of clusters, H is the number of predefined classes. The smaller the entropy, the better the clustering performance.

The generated clusters with the set of journal-based topic categories in BioMed are examined. To check the effectiveness across different collection sizes, all the three algorithms are applied to the sub-datasets with 5 scales from 400 to 800 and for each scale the sub-datasets are randomly selected 5 times for averaging. All topics in the datasets had discrete uniform distributions, and all experiments were run on a PC equipped with Intel (R) Xeon(R) CPU×3430 @ 2.40 GHz, 2 GB of Ram, and no parallel computing processes.

Based on the SSAP clustering results, an interesting application of our method is demonstrated. Figure 4 describes the relationships among the 10 top biomedical journals yielding a total of 400 articles. Within the graph, each node represents a biomedical journal. If a directed edge from journal A to B exits, it shows that at least two articles of journal A are clustered into the class dominated by journal B, and the weight of the edge represents the count number of the articles.

In Figure 4, it can be seen that most of these journals share topics with other journals. A detailed analysis of the graph shows that “BMC Cancer” gets eight out-degrees, which means that it has outward connections with most of the other journals except for the “Journal of Cardiovascular Magnetic Resonance”. By contrast, the “Journal of Medical Case Reports” has no out-degrees. The median out-degrees of the 10 journals in the network is 3. “BMC Bioinformatics”, “BMC Public Health”, “Malaria Journal” and "Retrovirology” all belong to this group. The out-degrees of “BMC Genomics” and “Journal of Cardiovascular Magnetic Resonance” are 4 and 2, respectively.

Table 3 gives the detailed parameter information of the relationship network. It can be seen that the clustering coefficient is 0.36 which is larger than 0, as most random world networks tend to be, but also much smaller than 1, which is a typical feature of ring-lattice world networks. It can also be noted that the characteristic path length is 1.89, which means that these nodes are well connected. Based on these two parameters, it can be concluded that the relationship network is similar to that of a small world [34].

Table 4 is the result of cluster distribution matrix. The principal diagonal of the table indicates the match number of the clustering results and the journal name of BioMed corpus. They are also the main parts of their clusters. The homologous texts are those belonging to other journals but are recognized under the given cluster label. For example, in cluster 1, there are 19 homologous texts, including nine articles from “BMC Evolutionary Biology”, seven from “BMC Genomics”, and three from “BMC Neuroscience”.

From the experimental results on full text clustering experiments, it can be seen that SSAP is superior to the classical k-means and AP algorithms for full text biomedical literature clustering. With the help of local similarity computing and semi-supervision, SSAP greatly enhances the clustering performance relative to k-means. Applying AP clustering to replace k-means clustering, the two AP-based algorithms obtained higher F-measures and lower entropies. This is due to the fact that the Cosine Coefficient similarity contains both the document's own information and a portion of the mutual information for the two vectors which would have been omitted by Euclidian distance. By introducing the semi-supervised strategy, the SSAP algorithm outperforms the unsupervised AP algorithm, achieving a higher F-measure than AP while maintaining similar computation times. In addition, because the k-means method treats each document as a 54367-dimension vector (i.e. 54367 unique words in 600 texts) using Euclidian distance, the problem is mapped into a large sparse matrix, which dramatically increases the computation time. By contrast, SSAP and AP treat each document as a much smaller vector space (i.e. at most contains 5274-dimension), which allows them to execute much more quickly.

In relationship network analysis, it is assumed that the manuscripts in the same journal share similar topics and have high possibility to be clustered in a same class. However, similar papers may also exist in different journals. Since the selected dataset belongs to a discrete uniform distribution, the edge between two journals in the relationship network can reveal similarity of their publishing scopes and strategies. For example, the scope of “BMC Bioinformatics” is mostly defined by “computational and statistical methods for the modeling and analysis of all kinds of biological data” [35], and it can be seen that the journal has strong relationships with most other BMC series journals, including out-degrees for “BMC Genomics”, “BMC Neuroscience”, and “BMC Evolutionary Biology”, as well as an in-degree with “BMC Cancer”. This is due to the fact that these journals belong to the same publishing company and “BMC Bioinformatics” defines a broad publishing scope, including all computing related models for all kinds of biological data. Moreover, with cancer research attracting so much attention and covering such diverse biomedical topics, the papers published by “BMC Cancer” are featured in many different research areas, including tissue analysis, diagnosis, and treatment of tumors. This explains why the “BMC Cancer” journal forms a central hub connected to most of the other journals. By contrast, the “Journal of Cardiovascular Magnetic Resonance” and “Journal of Medical Case Reports” are more focused on specific fields (e.g., “magnetic resonance methods applied to the cardiovascular system” [36], or “case report that expands the field of general medical knowledge, and original research relating to case reports” [37]). As a result, these journals have fewer in-degrees and fewer out-degrees.

The cluster distribution matrix is an intuitive and informative tool for analysis, from it, it can be noted that the following: