Exploring supervised and unsupervised methods to detect topics in biomedical text

Abstract

Background: Topic detection is a task that automatically identifies topics (e.g., "biochemistry" and "protein structure") in scientific articles based on information content. Topic detection will benefit many other natural language processing tasks including information retrieval, text summarization and question answering; and is a necessary step towards the building of an information system that provides an efficient way for biologists to seek information from an ocean of literature.

Automated systems to identify relevant documents in product risk management

“…The results showed that the model developed using SVM had the best prediction performance compared to those developed using other algorithms. This is in concordance with other studies which frequently showed that models developed using SVM outperforms those developed using other learning algorithms [20]. …”

“…Semantics refers to the study of 'meanings' linked to their words in linguistic studies [25]. Semantic features could be applied by using MeSH and the Unified Medical Language System (UMLS) concepts and semantic types [12,20]. UMLS is the most extensive known database of synonyms and concepts relations of biomedical and health-related terms, maintained by National Library of Medicine.…”

“…Supervised learning methods were used in this study to develop the models as it had been shown to have better performance than unsupervised learning methods in other studies [20]. In supervised learning, the prediction model was trained to recognize patterns in the abstracts of both 'useful' and 'non-useful' articles.…”

Clustering cliques for graph-based summarization of the biomedical research literature

“…They clustered these into 9 categories, one for each Wikipedia category and one additional cluster. While in reality, it is almost impossible to pre-define the number of the clusters for varied topics in biomedical domain, Lee and colleagues [33] compared supervised and unsupervised methods to detect topics in biomedical texts and found that the performance of supervised topic spotting methods was better. They also found that unsupervised hierarchical clustering was robust and more readily applicable in real world settings.…”

“…When using hierarchical clustering to group documents and generate labels for the clusters, the vector space model is often adopted to produce term or keyword vectors, which help indicate similarity among documents [30,32,33]. Subsequently, documents are clustered into several subgroups, and terms or keywords that are salient for a given cluster are extracted as the theme (or label) for the cluster.…”