Performance analysis of text classification algorithms for PubMed articles

dc.contributor.advisorBonenkamp, Koen
dc.contributor.advisorLittle, Francesca
dc.contributor.authorSavvi, Suzana
dc.date.accessioned2022-03-14T05:21:47Z
dc.date.available2022-03-14T05:21:47Z
dc.date.issued2021
dc.date.updated2022-03-14T05:18:11Z
dc.description.abstractThe Medical Subject Headings (MeSH) thesaurus is a controlled vocabulary developed by the US National Library of Medicine (NLM) for indexing articles in Pubmed Central (PMC) archive. The annotation process is a complex and time-consuming task relying on subjective manual assignment of MeSH concepts. Automating such tasks with machine learning may provide a more efficient way of organizing biomedical literature in a less ambiguous way. This research provides a case study which compares the performance of several different machine learning algorithms (Topic Modelling, Random Forest, Logistic Regression, Support Vector Classifiers, Multinomial Naive Bayes, Convolutional Neural Network and Long Short-Term Memory (LSTM)) in reproducing manually assigned MeSH annotations. Records for this study were retrieved from Pubmed using the E-utilities API to the Entrez system of databases at NCBI (National Centre for Biotechnology Information). The MeSH vocabulary is organised in a hierarchical structure and article abstracts labelled with a single MeSH term from the top second two layers were selected for training the machine learning models. Various strategies for text multiclass classification were considered. One was a Chi-square test for feature selection which identified words relevant to each MeSH label. The second approach used Named Entity Recognition (NER) to extract entities from the unstructured text and another approach relied on word embeddings able to capture latent knowledge from literature. At the start of the study text was tokenised using the Term Frequency Inverse Document Frequency (Tf-idf) technique and topic modelling performed with the objective to ascertain the correlation between assigned topics (unsupervised learning task) and MeSH terms in PubMed. Findings revealed the degree of coupling was low although significant. Of all of the classifier models trained, logistic regression on Tf-idf vectorised entities achieved highest accuracy. Performance varied across the different MeSH categories. In conclusion automated curation of articles by abstract may be possible for those target classes classified reliably and reproducibly.
dc.identifier.apacitationSavvi, S. (2021). <i>Performance analysis of text classification algorithms for PubMed articles</i>. (). ,Faculty of Science ,Department of Statistical Sciences. Retrieved from http://hdl.handle.net/11427/36059en_ZA
dc.identifier.chicagocitationSavvi, Suzana. <i>"Performance analysis of text classification algorithms for PubMed articles."</i> ., ,Faculty of Science ,Department of Statistical Sciences, 2021. http://hdl.handle.net/11427/36059en_ZA
dc.identifier.citationSavvi, S. 2021. Performance analysis of text classification algorithms for PubMed articles. . ,Faculty of Science ,Department of Statistical Sciences. http://hdl.handle.net/11427/36059en_ZA
dc.identifier.ris TY - Master Thesis AU - Savvi, Suzana AB - The Medical Subject Headings (MeSH) thesaurus is a controlled vocabulary developed by the US National Library of Medicine (NLM) for indexing articles in Pubmed Central (PMC) archive. The annotation process is a complex and time-consuming task relying on subjective manual assignment of MeSH concepts. Automating such tasks with machine learning may provide a more efficient way of organizing biomedical literature in a less ambiguous way. This research provides a case study which compares the performance of several different machine learning algorithms (Topic Modelling, Random Forest, Logistic Regression, Support Vector Classifiers, Multinomial Naive Bayes, Convolutional Neural Network and Long Short-Term Memory (LSTM)) in reproducing manually assigned MeSH annotations. Records for this study were retrieved from Pubmed using the E-utilities API to the Entrez system of databases at NCBI (National Centre for Biotechnology Information). The MeSH vocabulary is organised in a hierarchical structure and article abstracts labelled with a single MeSH term from the top second two layers were selected for training the machine learning models. Various strategies for text multiclass classification were considered. One was a Chi-square test for feature selection which identified words relevant to each MeSH label. The second approach used Named Entity Recognition (NER) to extract entities from the unstructured text and another approach relied on word embeddings able to capture latent knowledge from literature. At the start of the study text was tokenised using the Term Frequency Inverse Document Frequency (Tf-idf) technique and topic modelling performed with the objective to ascertain the correlation between assigned topics (unsupervised learning task) and MeSH terms in PubMed. Findings revealed the degree of coupling was low although significant. Of all of the classifier models trained, logistic regression on Tf-idf vectorised entities achieved highest accuracy. Performance varied across the different MeSH categories. In conclusion automated curation of articles by abstract may be possible for those target classes classified reliably and reproducibly. DA - 2021 DB - OpenUCT DP - University of Cape Town KW - Statistical Sciences LK - https://open.uct.ac.za PY - 2021 T1 - Performance analysis of text classification algorithms for PubMed articles TI - Performance analysis of text classification algorithms for PubMed articles UR - http://hdl.handle.net/11427/36059 ER - en_ZA
dc.identifier.urihttp://hdl.handle.net/11427/36059
dc.identifier.vancouvercitationSavvi S. Performance analysis of text classification algorithms for PubMed articles. []. ,Faculty of Science ,Department of Statistical Sciences, 2021 [cited yyyy month dd]. Available from: http://hdl.handle.net/11427/36059en_ZA
dc.language.rfc3066eng
dc.publisher.departmentDepartment of Statistical Sciences
dc.publisher.facultyFaculty of Science
dc.subjectStatistical Sciences
dc.titlePerformance analysis of text classification algorithms for PubMed articles
dc.typeMaster Thesis
dc.type.qualificationlevelMasters
dc.type.qualificationlevelMSc
Files
Original bundle
Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
thesis_sci_2021_savvi suzana.pdf
Size:
10.99 MB
Format:
Adobe Portable Document Format
Description:
License bundle
Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
license.txt
Size:
0 B
Format:
Item-specific license agreed upon to submission
Description:
Collections